Social video sites where people share their opinions and feelings are increasing in popularity. The face is known to reveal important aspects of human psychological traits, so the understanding of how facial expressions relate to personal constructs is a relevant problem in social media. We present a study of the connections between automatically extracted facial expressions of emotion and impressions of Big-Five personality traits in YouTube vlogs (i.e., video blogs). We use the Computer Expression Recognition Toolbox (CERT) system to characterize users of conversational vlogs. From CERT temporal signals corresponding to instantaneously recognized facial expression categories, we propose and derive four sets of behavioral cues that characterize face statistics and dynamics in a compact way. The cue sets are first used in a correlation analysis to assess the relevance of each facial expression of emotion with respect to Big-Five impressions obtained from crowd-observers watching vlogs, and also as features for automatic personality impression prediction. Using a dataset of 281 vloggers, the study shows that while multiple facial expression cues have significant correlation with several of the Big-Five traits, they are only able to significantly predict Extraversion impressions with moderate values of R2.

Controlling multiple devices while driving steals drivers' attention from the road and is becoming the cause of accidents in 1 out of 3 cases. Many research efforts are being dedicated to design, manufacture and test Human-Machine Interfaces that allow operating car devices without distracting the drivers' attention. A complete system for controlling the infotainment equipment through hand gestures is explained in this paper. The system works with a visible-infrared camera mounted on the ceiling of the car and pointing to the shift-stick area, and is based in a combination of some new and some well-known computer vision algorithms. The system has been tested by 23 volunteers on a car simulator and a real vehicle and the results show that the users slightly prefer this system to an equivalent one based on a touch-screen interface.

Parameterized Appearance Models, such as Active Appearance Models (AAM), Morphable Models, or Boosted Appearance Models, have been extensively used for face alignment. Discriminative methods learn a mapping function between appearance features and shape parameters. Different mapping functions have been studied in the literature, including linear regression, which has proved to perform well when close to the true solution. Despite its easiness, it still suffers from two major drawbacks: 1) It takes the whole data without highlighting relations among different regions of the face, and 2) it is computationally expensive both in time and memory. In this paper, we analyze the covariance of the training data, and propose a way to find related information. By clustering those patches that are related, we reach a noise-reduced regression matrix. Then, we construct a clean mapping matrix, with reduced dimensionality, taking only the relevant training information. Experiments show that this method outperforms linear regression for face alignment.

This paper describes a fully automated Real-Time Lecturer-Tracking module (RTLT) and the seamless integration into a Matter horn-based Lecture Capturing System (LCS). The main purpose of the RTLT module is obtaining a lecturer's portrait image for creating an integrated slides lecturer single-stream ready to distribute and consume in portable devices, where displayed contents must be optimized. The module robustly tracks any number of presenters in real-time using a set of visual cues and delivers frame-rate metadata to plug into a Virtual Cinematographer module. The so-called Gal tracker RTLT module allows broadcasting live in conjunction with the LCS, Gal caster, or processing off-line as a video-production engine inserted into the Matter horn workflow.

Data security and privacy are crucial issues to be addressed for assuring a successful deployment of biometrics-based recognition systems in real life applications. In this paper, a template protection scheme exploiting the properties of universal background models, eigen-user spaces, and the fuzzy commitment cryptographic protocol is presented. A detailed discussion on the security and information leakage of the proposed template protection system is given. The effectiveness of the proposed approach is investigated with application to online signature recognition. The given experimental results, evaluated on the public MCYT signature database, show that the proposed system can guarantee competitive recognition accuracy while providing protection to the employed biometric data.

The success of generative models for online signature verification has motivated many research works on this topic. These systems may use hidden Markov models (HMMs) in two different modes: user-specific HMM (US-HMM) and user-adapted universal background models (UBMs) (UA-UBMs). Verification scores can be obtained from likelihood ratios and a distance measure on the Viterbi decoded state sequences. This paper analyzes several factors that can modify the behavior of these systems and which have not been deeply studied yet. First, we study the influence of the feature set choice, paying special attention to the role of dynamic information order, suitability of feature sets on each kind of generative model-based system, and the importance of inclination angles and pressure. Moreover, this analysis is also extended to the influence of the HMM complexity in the performance of the different approaches. For this study, a set of experiments is performed on the publicly available MCYT-100 database using only skilled forgeries. These experiments provide interesting outcomes. First, the Viterbi path evidences a notable stability for most of the feature sets and systems. Second, in the case of US-HMM systems, likelihood evidence obtains better results when lowest order dynamics are included in the feature set, while likelihood ratio obtains better results in UA-UBM systems when lowest dynamics are not included in the feature set. Finally, US-HMM and UA-UBM systems can be used together for improved verification performance by fusing at the score level the Viterbi path information from the US-HMM system and the likelihood ratio evidence from the UA-UBM system. Additional comparisons to other state-of-the-art systems, from the ESRA 2011 signature evaluation contest, are also reported, reinforcing the high performance of the systems and the generality of the experimental results described in this paper.

In this paper, we present the main results of the BioSecure Signature Evaluation Campaign (ESRA'2011). The objective of ESRA'2011 is to evaluate through two different tasks the resistance of different online signature systems to skilled forgeries categorized automatically according to their quality. Task 1 aims at studying with only coordinate time functions the influence of acquisition conditions (digitizing tablet vs. PDA) on systems' performance. The two BioSecure Data Sets DS2 and DS3 make this possible, since they contain data from the same 382 people, acquired respectively on a digitizer and on a PDA. Task 2 then aims at assessing the contribution of the five time functions available on a digitizer (coordinates, pressure, pen inclination) on systems' resistance to different qualities of skilled forgeries. Results of the 13 systems involved in this competition are reported and analyzed for both tasks in this paper. We observe that the best system in terms of performance on forgeries of "bad" quality is not necessarily the most resistant to an increased quality of skilled forgeries. Also, we note that mobile conditions are still threatening independently of the quality of forgeries. Finally, when adding pen inclination time functions to pressure and coordinates, we find that the gap between systems in terms of performance is wider than when only pen coordinates and pressure are considered.

A general purpose driver's monitoring system should be able to robustly estimate the main rigid and elastic facial movements through time. Model-based methods have many advantages over feature-based methods for succeeding in this task. This paper presents a system for robust real-time tracking of a set of facial landmarks based on Active Appearance Models. The main differences with other AAM proposals in the literature are twofold. First, a run-time adaptation of the AAM regression matrix using a recursive algorithm to improve convergence precision, second, a multiresolution pose-dependent strategy, PD-AAM, to reduce error in landmarks location for rotated faces and to reduce also computational burden. The proposal is tested in the BUHMAP database, a public database with head and expression movements and in an own set of videos captured in a car. Tests show that the conjunction of these two strategies improve results over a classical AAM tracking system.

Human vision is primarily based on local contrast perception and its polarity. Viola and Jones proposed, in their well-known face detector framework, a boosted cascade of weak classifiers based on Haar-like features which encode local contrast and polarity information. Nevertheless contrast polarity invariance, which is not directly modeled in their framework, has been shown to be perceptually relevant for the human capability of detecting faces. In this paper we study, from both algorithmical and perceptual points of view, the effect of enhancing Haar-like features with polarity invariance and how it may improve cascaded classifiers.

In this paper we present a fully automatic system for face recognition across pose where no frontal view is needed in enrollment or test. The system uses three Active Appearance Models(AAMs): the first one is a generic multi resolution AAM, while the remaining ones are trained to cope with left/right variations (i.e. pose-dependent AAMs). During the fitting stage, pose is automatically estimated using eigenvector analysis, and a synthetic face is generated through texture warping. Results over CMU PIE Database show promising results compared to the performance achieved with manually land marked faces.

Advanced driver assistance systems have strong restrictions for real-time performance. Vision algorithms embedded in these systems need to balance accuracy and computational simplicity and there exists a continuous challenge to increase both goals. In this paper we define a new operator coined as Local Contour Patterns and use it in fast Hough-Transform-based approaches for circle and line detectors. We show an efficient implementation for traffic sign detection, relying only on shape information, that analyzes a 752 × 480 grayscale image in 40 ms in a Intel 8400 CPU, with a very good performance in real driving conditions.

A new multimodal biometric database designed and acquired within the framework of the European BioSecure Network of Excellence is presented. It is comprised of more than 600 individuals acquired simultaneously in three scenarios: 1) over the Internet, 2) in an office environment with desktop PC, and 3) in indoor/outdoor environments with mobile portable hardware. The three scenarios include a common part of audio/video data. Also, signature and fingerprint data have been acquired both with desktop PC and mobile portable hardware. Additionally, hand and iris data were acquired in the second scenario using desktop PC. Acquisition has been conducted by 11 European institutions. Additional features of the BioSecure Multimodal Database (BMDB) are: two acquisition sessions, several sensors in certain modalities, balanced gender and age distributions, multimodal realistic scenarios with simple and quick tasks per modality, cross-European diversity, availability of demographic data, and compatibility with other multimodal databases. The novel acquisition conditions of the BMDB allow us to perform new challenging research and evaluation of either monomodal or multimodal biometric systems, as in the recent BioSecure Multimodal Evaluation campaign. A description of this campaign including baseline results of individual modalities from the new database is also given. The database is expected to be available for research purposes through the BioSecure Association during 2008.

Person recognition using facial features, e.g., mug-shot images, has long been used in identity documents. However, due to the widespread use of web-cams and mobile devices embedded with a camera, it is now possible to realize facial video recognition, rather than resorting to just still images. In fact, facial video recognition offers many advantages over still image recognition; these include the potential of boosting the system accuracy and deterring spoof attacks. This paper presents an evaluation of person identity verification using facial video data, organized in conjunction with the International Conference on Biometrics (ICB 2009). It involves 18 systems submitted by seven academic institutes. These systems provide for a diverse set of assumptions, including feature representation and preprocessing variations, allowing us to assess the effect of adverse conditions, usage of quality information, query selection, and template construction for video-to-video face authentication.

Generalized Gaussian (GG) densities have been recently proposed to model both real and imaginary parts of Gabor coefficients. However, when matching faces, most systems make use of magnitude information only, due to its smooth behavior with displacements. The first goal of this paper is to propose a novel statistical model for the magnitude of Gabor coefficients, supposed that both real and imaginary parts are GG distributed. The proposed model, namely the ß-Rayleigh distribution, Rß(¿), is a generalization of the standard Rayleigh, R(¿), density. The Kullback Leibler (KL) divergence is used to measure the fitting accuracy of the model, showing the benefits of Rß(¿) over standard R(¿). The second goal of the paper tackles the selection of distance measures for Gabor features comparison, a topic that has received little attention in the literature. Inspired by the proposed statistical model, different ¿ßnorms are tested on the XM2VTS database, showing interesting results that confirm that classical distances used in Gabor-based recognition systems do not provide the best performance.

In this paper we present a solution to obtain useful and reliable user logs in a Learning Management System (LMS).Current LMS logs are combined with biometric-based logs that show the student behaviour. Our system models the student behaviour, allowing to know exactly how much time the student spends in front of the computer examining the con-tents of the LMS. Besides, user verification and face tracking are also integrated, what guarantees that the student is the person actually interacting with the system. The presented multimodal solution for user tracking and user ver-ification combines face tracking, face verification, speakerverification and fingerprint verification. Face tracking and face verification are performed in a non-collaborative fashion. Fingerprint or speaker verification is performed on demand, with the aim of avoiding a negative influence of adverse environmental or behavioural human factors in the reliability of the user logs generated by the system. These circumstances can thwart the non collaborative face veri-fication performance involved in the tracking process. The presented solution solves the problem of user tracking and authentication even in adverse environments for face verification.

Despite of the advances in the e-learning domain during the last decades, there is a lack of suitable mechanism to carry out assessment with the appropriate measures to avoid cheating. Current LMSs do not provide the needed features to check that the intended student is taking the online exam by himself, or even to know if he has spent the whole session time in front of the computer. This paper presents a web-based application that offers biometric authentication based on face-recognition. This application, which can be easily integrated in currently available LMSs, is able to use face-recognition during access control, tracking and assessment. Thus it is possible to improve security during critical phases in the learning process (e.g. assessment).

It has been shown in many different contexts that the Generalized Gaussian (GG) distribution represents a flexible and suitable tool for data modeling. Almost all the reported applications are focused on modeling points (fixed length vectors); a different but crucial scenario, where the employment of the GG has received little attention, is the modeling of sequential data, i.e. variable length vectors. This paper explores this last direction, describing a variant of the well known Hidden Markov Model (HMM) where the emission probability function of each state is represented by a GG. A training strategy based on the Expectation Maximization (EM) algorithm is presented. Different experiments using both synthetic and real data (EEG signal classification and face recognition) show the suitability of the proposed approach compared with the standard Gaussian HMM.

This paper tackles the problem of pose variations in a 2D face recognition scenario. Using a training set of sparse face meshes, we built a point distribution model and identified the parameters which are responsible for controlling the apparent changes in shape due to turning and nodding the head, namely the pose parameters. Given a test image and its associated mesh, the pose parameters are set to typical values of frontal faces, thus obtaining a virtual frontal mesh. Taking advantage of facial symmetry, we overcome problems due to self-occlusion and virtual frontal faces are synthesized via thin plate splines-based texture mapping. These corrected images are then fed into a recognition system that makes use of Gabor filtering for feature extraction. The CMU PIE database is used to assess the performance of the proposed method in a closed-set identification scenario where large pose variations are present, achieving state-of-the-art results.

Gabor filters are biologically motivated convolution kernels that have been widely used in the field of computer vision and, specially, in face recognition during the last decade. This paper proposes a statistical model of Gabor coefficients extracted from face images using generalized Gaussian distributions (GGD's). By measuring the Kullback-Leibler distance (KLD) between the pdf of the GGD and the relative frequency of the coefficients, we conclude that GGD's provide an accurate modeling. The underlying statistics allow us to reduce the required amount of data to be stored (i.e. data compression) via Lloyd-Max quantization. Verification experiments on the XM2VTS database show that performance does not drop when, instead of the original data, we use quantized coefficients.

This paper proposes novel ways to deal with pose variations in a 2-D face recognition scenario. Using a training set of sparse face meshes, we built a point distribution model and identified the parameters which are responsible for controlling the apparent changes in shape due to turning and nodding the head, namely the pose parameters. Based on them, we propose two approaches for pose correction: 1) a method in which the pose parameters from both meshes are set to typical values of frontal faces, and 2) a method in which one mesh adopts the pose parameters of the other one. Finally, we obtain pose corrected meshes and, taking advantage of facial symmetry, virtual views are synthesized via Thin Plate Splines-based warping. Given that the corrected images are not embedded into a constant reference frame, holistic methods are not suitable for feature extraction. Instead, the virtual faces are fed into a system that makes use of Gabor filtering for recognition. Unlike other approaches that warp faces onto a mean shape, we show that if only pose parameters are modified, client specific information remains in the warped image and discrimination between subjects is more reliable. Statistical analysis of the authentication results obtained on the XM2VTS database confirm the hypothesis. Also, the CMU PIE database is used to assess the performance of the proposed methods in an identification scenario where large pose variations are present, achieving state-of-the-art results and outperforming both research and commercial techniques.

This paper proposes, through the combination of concepts and tools from different fields within the computer vision community, an alternative path to the selection of key points in face images. The classical way of attempting to solve the face recognition problem using algorithms which encode local information is to localize a predefined set of points in the image, extract features from the regions surrounding those locations, and choose a measure of similarity (or distance) between correspondent features. Our approach, namely shape-driven Gabor jets, aims at selecting an own set of points and features for a given client. After applying a ridges and valleys detector to a face image, characteristic lines are extracted and a set of points is automatically sampled from these lines where Gabor features (jets) are calculated. So each face is depicted by R2points and their respective jets. Once two sets of points from face images have been extracted, a shape-matching algorithm is used to solve the correspondence problem (i.e., map each point from the first image to a point within the second image) so that the system is able to compare shape-matched jets. As a byproduct of the matching process, geometrical measures are computed and compiled into the final dissimilarity function. Experiments on the AR face database confirm good performance of the method against expression and, mainly, lighting changes. Moreover, results on the XM2VTS and BANCA databases show that our algorithm achieves better performance than implementations of the elastic bunch graph matching approach and other related techniques.

In this paper, we use a robust shape matching algorithm for establishing correspondences between points from face images, and Gabor vectors (jets) for feature computation. After extracting characteristic lines from faces, which is accomplished by using the ridges and valleys operator, shape is sampled through a set of points, where jets are calculated. So, each face is depicted by /spl Rfr//sup 2/ points, and their respective jets. Once two sets of points from face images have been extracted, the shape matching algorithm is used to solve the correspondence problem. A measure between the set of matched points gives an idea of the similarity of the faces. Also, comparison between shape-matched jets is possible, given that they are supposed to be located over the same face parts, leading to a system that is able to take shape and texture into account for face authentication.

This paper formulates an incomplete projection algorithm that is applied to the image recovery problem. The algorithm allows an easy implementation of dynamic load balancing for parallel architectures. Furthermore, the local computation-communication load ratio can be adjusted, since each processor performs a finite number of iterations of any projection-type technique, and this number can be provided as a parameter of the algorithm. Numerical results compare favorably with those obtained by the extrapolated method of parallel subgradient projections.

We investigated how hoarseness effects perceived hypernasality ratings in order to make a rating scale for hoarse voices. Thirty stimuli, of which 18 were target stimuli (three each for voices with and without hoarseness at three levels of hypernasality), and of which 12 were foil stimuli. These voices were listened to by four experienced speech pathologists. They were asked to rate hypernasality on 5-point scale. Perceived hypernasality decreased with hoarseness for a severely hypernasal voice, but results varied among the listeners for voices with no and moderate hypernasality.