ICPRAM 2016 Abstracts


Conference

ICPRAM 2016

Area 1 - Theory and Methods

Full Papers
Paper Nr: 5
Title:

On the Computation of the Number of Bubbles and Tunnels of a 3-D Binary Object

Authors:

Humberto Sossa

Abstract: Two formulations and two general procedures useful to compute the number of bubbles and tunnels of 3-D binary objects are introduced in this paper. The first formulation is useful to compute the number of bubbles or voids of the object, while the second one is only useful to compute the number of tunnels or holes of the object. The first procedure allows obtaining, in two steps, the number of bubbles and tunnels of a 3-D object. Finally, the second procedure permits computing, in three steps, the number of bubbles and tunnels of several 3-D objects from an image containing them. Correctness of the functioning of the two formulations is established theoretically. Results with a set of images are provided to demonstrate the utility and validity of the second proposed procedures.

Paper Nr: 6
Title:

Hadamard Code Graph Kernels for Classifying Graphs

Authors:

Tetsuya Kataoka and Akihiro Inokuchi

Abstract: Kernel methods such as Support Vector Machines (SVMs) are becoming increasingly popular because of their high performance on graph classification problems. In this paper, we propose two novel graph kernels called the Hadamard Code Kernel (HCK) and the Shortened HCK (SHCK). These kernels are based on the Hadamard code, which is used in spread spectrum-based communication technologies to spread message signals. The proposed graph kernels are equivalent to the Neighborhood Hash Kernel (NHK), one of the fastest graph kernels, and comparable to the Weisfeiler-Lehman Subtree Kernel (WLSK), one of the most accurate graph kernels. The fundamental performance and practicality of the proposed graph kernels are evaluated using three real-world datasets.

Paper Nr: 9
Title:

Interval Coded Scoring Index with Interaction Effects - A Sensitivity Study

Authors:

Lieven Billiet

Abstract: Scoring systems have been used since long in medical practice, but often they are based on experience rather than a structural approach. In literature, the interval coded scoring index (ICS) has been introduced as an alternative. It derives a scoring system from data using optimization techniques. This work discusses an extension, ICS*, that takes variable interactions into account. Furthermore, a study is performed to give insight into the new model’s sensitivity to noise, the size of the data set and the number of non-informative variables. The study shows interactions can mostly be discovered robustly, even in the presence of noise and spurious variables. A final validation on two UCI data sets further indicates the quality of the approach.

Paper Nr: 37
Title:

Assessing the Number of Clusters in a Mixture Model with Side-information

Authors:

Edith Grall-Maes and Duc Tung Dao

Abstract: This paper deals with the selection of cluster number in a clustering problem taking into account the sideinformation that some points of a chunklet arise from a same cluster. An Expectation-Maximization algorithm is used to estimate the parameters of a mixture model and determine the data partition. To select the number of clusters, usual criteria are not suitable because they do not consider the side-information in the data. Thus we propose suitable criteria which are modified version of three usual criteria, the bayesian information criterion (BIC), the Akaike information criterion (AIC), and the entropy criterion (NEC). The proposed criteria are used to select the number of clusters in the case of two simulated problems and one real problem. Their performances are compared and the influence of the chunklet size is discussed.

Paper Nr: 46
Title:

An Experimental Evaluation of the Adaptive Sampling Method for Time Series Classification and Clustering

Authors:

Muhammad Marwan Muhammad Fuad

Abstract: Adaptive sampling is a dimensionality reduction technique of time series data inspired by the dynamic programming piecewise linear approximation. This dimensionality reduction technique yields a suboptimal solution of the problem of polygonal curve approximation by limiting the search space. In this paper, we conduct extensive experiments to evaluate the performance of adaptive sampling in 1-NN classification and k-means clustering tasks. The experiments we conducted show that adaptive sampling gives satisfactory results in the aforementioned tasks even for relatively high compression ratios.

Paper Nr: 47
Title:

Adapted SIFT Descriptor for Improved Near Duplicate Retrieval

Authors:

Afra'a Ahmad Alyosef and Andreas Nürnberger

Abstract: The scale invariant feature transformation algorithm (SIFT) has been designed to detect and characterize local features in images. It is widely used to find similar regions in affine transformed images, to recognize similar objects or to retrieve near-duplicates of images. Due to the computational complexity of SIFT based matching operations several approaches have been proposed to speed up this process. However, most approaches lack significant decrease of matching accuracy compared to the original descriptor. We propose an approach that is optimized for near-duplicate image retrieval tasks by a dimensionality reduction process that differs from other methods by preserving the information around the keypoints of any region patches of the original descriptor. The computation of the proposed Region Compressed (RC) SIFT−64D descriptors is therefore faster and requires less memory for indexing. Most important, the obtained features show at the same time a better retrieval performance and seem to be even more robust. In order to prove this, we provide results of a comparative performance analysis using the original SIFT−128D, reduced SIFT versions, SURF−64D and the proposed RC-SIFT−64D in image near-duplicate retrieval using large scale image benchmark databases.

Paper Nr: 48
Title:

Foreground Segmentation for Moving Cameras under Low Illumination Conditions

Authors:

Wei Wang, Weili Li and Xiaoqing Yin

Abstract: A foreground segmentation method, including image enhancement, trajectory classification and object segmentation, is proposed for moving cameras under low illumination conditions. Gradient-field-based image enhancement is designed to enhance low-contrast images. On the basis of the dense point trajectories obtained in long frames sequences, a simple and effective clustering algorithm is designed to classify foreground and background trajectories. By combining trajectory points and a marker-controlled watershed algorithm, a new type of foreground labeling algorithm is proposed to effectively reduce computing costs and improve edge-preserving performance. Experimental results demonstrate the promising performance of the proposed approach compared with other competing methods.

Paper Nr: 49
Title:

A New Family of Bounded Divergence Measures and Application to Signal Detection

Authors:

Shivakumar Jolad, Ahmed Roman and Mahesh C. Shastry

Abstract: We introduce a new one-parameter family of divergence measures, called bounded Bhattacharyya distance (BBD) measures, for quantifying the dissimilarity between probability distributions. These measures are bounded, symmetric and positive semi-definite and do not require absolute continuity. In the asymptotic limit, BBD measure approaches the squared Hellinger distance. A generalized BBD measure for multiple distributions is also introduced. We prove an extension of a theorem of Bradt and Karlin for BBD relating Bayes error probability and divergence ranking. We show that BBD belongs to the class of generalized Csiszar f-divergence and derive some properties such as curvature and relation to Fisher Information. For distributions with vector valued parameters, the curvature matrix is related to the Fisher-Rao metric. We derive certain inequalities between BBD and well known measures such as Hellinger and Jensen-Shannon divergence. We also derive bounds on the Bayesian error probability. We give an application of these measures to the problem of signal detection where we compare two monochromatic signals buried in white noise and differing in frequency and amplitude.

Paper Nr: 52
Title:

Continuous Set Packing and Near-Boolean Functions

Authors:

Giovanni Rossi

Abstract: Given a family of feasible subsets of a ground set, the packing problem is to find a largest subfamily of pairwise disjoint family members. Non-approximability renders heuristics attractive viable options, while efficient methods with worst-case guarantee are a key concern in computational complexity. This work proposes a novel near-Boolean optimization method relying on a polynomial multilinear form with variables ranging each in a high-dimensional unit simplex. These variables are the elements of the ground set, and distribute each a unit membership over those feasible subsets where they are included. The given problem is thus translated into a continuous version where the objective is to maximize a function taking values on collections of points in a unit hypercube. Maximizers are shown to always include collections of hypercube disjoint vertices, i.e. partitions of the ground set, which constitute feasible solutions for the original discrete version of the problem. A gradient-based local search in the expanded continuous domain is designed. Approximations with polynomials of bounded degree and near-Boolean coalition formation games are also finally discussed.

Paper Nr: 55
Title:

Classifier Ensembles with Trajectory Under-Sampling for Face Re-Identification

Authors:

Roghayeh Soleymani

Abstract: In person re-identification applications, an individual of interest may be covertly tracked and recognized based on trajectories of faces or other distinguishing information captured with video surveillance camera. However, a varying level of imbalance often exists between target and non-target facial captures, and this imbalance level may differ from what was considered during design. The performance of face classification systems typically declines in such cases because, to avoid bias towards the majority class (non-target), they tend to optimize the overall accuracy under a balance class assumption. Specialized classifier ensembles trained on balanced data, where non-target samples are selected through random under-sampling or cluster-based sampling, have been proposed in literature, but they suffer from loss of information and low diversity and accuracy. In this paper, a new ensemble method is proposed for generating a diverse pool of classifiers, each one trained on different levels of class imbalance and complexity for a greater diversity of opinion. Ensembles with Trajectory Under Sampling (EoC-TUS) allows to select subsets of non-target training data based on trajectories information. Variants of these ensembles can give more importance to the most efficient classifiers in identifying target samples, or define efficient and diverse decision boundaries by starting selection of trajectories from the farthest ones to the target class. For validation, experiments are conducted using videos captured in the Faces In Action dataset, and compared to several baseline techniques. The proposed EoC-TUS outperforms state-of-the-art techniques in terms of accuracy and diversity over a range of imbalance levels in the input video.

Paper Nr: 113
Title:

Document Clustering Games

Authors:

Rocco Tripodi and Marcello Pelillo

Abstract: In this article we propose a new model for document clustering, based on game theoretic principles. Each document to be clustered is represented as a player, in the game theoretic sense, and each cluster as a strategy that the players have to choose in order to maximize their payoff. The geometry of the data is modeled as a graph, which encodes the pairwise similarity among each document and the games are played among similar players. In each game the players update their strategies, according to what strategy has been effective in previous games. The Dominant Set clustering algorithm is used to find the prototypical elements of each cluster. This information is used in order to divide the players in two disjoint sets, one collecting labeled players, which always play a definite strategy and the other one collecting unlabeled players, which update their strategy at each iteration of the games. The evaluation of the system was conducted on 13 document datasets and shows that the proposed method performs well compared to different document clustering algorithms.

Paper Nr: 132
Title:

Nonparametric Bayesian Line Detection - Towards Proper Priors for Robotic Computer Vision

Authors:

Anne C. van Rossum and Hai Xiang Lin

Abstract: In computer vision there are many sophisticated methods to perform inference over multiple lines, however they are quite ad-hoc. In this paper a fully Bayesian approach is used to fit multiple lines to a point cloud simultaneously. Our model extends a linear Bayesian regression model to an infinite mixture model and uses a Dirichlet process as a prior for the partition. We perform Gibbs sampling over non-unique parameters as well as over clusters to fit lines of a fixed length, a variety of orientations, and a variable number of data points. The performance is measured using the Rand Index, the Adjusted Rand Index, and two other clustering performance indicators. This paper is mainly meant to demonstrate that general Bayesian methods can be used for line estimation. Bayesian methods, namely, given a model and noise, perform optimal inference over the data. Moreover, rather than only demonstrating the concept as such, the first results are promising with respect to the described clustering performance indicators. Further research is required to extend the method to inference over multiple line segments and multiple volumetric objects that will need to be built on the mathematical foundation that has been laid down in this paper.

Short Papers
Paper Nr: 10
Title:

Similarity Function Learning with Data Uncertainty

Authors:

Julien Bohné and Sylvain Colin

Abstract: Similarity functions are at the core of many pattern recognition applications. Standard approaches use feature vectors extracted from a pair of images to compute their degree of similarity. Often feature vectors are noisy and a direct application of standard similarly learning methods may result in unsatisfactory performance. However, information on statistical properties of the feature extraction process may be available, such as the covariance matrix of the observation noise. In this paper, we present a method which exploits this information to improve the process of learning a similarity function. Our approach is composed of an unsupervised dimensionality reduction stage and the similarity function itself. Uncertainty is taken into account throughout the whole processing pipeline during both training and testing. Our method is based on probabilistic models of the data and we propose EM algorithms to estimate their parameters. In experiments we show that the use of uncertainty significantly outperform other standard similarity function learning methods on challenging tasks.

Paper Nr: 14
Title:

Similarity Assessment as a Dual Process Model of Counting and Measuring

Authors:

Bert Klauninger and Horst Eidenberger

Abstract: Based on recent findings from the field of human similarity perception, we propose a dual process model (DPM) of taxonomic and thematic similarity assessment which can be utilised in machine learning applications. Taxonomic reasoning is related to predicate based measures (counting) whereas thematic reasoning is mostly associated with metric distances (measuring). We suggest a procedure that combines both processes into a single similarity kernel. For each feature dimension of the observational data, an optimal measure is selected by a Greedy algorithm: A set of possible measures is tested, and the one that leads to improved classification performance of the whole model is denoted. These measures are combined into a single SVM kernel by means of generalisation (converting distances into similarities) and quantisation (applying predicate based measures to interval scale data). We then demonstrate how to apply our model to a classification problem of MPEG-7 features from a test set of images. Evaluation shows that the performance of the DPM kernel is superior to those of the standard SVM kernels. This supports our theory that the DPM comes closer to human similarity judgment than any singular measure, and it motivates our suggestion to employ the DPM not only in image retrieval but also in related tasks.

Paper Nr: 15
Title:

Machine Learning with Dual Process Models

Authors:

Bert Klauninger

Abstract: Similarity measurement processes are a core part of most machine learning algorithms. Traditional approaches focus on either taxonomic or thematic thinking. Psychological research suggests that a combination of both is needed to model human-like similarity perception adequately. Such a combination is called a Similarity Dual Process Model (DPM). This paper describes how to construct DPMs as a linear combination of existing measures of similarity and distance. We use generalisation functions to convert distance into similarity. DPMs are similar to kernel functions. Thus, they can be integrated into any machine learning algorithm that uses kernel functions.Clearly, not all DPMs that can be formulated work equally well. Therefore we test classification performance in a real-world task: the detection of pedestrians in images. We assume that DPMs are only viable if they yield better classifiers than their constituting parts. In our experiments, we found DPM kernels that matched the performance of conventional ones for our data set. Eventually, we provide a construction kit to build such kernels to encourage further experiments in other application domains of machine learning.

Paper Nr: 17
Title:

Hidden Markov Random Fields and Direct Search Methods for Medical Image Segmentation

Authors:

El-Hachemi Guerrout and Samy Ait-Aoudia

Abstract: The goal of image segmentation is to simplify the representation of an image to items meaningful and easier to analyze. Medical image segmentation is one of the fundamental problems in image processing field. It aims to provide a crucial decision support to physicians. There is no one way to perform the segmentation. There are several methods based on HMRF. Hidden Markov Random Fields (HMRF) constitute an elegant way to model the problem of segmentation. This modelling leads to the minimization of an energy function. In this paper we investigate direct search methods that are Nelder-Mead and Torczon methods to solve this optimization problem. The quality of segmentation is evaluated on grounds truths images using the Kappa index called also Dice Coefficient (DC). The results show the supremacy of the methods used compared to others methods.

Paper Nr: 18
Title:

Locally Linear Embedding based on Rank-order Distance

Authors:

Xili Sun and Yonggang Lu

Abstract: Dimension reduction has become an important tool for dealing with high dimensional data. Locally linear embedding (LLE) is a nonlinear dimension reduction method which can preserve local configurations of nearest neighbors. However, finding the nearest neighbors requires the definition of a distance measure, which is a critical step in LLE. In this paper, the Rank-order distance measure is used to substitute the traditional Euclidean distance measure in order to find better nearest neighbor candidates for preserving local configurations of the manifolds. The Rank-order distance between the data points is calculated using their neighbors’ ranking orders, and is shown to be able to improve the clustering of high dimensional data. The proposed method is called Rank-order based LLE (RLLE). The RLLE method is evaluated by comparing with the original LLE, ISO-LLE and IED-LLE on two handwritten datasets. It is shown that the effectiveness of a distance measure in the LLE method is closely related to whether it can be used to find good nearest neighbors. The experimental results show that the proposed RLLE method can improve the process of dimension reduction effectively, and C-index is another good candidate for evaluating the dimension reduction results.

Paper Nr: 38
Title:

Biometric Sensor Interoperability: A Case Study in 3D Face Recognition

Authors:

Javier Galbally and Riccardo Satta

Abstract: Biometric systems typically suffer a significant loss of performance when the acquisition sensor is changed between enrolment and authentication. Such a problem, commonly known as sensor interoperability, poses a serious challenge to the accuracy of matching algorithms. The present work addresses for the first time the sensor interoperability issue in 3D face recognition systems, analysing the performance of two popular and well known techniques for 3D facial authentication. For this purpose, a new gender-balanced database comprising 3D data of 26 subjects has been acquired using two devices belonging to the new generation of low-cost 3D sensors. The results show the high sensor-dependency of the tested systems and the need to develop matching algorithms robust to the variation in the sensor resolution.

Paper Nr: 39
Title:

Multi-person Visual Focus of Attention from Head Pose on a Natural Classroom

Authors:

Yuanyuan Liu, Leyuan Liu and Jingying Chen

Abstract: Visual focus of attention (VFOA) recognition is important for human-computer interface (HCI). Recently, promising results have been reported using special hardware in constrained environment. However, VFOA recognition remains challenging in natural environment, e.g., various illuminations, occlusions, expressions and wide scenes. In this paper, we propose a multi-person VFOA recognition approach from head pose in a natural classroom. The approach includes three stages. First, multi-face positions are detected and tracked in the sub-windows. Second, a hierarchical learning approach, Dirichlet-tree enhanced hybrid framework of classification and regression forests (Hybrid D-RF) is proposed to estimate continuous head pose. Third, a VFOA model is proposed based on the estimated head pose, visual environment cues and prior state for attention recognition and tracking in the natural classroom. The experimental results on several public databases and real-life applications show the proposed approach is robust and efficient for multi-persons’ VFOA recognition and tracking in practice.

Paper Nr: 40
Title:

A Mobile Indoor Positioning System Founded on Convolutional Extraction of Learned WLAN Fingerprints

Authors:

Avi Bleiweiss

Abstract: The proliferation of both wireless local area networks and mobile devices facilitated cost-effective indoor positioning systems that obviate the need for expensive infrastructure. We explore a floor-level, indoor localization system to predict the physical position of a mobile device holder in an office space by sensing a fingerprint of signal strength values, received from a plurality of wireless access points. In this work, we devise an instructive model that tailors elemental algorithms for unsupervised fingerprint learning, and resorts to only using a single-layer convolutional neural-network, succeeded by pooling. We applied our model to a fingerprint-based dataset that renders large multi-story buildings, and present a detailed analysis of the effect of changing setup parameters including the number of hidden nodes, the receptive field size, and the stride between extracted features. Our results surprisingly show that classification performance improves markedly with a sparser feature extraction, and affirms a more intuitive gain, yet milder, as any of the number of features or the tile size increases. Despite its simplicity, the positional accuracy we attained is sufficient to provide a useful tool for a location-aware mobile application, purposed to automate the mapping of building occupants.

Paper Nr: 43
Title:

Sparse-Reduced Computation - Enabling Mining of Massively-large Data Sets

Authors:

Philipp Baumann

Abstract: Machine learning techniques that rely on pairwise similarities have proven to be leading algorithms for classification. Despite their good and robust performance, similarity-based techniques are rarely chosen for largescale data mining because the time required to compute all pairwise similarities grows quadratically with the size of the data set. To address this issue of scalability, we introduced a method called sparse computation, which efficiently generates a sparse similarity matrix that contains only significant similarities. Sparse computation achieves significant reductions in running time with minimal and often no loss in accuracy. However, for massively-large data sets even such a sparse similarity matrix may lead to considerable running times. In this paper, we propose an extension of sparse computation called sparse-reduced computation that not only avoids computing very low similarities but also avoids computing similarities between highly-similar or identical objects by compressing them to a single object. Our computational results show that sparse-reduced computation allows highly-accurate classification of data sets with millions of objects in seconds.

Paper Nr: 45
Title:

Remote Heart Rate Determination in RGB Data - An Investigation using Independent Component Analysis and Adaptive Filtering

Authors:

Christian Wiede, Julia Richter and André Apitzsch

Abstract: An emerging topic in the field of elderly care is the determination and tracking of vital parameters, such as the heart rate. This parameter provides important information about a person’s current health status. Within the last years, various research focussed on this topic. The recognition of vital parameters is increasingly relevant for our ageing society. This paper presents a method to remotely determine the human heart rate with a camera. At this point, we suggest to use independent component analysis (ICA) and adaptive filtering for a robust detection. In our processing chain, we used different image processing techniques, e. g. face detection, and signal processing techniques, e. g. FFT and bandpass filtering, in this study. An evaluation with several probands, illuminations, frame rates and different heart rate levels showed that we could achieve a mean error of 4.36 BPM, which corresponds to CAND of 94.45 %, and a speed of 35 fps.

Paper Nr: 71
Title:

Understanding the Interplay of Simultaneous Model Selection and Representation Optimization for Classification Tasks

Authors:

Fabian Bürger and Josef Pauli

Abstract: The development of classification systems that meet the desired accuracy levels for real world-tasks applications requires a lot of expertise. Numerous challenges, like noisy feature data, suboptimal algorithms and hyperparameters, degrade the generalization performance. On the other hand, almost countless solutions have been developed, e.g. feature selection, feature preprocessing, automatic algorithm and hyperparameter selection. Furthermore, representation learning is emerging to automatically learn better features. The challenge of finding a suitable and tuned algorithm combination for each learning task can be solved by automatic optimization frameworks. However, the more components are optimized simultaneously, the more complex their interplay becomes with respect to the generalization performance and optimization run time. This paper analyzes the interplay of the components in a holistic framework which optimizes the feature subset, feature preprocessing, representation learning, classifiers and all hyperparameters. The evaluation on a real-world dataset that suffers from the curse of dimensionality shows the potential benefits and risks of such holistic optimization frameworks.

Paper Nr: 72
Title:

Denoising 3D Microscopy Images of Cell Nuclei using Shape Priors on an Anisotropic Grid

Authors:

Mathieu Bouyrie and Cristina Manfredotti

Abstract: This paper presents a new multiscale method to denoise three-dimensional images of cell nuclei. The specificity of this method is its awareness of the noise distribution and object shapes. It combines a multiscale representation called Isotropic Undecimated Wavelet Transform (IUWT) with a nonlinear transform, a statistical test and a variational method, to retrieve spherical shapes in the image. Beyond extending an existing 2D approach to a 3D problem, our algorithm takes the sampling grid dimensions into account. We compare our method to the two algorithms from which it is derived on a representative image analysis task, and show that it is superior to both of them. It brings a slight improvement in the signal-to-noise ratio and a significant improvement in cell detection.

Paper Nr: 80
Title:

A Formal Approach to Anomaly Detection

Authors:

André Eriksson and Hedvig Kjellström

Abstract: While many advances towards effective anomaly detection techniques targeting specific applications have been made in recent years, little work has been done to develop application-agnostic approaches to the subject. In this article, we present such an approach, in which anomaly detection methods are treated as formal, structured objects. We consider a general class of methods, with an emphasis on methods that utilize structural properties of the data they operate on. For this class of methods, we develop a decomposition into sub-methods—simple, restricted objects, which may be reasoned about independently and combined to form methods. As we show, this formalism enables the construction of software that facilitates formulating, implementing, evaluating, as well as algorithmically finding and calibrating anomaly detection methods.

Paper Nr: 89
Title:

Machine Learning based Number Plate Detection and Recognition

Authors:

Zuhaib Ahmed Shaikh and Umair Ali Khan

Abstract: Automatic Number Plate Detection and Recognition (ANPDR) has become of significant interest with the substantial increase in the number of vehicles all over the world. ANPDR is particularly important for automatic toll collection, traffic law enforcement, parking lot access control, and gate entry control, etc. Due to the known efficacy of image processing in this context, a number of ANPDR solutions have been proposed. However, these solutions are either limited in operations or work only under specific conditions and environments. In this paper, we propose a robust and computationally-efficient ANPDR system which uses Deformable Part Models (DPM) for extracting number plate features from training images, Structural Support Vector Machine (SSVM) for training a number plate detector with the extracted DPM features, several image enhancement operations on the extracted number plate, and Optical Character Recognition (OCR) for extracting the numbers from the plate. The results presented in this paper, obtained by long-term experiments performed under different conditions, demonstrate the efficiency of our system. They also show that our proposed system outperforms other ANPDR techniques not only in accuracy, but also in execution time.

Paper Nr: 94
Title:

A Pareto Front Approach for Feature Selection

Authors:

Enguerran Grandchamp

Abstract: This article deals with the multi-objective aspect of an hybrid algorithm that we propose to solve the feature subset selection problem. The hybrid aspect is due to the sequence of a filter and a wrapper method. The filter method reduces the exploration space by keeping subsets having good internal properties and the wrapper method chooses among the remaining subsets with a classification performances criterion. In the filter step, the subsets are evaluated in a multi-objective way to ensure diversity within the subsets. The evaluation is based on the mutual information to estimate the dependency between features and classes and the redundancy between features within the same subset. We kept the non-dominated (Pareto optimal) subsets for the second step. In the wrapper step, the selection is made according to the stability of the subsets regarding classification performances during learning stage on a set of classifiers to avoid the specialization of the selected subsets for a given classifiers. The proposed hybrid approach is experimented on a variety of reference data sets and compared to the classical feature selection methods FSDD and mRMR. The resulting algorithm outperforms these algorithms.

Paper Nr: 95
Title:

An Episode-based Approach to Identify Website User Access Patterns

Authors:

Madhuka Udantha

Abstract: Mining web access log data is a popular technique to identify frequent access patterns of website users. There are many mining techniques such as clustering, sequential pattern mining and association rule mining to identify these frequent access patterns. Each can find interesting access patterns and group the users, but they cannot identify the slight differences between accesses patterns included in individual clusters. But in reality these could refer to important information about attacks. This paper introduces a methodology to identify these access patterns at a much lower level than what is provided by traditional clustering techniques, such as nearest neighbour based techniques and classification techniques. This technique makes use of the concept of episodes to represent web sessions. These episodes are expressed in the form of regular expressions. To the best of our knowledge, this is the first time to apply the concept of regular expressions to identify user access patterns in web server log data. In addition to identifying frequent patterns, we demonstrate that this technique is able to identify access patterns that occur rarely, which would have been simply treated as noise in traditional clustering mechanisms.

Paper Nr: 123
Title:

A Statistical Quadtree Decomposition to Improve Face Analysis

Authors:

Vagner Amaral

Abstract: The feature extraction is one of the most important steps in face analysis applications and this subject always received attention in the computer vision and pattern recognition areas due to its applicability and wide scope. However, to define the correct spatial relevance of physiognomical features remains a great challenge. It has been proposed recently, with promising results, a statistical spatial mapping technique that highlights the most discriminating facial features using some task driven information from data mining. Such priori information has been employed as a spatial weighted map on Local Binary Pattern (LBP), that uses Chi-Square distance as a nearest neighbour based classifier. Intending to reduce the dimensionality of LBP descriptors and improve the classification rates we propose and implement in this paper two quad-tree image decomposition algorithms to task related spatial map segmentation. The first relies only on split step (top-down) of distinct regions and the second performs the split step followed by a merge step (bottom-up) to combine similar adjacent regions. We carried out the experiments with two distinct face databases and our preliminary results show that the top-down approach achieved similar classification results to standard segmentation using though less regions.

Posters
Paper Nr: 20
Title:

Adding Model Constraints to CNN for Top View Hand Pose Recognition in Range Images

Authors:

Aditya Tewari and Frederic Grandidier

Abstract: A new dataset for hand-pose is introduced. The dataset includes the top view images of the palm by Time of Flight (ToF) camera. It is recorded in an experimental setting with twelve participants for six hand-poses. An evaluation on the dataset is carried out with a dedicated Convolutional Neural Network (CNN) architecture for Hand Pose Recognition (HPR). This architecture uses a model-layer. The small size model layer creates a funnel shape network which adds a priori knowledge and constrains the network by modelling the degree of freedom of the palm, such that it learns palm features. It is demonstrated that this network performs better than a similar network without the prior added. A two-phase learning scheme which allows training the model on full dataset even when the classification problem is confined to a subset of the classes is described. The best model performs at an accuracy of 92%. Finally, we show the feature transfer capability of the network and compare the extracted features from various networks and discuss usefulness for various applications.

Paper Nr: 23
Title:

Fingerprint Pores Matching based on Improved Deterministic Annealing Algorithm

Authors:

Guangming Lu

Abstract: High Resolution Fingerprint Identification System (HRFIS) has become a hot topic in the field of academic research. Compare to traditional Automatic Fingerprint Identification System (AFIS), HRFIS reduces the risk of being faked by using level-3 features, such as pores, which can not be detected in lower resolution images (such as 500-dpi images). However, there is a serious problem in HRFIS: there are hundreds of sweat pores in one fingerprint image, which will spend a considerable amount of time for direct fingerprint matching. In this paper, we propose a scheme to select the more stable and representative sweat pores for fingerprint matching based on the improved deterministic annealing algorithm (DAA). First, the singular points are used for fingerprint alignment, then we improve the convergence condition and the design of adaptive annealing ratio of DAA to make the algorithm faster and more effective. Through the selection process, only 30%  35% of the original number of sweat pores are used for final matching. In the experiments, our method is compared with the direct sweat pore matching algorithm - Random Sample Consensus method (RANSAC) with and without alignment. The results show that the proposed method is more efficient.

Paper Nr: 30
Title:

Multiobjective Bacterial Foraging Optimization using Archive Strategy

Authors:

Cuicui Yang and Junzhong Ji

Abstract: Multiobjective optimization problems widely exist in engineering application and science research. This paper presents an archive bacterial foraging optimizer to deal with multiobjective optimization problems. Under the concept of Pareto dominance, the proposed algorithm uses chemotaxis, conjugation, reproduction and elimination-and-dispersal mechanisms to approximate to the true Pareto fronts in multiobjective optimization problems. In the optimization process, the proposed algorithm incorporates an external archive to save the nondominated solutions previously found and utilizes the crowding distance to maintain the diversity of the obtained nondominated solutions. The proposed algorithm is compared with two state-of-the-art algorithms on four standard test problems. The experimental results indicate that our approach is a promising algorithm to deal with multiobjective optimization problems.

Paper Nr: 34
Title:

Are Large Scale Training Images or Discriminative Features Important for Codebook Construction?

Authors:

Veerapathirapillai Vinoharan and Amirthalingam Ramanan

Abstract: Advances in machine learning and image feature representations have led to great progress in pattern recognition approaches in recognising up to 1000 visual object categories. However, the human brain solves this problem effortlessly as it can recognise about 10000 to 100000 objects with a small number of examples. In recent years bag-of-features approach has proved to yield state-of-the-art performance in large scale evaluations. In such systems a visual codebook plays a crucial role. For constructing a codebook researchers cover a large-scale of training image set. But this brings up the issue of scalability. A large volume of training data becomes difficult to process whereas the high dimensional image representation could make many machine learning algorithms become inefficient or even a breakdown. In this work we investigate whether the dominant bag-of-features approach used in object recognition will continue significantly to improve with large training image set or not. We have validated a one-pass clustering algorithm to construct visual codebooks for object classification tasks on the PASCAL VOC Challenge image set. Our testing results show that adding more training images do not contribute significantly to increase the performance of classification but it increases the overall model complexity in terms of increased storage requirement and greater computational time. This study further suggests an alternative view to the community working with the patch-based object recognition to enforce retaining more discriminative descriptors rather than the reminiscent of the BIG data hypothesis.

Paper Nr: 44
Title:

Aircraft Unsteady Aerodynamic Hybrid Modeling Based on State-Space Representation and Neural Network

Authors:

Ouyang Guang

Abstract: This paper proposes a hybrid model which combines state-space representation and back-propagation neural network to describe the aircraft unsteady aerodynamic characteristics. Firstly, the state-space model is analysed and evaluated using wind-tunnel experimental data. Subsequently, back-propagation neural network is introduced and combined with state-space representation to form a hybrid model. In this hybrid model, the separation point model in state-space representation is reserved to describe the time delay of the unsteady aerodynamic responses, while the conventional polynomial model is replaced by back-propagation neural network to improve accuracy and universality. Finally, lift coefficient and pitch moment coefficient data from the wind-tunnel experiments are used to estimate the hybrid model. With high similarity to the wind-tunnel data, the hybrid model presented in this paper is proved to be accurate and effective for aircraft unsteady aerodynamic modeling.

Paper Nr: 51
Title:

Classification of Dust Elements by Spatial Geometric Features

Authors:

A. Proietti, M. Panella and E. D. Di Claudio

Abstract: Management of air quality is an important task in many human activities. It is carried out mainly by installing ventilation and filtering facilities. In order to ensure efficiency, these systems must be designed after the knowledge of key environmental parameters, such as size and type of particles and fibres present in the air. In this paper, we propose a new method for the classification of dust particles and fibres based on a minimal set of geometric features extracted from binary images of dust elements, captured by a very cheap imaging system. The proposed technique is discussed and tested. Experimental results obtained by real- measured data are presented, showing satisfactory performance by using several well-known classifiers.

Paper Nr: 58
Title:

GPS Trajectory Data Enrichment based on a Latent Statistical Model

Authors:

Akira Kinoshita, Atsuhiro Takasu, Kenro Aihara, Jun Ishii, Hisashi Kurasawa and Hiroshi Sato

Abstract: This paper proposes a latent statistical model for analyzing global positioning system (GPS) trajectory data. Because of the rapid spread of GPS-equipped devices, numerous GPS trajectories have become available, and they are useful for various location-aware systems. To better utilize GPS data, a number of sensor data mining techniques have been developed. This paper discusses the application of a latent statistical model to two closely related problems, namely, moving mode estimation and interpolation of the GPS observation. The proposed model estimates a latent mode of moving objects and represents moving patterns according to the mode by exploiting a large GPS trajectory dataset. We evaluate the effectiveness of the model through experiments using the GeoLife GPS Trajectories dataset and show that more than three-quarters of covered locations were correctly reproduced by interpolation at a fine granularity.

Paper Nr: 61
Title:

A Comparative Study on Outlier Removal from a Large-scale Dataset using Unsupervised Anomaly Detection

Authors:

Markus Goldstein and Seiichi Uchida

Abstract: Outlier removal from training data is a classical problem in pattern recognition. Nowadays, this problem becomes more important for large-scale datasets by the following two reasons: First, we will have a higher risk of “unexpected” outliers, such as mislabeled training data. Second, a large-scale dataset makes it more difficult to grasp the distribution of outliers. On the other hand, many unsupervised anomaly detection methods have been proposed, which can be also used for outlier removal. In this paper, we present a comparative study of nine different anomaly detection methods in the scenario of outlier removal from a large-scale dataset. For accurate performance observation, we need to use a simple and describable recognition procedure and thus utilize a nearest neighbor-based classifier. As an adequate large-scale dataset, we prepared a handwritten digit dataset comprising of more than 800,000 manually labeled samples. With a data dimensionality of 16×16 = 256, it is ensured that each digit class has at least 100 times more instances than data dimensionality. The experimental results show that the common understanding that outlier removal improves classification performance on small datasets is not true for high-dimensional large-scale datasets. Additionally, it was found that local anomaly detection algorithms perform better on this data than their global equivalents.

Paper Nr: 66
Title:

Job Recommendation from Semantic Similarity of LinkedIn Users’ Skills

Authors:

Giacomo Domeniconi, Gianluca Moro and Andrea Pagliarani

Abstract: Until recently job seeking has been a tricky, tedious and time consuming process, because people looking for a new position had to collect information from many different sources. Job recommendation systems have been proposed in order to automate and simplify this task, also increasing its effectiveness. However, current approaches rely on scarce manually collected data that often do not completely reveal people skills. Our work aims to find out relationships between jobs and people skills making use of data from LinkedIn users’ public profiles. Semantic associations arise by applying Latent Semantic Analysis (LSA). We use the mined semantics to obtain a hierarchical clustering of job positions and to build a job recommendation system. The outcome proves the effectiveness of our method in recommending job positions. Anyway, we argue that our approach is definitely general, because the extracted semantics could be worthy not only for job recommendation systems but also for recruiting systems. Furthermore, we point out that both the hierarchical clustering and the recommendation system do not require parameters to be tuned.

Paper Nr: 68
Title:

Experiments on Adaptation Methods to Improve Acoustic Modeling for French Speech Recognition

Authors:

Saeideh Mirzaei, Pierrick Milhorat and Jérôme Boudy

Abstract: To improve the performance of Automatic Speech Recognition (ASR) systems, the models must be retrained in order to better adjust to the speaker’s voice characteristics, the environmental and channel conditions or the context of the task. In this project we focus on the mismatch between the acoustic features used to train the model and the vocal characteristics of the front-end user of the system. To overcome this mismatch, speaker adaptation techniques have been used. A significant performance improvement has been shown using using constrained Maximum Likelihood Linear Regression (cMLLR) model adaptation methods, while a fast adaptation is guaranteed by using linear Vocal Tract Length Normalization (lVTLN).We have achieved a relative gain of approximately 9.44% in the word error rate with unsupervised cMLLR adaptation. We also compare our ASR system with the Google ASR and show that, using adaptation methods, we exceed its performance.

Paper Nr: 74
Title:

Metrics for Clustering Comparison in Bioinformatics

Authors:

Giovanni Rossi

Abstract: Developing from a concern in bioinformatics, this work analyses alternative metrics between partitions. From both theoretical and applicative perspectives, a useful and interesting distance between any two partitions is HD, which counts the number of atoms finer than either one but not both. While faithfully reproducing the traditional Hamming distance between subsets, HD is very sensible and computable through scalar products between Boolean vectors. It properly deals with complements and axiomatically resembles the entropy-based variation of information VI distance. Entire families of metrics (including HD and VI) obtain as minimal paths in the weighted graph given by the Hasse diagram: submodular weighting functions yield path-based distances visiting the join (of any two partitions), whereas supermodularity leads to visit the meet. This yields an exact (rather than heuristic) approach to the consensus partition (combinatorial optimization) problem.

Paper Nr: 79
Title:

Learning of Graph Compressed Dictionaries for Sparse Representation Classification

Authors:

Farshad Nourbakhsh and Eric Granger

Abstract: Despite the limited target data available to design face models in video surveillance applications, many faces of non-target individuals may be captured over multiple cameras in operational environments to improve robustness to variations. This paper focuses on Sparse Representation Classification (SRC) techniques that are suitable for the design of still-to-video FR systems based on under-sampled dictionaries. The limited reference data available during enrolment is complemented by an over-complete external dictionary that is formed with an abundance of faces from non-target individuals. In this paper, the Graph-Compressed Dictionary Learning (GCDL) technique is proposed to learn compact auxiliary dictionaries for SRC. GCDL is based on matrix factorization, and allows to maintain a high level of SRC accuracy with compressed dictionaries because it exploits structural information to represent intra-class variations. Graph compression based on matrix factorization shown to efficiently compress data, and can therefore rapidly construct compact dictionaries. Accuracy and efficiency of the proposed GCDL technique is assessed and compared to reference sparse coding and dictionary learning techniques using images from the CAS-PEAL database. GCDL is shown to provide fast matching and adaptation of compressed dictionaries to new reference faces from the video surveillance environments.

Paper Nr: 97
Title:

Choquet Integral based Feature Selection for Early Breast Cancer Diagnosis from MRIs

Authors:

Soumaya Trabelsi Ben Ameur and Florence Cloppet

Abstract: This paper focuses on breast cancer of the mammary gland. Both basic segmentation steps and usual features are recalled. Then textural and morphological information are combined to improve the overall performance of breast MRI in a computer-aided system. A model of selection based on Choquet integral is provided. Such model is suitable when handling with a weak amount of data even ambiguous in some extent. Achieved results compared to well-known classification methods show the interest of our approach.

Paper Nr: 103
Title:

Matching CAD Model and Image Features for Robot Navigation and Inspection of an Aircraft

Authors:

Igor Jovančević, Ilisio Viana and Jean-José Orteu

Abstract: This paper focuses on the navigation of a moving robot equipped with cameras, moving around an aircraft to perform inspection of different types of items (probes, doors, etc.). Matching CAD model and image features is useful to provide meaningful features for localization and inspection tasks. In our approach two primitive sets are matched using a similarity function. The similarity scores are injected in the edges of a bipartite graph. A best-match search procedure in bipartite graph guarantees the uniqueness of the match solution. The method provides good matching results even when the location of the robot with respect to the aircraft is badly estimated. Inspection approaches on static ports and air inlet vent are presented.

Paper Nr: 109
Title:

Efficient Evidence Accumulation Clustering for Large Datasets

Authors:

Diogo Silva

Abstract: The unprecedented collection and storage of data in electronic format has given rise to an interest in automated analysis for generation of knowledge and new insights. Cluster analysis is a good candidate since it makes as few assumptions about the data as possible. A vast body of work on clustering methods exist, yet, typically, no single method is able to respond to the specificities of all kinds of data. Evidence Accumulation Clustering (EAC) is a robust state of the art ensemble algorithm that has shown good results. However, this robustness comes with higher computational cost. Currently, its application is slow or restricted to small datasets. The objective of the present work is to scale EAC, allowing its applicability to big datasets, with technology available at a typical workstation. Three approaches for different parts of EAC are presented: a parallel GPU K-Means implementation, a novel strategy to build a sparse CSR matrix specialized to EAC and Single-Link based on Minimum Spanning Trees using an external memory sorting algorithm. Combining these approaches, the application of EAC to much larger datasets than before was accomplished.

Paper Nr: 126
Title:

Stability Feature Selection using Cluster Representative LASSO

Authors:

Niharika Gauraha

Abstract: Variable selection in high dimensional regression problems with strongly correlated variables or with near linear dependence among few variables remains one of the most important issues. We propose to cluster the variables first and then do stability feature selection using Lasso for cluster representatives. The first step involves generation of groups based on some criterion and the second step mainly performs group selection with controlling the number of false positives. Thus, our primary emphasis is on controlling type-I error for group variable selection in high-dimensional regression setting. We illustrate the method using simulated and pseudo-real data, and we show that the proposed method finds an optimal and consistent solution.

Paper Nr: 130
Title:

Two Stage SVM Classification for Hyperspectral Data

Authors:

Michal Cholewa and Przemyslaw Glomb

Abstract: In this article, we present a method of enhancing the SVM classification of hyperspectral data with the use of three supporting classifiers. It is done by applying the fully trained classifiers on learning set to obtain the pattern of their behavior which then can be used for refinement of classifier construction. The second stage either is a straightforward translation of first stage, if the first stage classifiers agree on the result, or it consists of using retrained SVM classifier with only the data from learning data selected using first stage. The scheme shares some features with committee of experts fusion scheme, yet it clearly distinguishes lead classifier using the supporting ones only to refine its construction. We present the construction of two-stage scheme, then test it against the known Indian Pines HSI dataset and test it against straightforward use of SVM classifier, over which our method achieves noticeable improvement.

Area 2 - Applications

Full Papers
Paper Nr: 2
Title:

Information Efficient Automatic Object Detection and Segmentation using Cosegmentation, Similarity based Clustering, and Graph Label Transfer

Authors:

Johannes Steffen and Marko Rak

Abstract: We tackle the problem of unsupervised object cosegmentation combining automatic image selection, cosegmentation, and knowledge transfer to yet unlabelled images. Furthermore, we overcome the limitations often present in state-of-the-art methods in object cosegmentation, namely, high complexity and poor scalability w.r.t. image set size. Our proposed approach is robust, reasonably fast, and scales linearly w.r.t. the image set size. We tested our approach on two commonly used cosegmentation data sets and outperformed some of the state-of-the-art methods using significantly less information than possible. Additionally, results indicate the applicability of our approach on larger image sets.

Paper Nr: 4
Title:

Statistical Measurement Validation with Application to Electronic Nose Technology

Authors:

Mina Mirshahi

Abstract: An artificial olfaction called electronic nose (e-nose) relies on an array of gas sensors with the capability of mimicking the human sense of smell. Applying an appropriate pattern recognition on the sensor’s output returns odor concentration and odor classification. Odor concentration plays a key role in analyzing odors. Assuring the validity of measurements in each stage of sampling is a critical issue in sampling odors. An accurate prediction for odor concentration demands for careful monitoring of the gas sensor array measurements through time. The existing e-noses capture all odor changes in its environment with possibly varying range of error. Consequently, some measurements may distort the pattern recognition results. We explore e-nose data and provide a statistical algorithm to assess the data validity. Our online algorithm is computationally efficient and treats data as being sampled.

Paper Nr: 19
Title:

Activity Recognition based on High-Level Reasoning - An Experimental Study Evaluating Proximity to Objects and Pose Information

Authors:

Julia Richter, Christian Wiede and Enes Dayangac

Abstract: In the context of Ambient Assisted Living (AAL), the detection of daily activities is an active field of research. In this study, we present an algorithm for the performed Activities of Daily Living (ADLs) related to personal hygiene, which is based on the evaluation of a person’s proximity to objects and pose information. To this end, we have employed a person detection algorithm that provides a person’s position within a room. By fusing the obtained position with the objects’ position, we were able to deduce whether the person was occupied with a certain object and to draw conclusions about the performed ADLs. One prerequisite for a reliable modelling of human activities is the knowledge about the accuracy of the person detection algorithm. We have, therefore, analysed the algorithm with regard to its accuracy under different, application-specific conditions. The results show that the considered algorithm ensures high accuracy for our AAL application and that it is even suitable for environments, in which objects are very close to each other. On the basis of these findings, tests with video sequences have been conducted in an AAL environment. This evaluation confirmed that the reasoning algorithm can reliably recognise activities related to personal hygiene.

Paper Nr: 42
Title:

k-fold Subsampling based Sequential Backward Feature Elimination

Authors:

Jeonghwan Park

Abstract: We present a new wrapper feature selection algorithm for human detection. This algorithm is a hybrid feature selection approach combining the benefits of filter and wrapper methods. It allows the selection of an optimal feature vector that well represents the shapes of the subjects in the images. In detail, the proposed feature selection algorithm adopts the k-fold subsampling and sequential backward elimination approach, while the standard linear support vector machine (SVM) is used as the classifier for human detection. We apply the proposed algorithm to the publicly accessible INRIA and ETH pedestrian full image datasets with the PASCAL VOC evaluation criteria. Compared to other state of the arts algorithms, our feature selection based approach can improve the detection speed of the SVM classifier by over 50% with up to 2% better detection accuracy. Our algorithm also outperforms the equivalent systems introduced in the deformable part model approach with around 9% improvement in the detection accuracy.

Paper Nr: 54
Title:

Data Based Color Constancy

Authors:

Wei Xu and Huaxin Xiao

Abstract: Color constancy is an important task in computer vision. By analyzing the image formation model, color gamut data under one light source can be mapped to a hyperplane whose normal vector is only determined by its light source. Thus, the canonical light source is represented through the kernel method, which trains the color data. When an image is captured under an unknown illuminant, the image-corrected matrix is obtained through optimization. After being mapped to the high-dimensional space, the corrected color data are best fit for the hyperplane of the canonical illuminant. The proposed unsupervised feature-mining kernel method only depends on the color data without any other information. The experiments on the standard test datasets show that the proposed method achieves comparable performance with other state-of-the-art methods.

Paper Nr: 59
Title:

Sparse Physics-based Gaussian Process for Multi-output Regression using Variational Inference

Authors:

Ankit Chiplunkar and Emmanuel Rachelson

Abstract: In this paper a sparse approximation of inference for multi-output Gaussian Process models based on a Variational Inference approach is presented. In Gaussian Processes a multi-output kernel is a covariance function over correlated outputs. Using a general framework for constructing auto- and cross-covariance functions that are consistent with the physical laws, physical relationships among several outputs can be imposed. One major issue with Gaussian Processes is efficient inference, when scaling up-to large datasets. The issue of scaling becomes even more important when dealing with multiple outputs, since the cost of inference increases rapidly with the number of outputs. In this paper we combine the use of variational inference for efficient inference with multi-output kernels enforcing relationships between outputs. Results of the proposed methodology for synthetic data and real world applications are presented. The main contribution of this paper is the application and validation of our methodology on a dataset of real aircraft flight tests, while imposing knowledge of aircraft physics into the model.

Paper Nr: 84
Title:

Display Content Change Rate Analysis for Power Saving in Transmissive Panels

Authors:

Raghu Bankapur

Abstract: Energy conservation to protract battery life is a major challenge for sustained richer user experience in mobile devices. This paper presents Content Change Rate Coefficient (CCRC) and image Color Distribution Coefficient (CDC) based method to govern backlight scaling and image luminosity adjustment to reduce power consumption in backlight module. The existing methods intending to achieve similar results have significant shortcomings like inter-frame brightness distortion, flickering effects, clipping artifacts, color distortion. These problems are addressed in proposed technique and user's visual perception is not compromised while ensuring image fidelity (less than 6.2% degradation) and reduces nearly 80mA current consumption. Proposed method derives Aggressiveness Coefficient from color distribution and content change rate to address above problems. Method is prototyped on Samsung Galaxy Tab AS and Galaxy Mega2 and experimental results clearly show 16% reduction in current consumption and 88% reduction in flickering artifacts, which is active phone usage time getting extended by ~1hr for an average usage of 20hrs.

Paper Nr: 96
Title:

Video based Swimming Analysis for Fast Feedback

Authors:

Paavo Nevalainen, Antti Kauhanen and Csaba Raduly-Baka

Abstract: This paper proposes a digital camera based swimming analysis system for athletic use with a low budget. The recreational usage is possible during the analysis phase, and no alterations of the pool environment are needed. The system is of minimum complexity, has a real-time feedback mode, uses only underwater cameras, is flexible and can be installed in many types of public swimming pools. Possibly inaccurate camera placement poses no problem. Both commercially available and tailor made software were utilized for video signal collection and computational analysis and for providing a fast visual feedback for swimmers to improve the athletic performance. The small number of cameras with a narrow overlapping view makes the conventional stereo calibration inaccurate and a direct planar calibration method is proposed in this paper instead. The calibration method is presented and its accuracy is evaluated. The quick feedback is a key issue in improving the athletic performance. We have developed two indicators, which are easy to visualize. The first one is the swimming speed measured from the video signal by tracking a marker band at the waist of the swimmer, another one is the rudimentary swimming cycle analysis focusing to the regularity of the cycle.

Paper Nr: 98
Title:

Motion Artifact Reduction in Photoplethysmography using Bayesian Classification for Physical Exercise Identification

Authors:

Giorgio Biagetti, Paolo Crippa and Laura Falaschetti

Abstract: Accurate heart rate (HR) estimation from photoplethysmography (PPG) recorded from subjects’ wrist when the subjects are performing various physical exercises is a challenging problem. This paper presents a framework that combines a robust algorithm capable of estimating HR from PPG signal with subjects performing a single exercise and a physical exercise identification algorithm capable of recognizing the exercise the subject is performing. Experimental results on subjects performing two different exercises show that an improvement of about 50% in the accuracy of HR estimation is achieved with the proposed approach.

Paper Nr: 112
Title:

Detection of Raindrop with Various Shapes on aWindshield

Authors:

Junki Ishizuka and Kazunori Onoguchi

Abstract: This paper presents the method to detect raindrops with various shapes on a windshield from an in-vehicle single camera. Raindrops on a windshield causes various bad influence for video-based automobile applications, such as pedestrian detection, lane detection and so on. Therefore, it’s important to understand the state of the raindrop on a windshield for a driving safety support system or an automatic driving vehicle. Although conventional methods are considered on isolated spherical raindrops, our method can be applied to raindrops with various shapes, e.g. a band-like shape. In the daytime, our method detects raindrop candidates by examining the difference of the blur between the surrounding areas. We uses the ratio of the edge strength extracted from two kinds of smoothed images as the degree of the blur. At night, bright areas whose intensity does not change so much are detected as raindrops.

Paper Nr: 121
Title:

Exploiting Ambiguities in the Analysis of Cumulative Matching Curves for Person Re-identification

Authors:

Vito Renò, Angelo Cardellicchio and Tiziano Politi

Abstract: In this paper, a method to find, exploit and classify ambiguities in the results of a person re-identification (PRID) algorithm is presented. We start from the assumption that ambiguity is implicit in the classical formulation of the re-identification problem, as a specific individual may resemble one or more subjects by the color of dresses or the shape of the body. Therefore, we propose the introduction of the AMbiguity rAte in REidentification (AMARE) approach, which relates the results of a classical PRID pipeline on a specific dataset with their effectiveness in re-identification terms, exploiting the ambiguity rate (AR). As a consequence, the cumulative matching curves (CMC) used to show the results of a PRID algorithm will be filtered according to the AR. The proposed method gives a different interpretation of the output of PRID algorithms, because the CMC curves are processed, split and studied separately. Real experiments demonstrate that the separation of the results is really helpful in order to better understand the capabilities of a PRID algorithm.

Short Papers
Paper Nr: 12
Title:

English-Turkish Parallel Treebank with Morphological Annotations and its Use in Tree-based SMT

Authors:

Onur Görgün and Olcay Taner Yıldız

Abstract: In this paper, we report our tree based statistical translation study from English to Turkish. We describe our data generation process and report the initial results of tree-based translation under a simple model. For corpus construction, we used the Penn Treebank in the English side. We manually translated about 5K trees from English to Turkish under grammar constraints with adaptations to accommodate the agglutinative nature of Turkish morphology. We used a permutation model for subtrees together with a word to word mapping. We report BLEU scores under simple choices of inference algorithms.

Paper Nr: 22
Title:

Feature Detection and Description using a Harris-Hessian/FREAK Combination on an Embedded GPU

Authors:

Max Danielsson and Thomas Sievert

Abstract: GPUs in embedded platforms are reaching performance levels comparable to desktop hardware, thus it becomes interesting to apply Computer Vision techniques. We propose, implement, and evaluate a novel feature detector and descriptor combination, i.e., we combine the Harris-Hessian detector with the FREAK binary descriptor. The implementation is done in OpenCL, and we evaluate the execution time and classification performance. We compare our approach with two other methods, FAST/BRISK and ORB. Performance data is presented for the mobile device Xperia Z3 and the desktop Nvidia GTX 660. Our results indicate that the execution times on the Xperia Z3 are insufficient for real-time applications while desktop execution shows future potential. Classification performance of Harris-Hessian/FREAK indicates that the solution is sensitive to rotation, but superior in scale variant images.

Paper Nr: 24
Title:

Outdoor Context Awareness Device That Enables Mobile Phone Users to Walk Safely through Urban Intersections

Authors:

Jihye Hwang and Younggwang Ji

Abstract: Research in social science has shown that the mobile phone users pay less attention to their surroundings, which exposes them to various hazards such as collisions with vehicles than other pedestrians. In this paper, we propose a novel handheld device that assists mobile phone users to walk more safely outdoors. The proposed system is implemented on a smart phone and uses its back camera to detect the current outdoor context, e.g. traffic intersections, roadways, and sidewalks, finally alerts the user of unsafe situations using sound and vibration from the phone. The outdoor context awareness is performed by three steps: preprocessing, feature extraction, and context recognition. First, it improves the image contrast while removing image noise, and then it extracts the color and texture descriptors from each pixel. Next, each pixel is classified as an intersection, sidewalk, or roadway using a support vector machine-based classifier. Then, to support the real-time performance on the smart phone, a multi-scale classification is applied to input image, where the coarse layer first discriminates the boundary pixels from the background and the fine layer categorizes the boundary pixels as sidewalk, roadway, or intersection. In order to demonstrate the effectiveness of the proposed method, some real-world experiments were performed, then the results showed that the proposed system has the accuracy of above 98% at the various environments.

Paper Nr: 26
Title:

Geometry Analysis of Superconducting Cables for the Optimization of Global Performances

Authors:

Nicolas Lermé and Petr Dokládal

Abstract: Superconducting cables have now become a mature technology for energy transport, high-field magnets (MRI, LHC) and fusion applications (ToreSupra, and eventually ITER and DEMO). The superconductors are extremely brittle and suffer from electrical damages brought by mechanical strain induced by electromagnetic field that they generate. An optimal wiring architecture, obtained by simulation, can limit these damages. However, the simulation is a complex process and needs validation. This validation is performed on real 3D samples by the means of image processing. Within this objective, this paper is, to our best knowledge, the first one to present a method to segment the samples of three types of cables as well as a shape and geometry analysis. Preliminary results are encouraging and intended to be later compared to the simulation results.

Paper Nr: 27
Title:

Full Video Processing for Mobile Audio-Visual Identity Verification

Authors:

Alexander Usoltsev

Abstract: This paper describes a bi-modal biometric verification system based on voice and face modalities, which takes advantage of the full video processing instead of using still-images. The bi-modal system is evaluated on the MOBIO corpus and results show a relative improvement of performance by nearly 10% when the whole video is used. The fusion between face and speaker verification systems, using linear logistic regression weights, gives a relative improvement of performance that varies between 30% and 60% comparing to the best uni-modal system. Proof-of-concept iPad application is developed based on the proposed bi-modal system.

Paper Nr: 28
Title:

Comparing Color Descriptors between Image Segments for Saliency Detection

Authors:

Anurag Singh

Abstract: Detecting salient regions in an image or video frame is an important step in early vision and image understanding. We present a visual saliency detection method by measuring the difference in color content of an image segment with that of its neighbors. We represent each segment with richer color descriptors in the form of a regional dominant color descriptor. The color difference between a pair of neighbors is found using the Earth Mover’s Distance. The cost of moving color descriptors between neighboring segments robustly captures the difference between neighboring segments. We evaluate our method on standard datasets and compare it with other state-of-the-art methods to demonstrate that it has better true positive rate at a fixed false positive rate in detecting salient pixels relative to the ground truth. The proposed method uses local cues without being an edge highlighter, a common problem of local contrast-based methods.

Paper Nr: 33
Title:

Pattern Recognition in Real Time using Neural Networks: An Application for Pressure Measurement

Authors:

Parham Piroozan

Abstract: Retrieving information in real time from fringe patterns is a topic of great importance in scientific and engineering applications of optical methods. This paper describes an application of neural networks for real time pressure measurement using fringe pattern recognition. It is based on the capability of neural networks to recognize signals that are similar but not identical to the signals which were used to train the network. In this investigation a pressure sensor, which was part of the wall of the wind tunnel, and an optical apparatus were used to produce moiré fringes. The fringe patterns generated were analyzed by a back propagation neural network at the speed of the recording device, which was a CCD camera. This method of information retrieval was used to measure the pressure fluctuations in the boundary layer flow. A second neural network was used to recognize the pressure patterns and to provide input to a control system that was capable to preserve the stability of the flow.

Paper Nr: 41
Title:

ABLE: An Automated Bacterial Load Estimator for the Urinoculture Screening

Authors:

Paolo Andreini, Simone Bonechi and Monica Bianchini

Abstract: Urinary Tract Infections (UTIs) are very common in women, babies and the elderly. The most frequent cause is a bacterium, called Escherichia Coli, which usually lives in the digestive system and in the bowel. Infections can target the urethra, bladder or kidneys. Traditional analysis methods, based on human experts’ evaluation, are typically used to diagnose UTIs, an error prone and lengthy process, whereas an early treatment of common pathologies is fundamental to prevent the infection spreading to kidneys. This paper presents an image based Automated Bacterial Load Estimator (ABLE) system for the urinoculture screening, that provides quick and traceable results for UTIs. Infections are accurately detected and the bacterial load is evaluated through image processing techniques. First, digital color images of the Petri dishes are automatically captured, and cleaned from noisily elements due to laboratory procedures, then specific spatial clustering algorithms are applied to isolate the colonies from the culture ground and, finally, an accurate evaluation of the infection severity is performed. A dataset of 499 urine samples has been used during the experiments and the obtained results are fully discussed. The ABLE system speeds up the analysis, grants repeatable results, contributes to the process standardization, and guarantees a significant cost reduction.

Paper Nr: 83
Title:

Using Differential Evolution to Improve Pheromone-based Coordination of Swarms of Drones for Collaborative Target Detection

Authors:

Mario G. C. A. Cimino

Abstract: In this paper we propose a novel algorithm for adaptive coordination of drones, which performs collaborative target detection in unstructured environments. Coordination is based on digital pheromones released by drones when detecting targets, and maintained in a virtual environment. Adaptation is based on the Differential Evolution (DE) and involves the parametric behaviour of both drones and environment. More precisely, attractive/repulsive pheromones allow indirect communication between drones in a flock, concerning the availability/unavailability of recently found targets. The algorithm is effective if structural parameters are properly tuned. For this purpose DE combines different parametric solutions to increase the swarm performance. We focus first on the study of the principal parameters of the DE, i.e., the crossover rate and the differential weight. Then, we compare the performance of our algorithm with three different strategies on six simulated scenarios. Experimental results show the effectiveness of the approach.

Paper Nr: 87
Title:

Classification of Mild Cognitive Impairment Subtypes using Neuropsychological Data

Authors:

Upul Senanayake, Arcot Sowmya, Laughlin Dawes and Nicole A. Kochan

Abstract: While the research on Alzheimer’s disease (AD) is progressing, timely intervention before an individual becomes demented is often emphasized. Mild Cognitive Impairment (MCI), which is thought of as a prodromal syndrome to AD, may be useful in this context as potential interventions can be applied to individuals at increased risk of developing dementia. The current study attempts to address this problem using a selection of machine learning algorithms to discriminate between cognitively normal individuals and MCI individuals among a cohort of community dwelling individuals aged 70-90 years based on neuropsychological test performance. The overall best algorithm in our experiments was AdaBoost with decision trees while random forests was consistently stable. Ten-fold cross validation was used with ten repetitions to reduce variability and assess generalizing capabilities of the trained models. The results presented are consistently of the same calibre or better than the limited number of similar studies reported in the literature.

Paper Nr: 108
Title:

HMM-based Transient and Steady-state Current Signals Modeling for Electrical Appliances Identification

Authors:

Mohamed Nait-Meziane, Abdenour Hacine-Gharbi, Philippe Ravier and Guy Lamarque

Abstract: The electrical appliances identification problem is gaining a rapidly growing interest these past few years due to the recent need of this information in the new smart grid configuration. In this work, we propose to construct an appliance identification system based on the use of Hidden Markov Models (HMM) to model transient and steady-state electrical current signals. For this purpose, we investigate the usefulness of different choices for the proposed identification system such as: the use of the transient and the steady-state current signals, the use of even and odd-order harmonics as features, and the optimal number of features to take into account. This work also discusses the choice of the Short-Time Fourier Series (STFS) coefficients as adapted features for the representation of transient and steady-state current signals.

Paper Nr: 122
Title:

Pixel-wise Ground Truth Annotation in Videos - An Semi-automatic Approach for Pixel-wise and Semantic Object Annotation

Authors:

Julius Schöning

Abstract: In the last decades, a large diversity of automatic, semi-automatic and manual approaches for video segmentation and knowledge extraction from video-data has been proposed. Due to the high complexity in both the spatial and temporal domain, it continues to be a challenging research area. In order to develop, train, and evaluate new algorithms, ground truth of video-data is crucial. Pixel-wise annotation of ground truth is usually time-consuming, does not contain semantic relations between objects and uses only simple geometric primitives. We provide a brief review of related tools for video annotation, and introduce our novel interactive and semi-automatic segmentation tool iSeg. Extending an earlier implementation, we improved iSeg with a semantic time line, multithreading and the use of ORB features. A performance evaluation of iSeg on four data sets is presented. Finally, we discuss possible opportunities and applications of semantic polygon-shaped video annotation, such as 3D reconstruction and video inpainting.

Paper Nr: 124
Title:

The Role of the Complex Extended Textural Microstructure Co-occurrence Matrix in the Unsupervised Detection of the HCC Evolution Phases, based on Ultrasound Images

Authors:

Delia Mitrea

Abstract: The hepatocellular carcinoma (HCC) is a frequent malignant liver tumour and one of the main causes of death. Detecting the HCC evolution phases is an important issue, aiming the early diagnosis of this tumour and patient monitoring with maximum accuracy. Our objective is to discover the evolution stages of HCC, through unsupervised classification techniques, using advanced texture analysis methods. In this work, we assessed the role that the Haralick features derived from the Complex Extended Textural Microstructure Co-occurrence Matrices (CETMCM) have in the unsupervised detection of the HCC evolution stages. A textural model for these phases was also generated. The obtained results were validated by supervised classifiers, well known for their performance, such as the Multilayer Perceptron (MLP), Support Vector Machines (SVM), respectively decision trees and they were also compared with the previously obtained results in this domain. The final classification accuracy was about 90%.

Paper Nr: 131
Title:

Motion Classification for Analyzing the Order Picking Process using Mobile Sensors - General Concepts, Case Studies and Empirical Evaluation

Authors:

Sascha Feldhorst and Mojtaba Masoudenijad

Abstract: This contribution introduces a new concept to analyze the manual order picking process which is a key task in the field of logistics. The approach relies on a sensor-based motion classification already used in other domains like sports or medical science. Thereby, different sensor data, e. g. acceleration or rotation rate, are continuously recorded during the order picking process. With help of this data, the process can be analyzed to identify different motion classes, like walking or picking, and the time a subject spends in each class. Moreover, relevant motion classes within the order picking process are defined which were identified during field studies in two different companies. These classes are recognized by a classification system working with methods from the field of statistical pattern recognition. The classification is done with a supervised learning approach for which promising results can be shown.

Posters
Paper Nr: 7
Title:

An Adaptive Stigmergy-based System for Evaluating Technological Indicator Dynamics in the Context of Smart Specialization

Authors:

Antonio L. Alfeo, Francesco P. Appio, Mario G. C. A. Cimino and Alessandro Lazzeri

Abstract: Regional innovation is more and more considered an important enabler of welfare. It is no coincidence that the European Commission has started looking at regional peculiarities and dynamics, in order to focus Research and Innovation Strategies for Smart Specialization towards effective investment policies. In this context, this work aims to support policy makers in the analysis of innovation-relevant trends. We exploit a European database of the regional patent application to determine the dynamics of a set of technological innovation indicators. For this purpose, we design and develop a software system for assessing unfolding trends in such indicators. In contrast with conventional knowledge-based design, our approach is biologically-inspired and based on self-organization of information. This means that a functional structure, called track, appears and stays spontaneous at runtime when local dynamism in data occurs. A further prototyping of tracks allows a better distinction of the critical phenomena during unfolding events, with a better assessment of the progressing levels. The proposed mechanism works if structural parameters are correctly tuned for the given historical context. Determining such correct parameters is not a simple task since different indicators may have different dynamics. For this purpose, we adopt an adaptation mechanism based on differential evolution. The study includes the problem statement and its characterization in the literature, as well as the proposed solving approach, experimental setting and results.

Paper Nr: 11
Title:

Estimating Reflectance Parameter of Polyp using Medical Suture Information in Endoscope Image

Authors:

Yuji Iwahori, Daiki Yamaguchi, Tsuyoshi Nakamura and Boonserm Kijsirikul

Abstract: An endoscope is a medical instrument that acquires images inside the human body. In this paper, a new 3-D reconstruction approach is proposed to estimate the size and shape of the polyp under conditions of both point light source illumination and perspective projection. Previous approaches could not know the size of polyp without assuming reflectance parameters as known constant. Even if it was possible to estimate the absolute size of polyp, it was assumed that the parameter of camera movement ∆Z is treated as a known along the depth direction. Here two images are used with a medical suture which is known size object to solve this problem and the proposed approach shows the parameter of camera movement can be estimated with robust accuracy with correspondence between two images taken via slight movement of Z. Experiments with endoscope images are demonstrated to evaluate the validity of proposed approach.

Paper Nr: 25
Title:

Learning from Partially Occluded Faces

Authors:

Fares Al-Qunaieer and Mohamed Alkanhal

Abstract: Although face recognition methods in controlled environments have achieved high accuracy results, there are still problems in real-life situations. Some of the challenges include changes in face expressions, pose, lighting conditions or presence of occlusion. There were several efforts for tackling the occlusion problem, mainly by learning discriminating features from non-occluded faces for occluded faces recognition. In this paper, we propose the reversed process, to learn from the occluded faces for the purpose of non-occluded faces recognition. This process has several useful applications, such as in suspects identification and person re-identification. Correlation filters are constructed from training images (occluded faces) images of each person, which are used later for the classification of input images (non-occluded faces). In addition, the use of skin masks with the correlation filters is investigated.

Paper Nr: 63
Title:

Design of a Low-false-positive Gesture for a Wearable Device

Authors:

Ryo Kawahata, Atsushi Shimada and Takayoshi Yamashita

Abstract: As smartwatches are becoming more widely used in society, gesture recognition, as an important aspect of interaction with smartwatches, is attracting attention. An accelerometer that is incorporated in a device is often used to recognize gestures. However, a gesture is often detected falsely when a similar pattern of action occurs in daily life. In this paper, we present a novel method of designing a new gesture that reduces false detection. We refer to such a gesture as a low-false-positive (LFP) gesture. The proposed method enables a gesture design system to suggest LFP motion gestures automatically. The user of the system can design LFP gestures more easily and quickly than what has been possible in previous work. Our method combines primitive gestures to create an LFP gesture. The combination of primitive gestures is recognized quickly and accurately by a random forest algorithm using our method. We experimentally demonstrate the good recognition performance of our method for a designed gesture with a high recognition rate and without false detection.

Paper Nr: 64
Title:

Fully Automated Soft Contact Lens Detection from NIR Iris Images

Authors:

Balender Kumar

Abstract: Iris is considered as one of the best biometric trait for human authentication due to its accuracy and permanence. However easy iris spoofing raise the risk of false acceptance or false rejection. Recent iris recognition research has made an attempt to quantify the performance degradation due to the use of contact lens. This study proposes a strategy to detect soft contact lens in visual pictures of the eye obtained using NIR sensor. The lens border is detected by considering small annular ring-like area near the outer iris boundary and locating candidate points while traversing along the lens perimeter. The system performance is evaluated over public databases such as IIITD-Cogent, UND 2010, IIITD-Vista along with our self created IITK database. The rigorous experimentation revels the superior performance of the proposed system as compared with other existing techniques.

Paper Nr: 77
Title:

Domain Specific Author Attribution based on Feedforward Neural Network Language Models

Authors:

Zhenhao Ge and Yufang Sun

Abstract: Authorship attribution refers to the task of automatically determining the author based on a given sample of text. It is a problem with a long history and has a wide range of application. Building author profiles using language models is one of the most successful methods to automate this task. New language modeling methods based on neural networks alleviate the curse of dimensionality and usually outperform conventional N-gram methods. However, there have not been much research applying them to authorship attribution. In this paper, we present a novel setup of a Neural Network Language Model (NNLM) and apply it to a database of text samples from different authors. We investigate how the NNLM performs on a task with moderate author set size and relatively limited training and test data, and how the topics of the text samples affect the accuracy. NNLM achieves nearly 2.5\% reduction in perplexity, a measurement of fitness of a trained language model to the test data. Given 5 random test sentences, it also increases the author classification accuracy by 3.43\% on average, compared with the N-gram methods using SRILM tools. An open source implementation of our methodology is freely available at https://github.com/zge/authorship-attribution/.

Paper Nr: 86
Title:

Reducing Uncertainty in User-independent Activity Recognition - A Sensor Fusion-based Approach

Authors:

Pekka Siirtola and Juha Röning

Abstract: In this study, a novel user-independent method to recognize activities accurately in situations where traditional accelerometer based classification contains a lot of uncertainty is presented. The method uses two recognition models: one using only accelerometer data and other based on sensor fusion. However, as a sensor fusionbased method is known to consume more battery than an accelerometer-based, sensor fusion is only used when the classification result obtained using acceleration contains uncertainty and, therefore, is unreliable. This reliability is measured based on the posterior probabilities of the classification result and it is studied in the article how high the probability needs to be to consider it reliable. The method is tested using two data sets: daily activity data set collected using accelerometer and magnetometer, and tool recognition data set consisting of data from accelerometer and gyroscope measurements. The results show that by applying the presented method, the recognition rates can be improved compared to using only accelerometers. It was noted that all the classification results should not be trusted as posterior probabilities under 95% cannot be considered reliable, and by replacing these results with the results of sensor fusion -based model, the recognition accuracy improves from three to six percentage units.

Paper Nr: 91
Title:

Robust Registration Method of 3D Point Cloud Data

Authors:

Sungho Suh

Abstract: 3D point cloud data is used for 3D model acquisition, geometry processing and 3D inspection. Registration of 3D point cloud data is crucial for each field. The difference between 2D image registration and 3D point cloud registration is that the latter requires several things to be considered: translation on each plane, rotation, tilt and etc. This paper describes a method of registering 3D point cloud data with noise. The relationship between the two sets of 3D point cloud data can be obtained by Affine transformation. In order to calculate 3D Affine transformation matrix, corresponding points are required. To find the corresponding points, we use the height map which is projected from 3D point cloud data onto XY plane. We formulate the height map matching as a cost function and estimate the corresponding points. To find the proper 3D Affine transformation matrix, we formulate a cost function which uses the relationship of the corresponding points. Also the proper 3D Affine transformation matrix can be calculated by minimizing the cost function. The experimental results show that the proposed method can be applied to various objects and gives better performance than the previous work.

Paper Nr: 93
Title:

A Novel Algorithm for String Matching with Mismatches

Authors:

Vinod-prasad P.

Abstract: We present an online algorithm to deal with pattern matching in strings. The problem we investigate is commonly known as ‘string matching with mismatches’ in which the objective is to report the number of characters that match when a pattern is aligned with every location in the text. The novel method we propose is based on the frequencies of individual characters in the pattern and the text. Given a pattern of length M, and the text of length N, both defined over an alphabet of size σ, the algorithm consumes O(M) space and executes in O(MN/σ) time on the average. The average execution time O(MN/σ) simplifies to O(N) for patterns of size M ≤ σ. The algorithm makes use of simple arrays, which reduces the cost overhead to maintain the complex data structures such as suffix trees or automaton.

Paper Nr: 99
Title:

A Practical Framework for the Development of Augmented Reality Applications by using ArUco Markers

Authors:

Danilo Avola, Luigi Cinque and Gian Luca Foresti

Abstract: The Augmented Reality (AR) is an expanding field of the Computer Graphics (CG) that merges items of the real-world environment (e.g., places, objects) with digital information (e.g., multimedia files, virtual objects) to provide users with an enhanced interactive multi-sensorial experience of the real-world that surrounding them. Currently, a wide range of devices is used to vehicular AR systems. Common devices (e.g., cameras equipped on smartphones) enable users to receive multimedia information about target objects (non-immersive AR). Advanced devices (e.g., virtual windscreens) provide users with a set of virtual information about points of interest (POIs) or places (semi-immersive AR). Finally, an ever-increasing number of new devices (e.g., HeadMounted Display, HMD) support users to interact with mixed reality environments (immersive AR). This paper presents a practical framework for the development of non-immersive augmented reality applications through which target objects are enriched with multimedia information. On each target object is applied a different ArUco marker. When a specific application hosted inside a device recognizes, via camera, one of these markers, then the related multimedia information are loaded and added to the target object. The paper also reports a complete case study together with some considerations on the framework and future work.

Paper Nr: 105
Title:

On the Use of Feature Descriptors on Raw Image Data

Authors:

Alina Trifan and António J. R. Neves

Abstract: Local feature descriptors and detectors have been widely used in computer vision in the last years for solving object detection and recognition tasks. Research efforts have been focused on reducing the complexity of these descriptors and improving their accuracy. However, these descriptors have not been tested until now on raw image data. This paper presents a study on the use of two of the most known and used feature descriptors, SURF and SIFT, directly on raw CFA images acquired by a digital camera. We are interested in understanding if the number and quality of the keypoints obtained from a raw image are comparable to the ones obtained in the grayscale images, which are normally used by these transforms. The results that we present show that the number and positions of the keypoints obtained from grayscale images are similar to the ones obtained from CFA images and furthermore to the ones obtained from grayscale images that resulted directly from the interpolation of a CFA image.

Paper Nr: 106
Title:

The Effects of Visual and Auditory Stimulation on EEG Power Spectra during the Viewing of Disgust-Eliciting Videos

Authors:

Mi-Jin Lee

Abstract: Disgust is an affect produced in response to something that is offensive or unpleasant. This emotion is associated with feelings of dizziness and vomiting and, in severe cases, mental illnesses, such as obsessive compulsive disorder and depression. Most experimental electroencephalography (EEG) studies on disgust have identified activated brain areas or disgust elicitors or examined the effects of unimodal stimulation, such as visual, auditory, olfactory, or haptic stimulation. This EEG study examined the effects of disguste liciting visual stimuli that were presented with different auditory stimuli in relative power spectrum analyses of the delta-, theta-, alpha-, beta-, and gamma-wave bands. The EEG data were collected while the participants watched disgust-eliciting videos of body mutilation and disgusting creatures with the original soundtrack or auditory stimuli. Two types of auditory stimuli were used: relaxing music or exciting music. The EEG power spectra of all of the frequency bands were lower in response to videos with auditory stimuli compared with videos with the original soundtracks. Additionally, the mood of the music aroused different responses depending on the type of disgust elicitor, and the types of music that reduced disgust differed according to the different types of disgust elicitors.

Paper Nr: 118
Title:

Investigation of Gait Representations in Lower Knee Gait Recognition

Authors:

Chirawat Wattanapanich and Hong Wei

Abstract: This paper investigates the effect of lower knee gait representations on gait recognition. After reviewing three emerging gait representations, i.e. Gait Energy Image (GEI), Gait Entropy Image (GEnI), and Gait Gaussian Image (GGI), a new gait representation, Gait Gaussian Entropy Image (GGEnI), is proposed to combine advantages of entropy and Gaussian in improving the robustness to noises and appearance changes. Experimental results have shown that lower knee gait representations can successfully detect camera view angles in CASIA Gait Dataset B, and they are better than full body representations in gait recognition under the condition of wearing coat. The gait representations involving the Gaussian technique have shown robustness to noises, whilst the representations involving entropy provide a better robustness to appearance changes.

Paper Nr: 119
Title:

A Ground Truth Vision System for Robotic Soccer

Authors:

António J. R. Neves and Fred Gomes

Abstract: Robotic soccer represents an innovative and appealing test bed for the most recent advances in multi-agent systems, artificial intelligence, perception and navigation and biped walking. The main sensorial element of a soccer robot must be its perception system, most of the times based on a digital camera, through which the robot analyses the surrounding world and performs accordingly. Up to this date, the validation of the vision system of a soccer robots can only be related to the way the robot and its team mates interpret the surroundings, relative to their owns. In this paper we propose an external monitoring vision system that can act as a ground truth system for the validations of the objects of interest of a robotic soccer game, mainly robots and ball. The system we present is made of two to four digital cameras, strategically positioned above the soccer field. We present preliminary results regarding the accuracy of the detection of a soccer ball, which proves that such a system can indeed be used as a provider for ground truth ball positions on the field during a robotic soccer game.