Analyse de mouvements faciaux à partir d'images vidéo

Lors d'une intervention conversationnelle, le langage est supporté par une communication non-verbale qui joue un rôle central dans le comportement social humain en permettant de la rétroaction et en gérant la synchronisation, appuyant ainsi le contenu et la signification du discours. En effet, 55% du message est véhiculé par les expressions faciales, alors que seulement 7% est dû au message linguistique et 38% au paralangage. L'information concernant l'état émotionnel d'une personne est généralement inférée par les attributs faciaux. Cependant, on ne dispose pas vraiment d'instruments de mesure spécifiquement dédiés à ce type de comportements. En vision par ordinateur, on s'intéresse davantage au développement de systèmes d'analyse automatique des expressions faciales prototypiques pour les applications d'interaction homme-machine, d'analyse de vidéos de réunions, de sécurité, et même pour des applications cliniques. Dans la présente recherche, pour appréhender de tels indicateurs observables, nous essayons d'implanter un système capable de construire une source consistante et relativement exhaustive d'informations visuelles, lequel sera capable de distinguer sur un visage les traits et leurs déformations, permettant ainsi de reconnaître la présence ou absence d'une action faciale particulière. Une réflexion sur les techniques recensées nous a amené à explorer deux différentes approches. La première concerne l'aspect apparence dans lequel on se sert de l'orientation des gradients pour dégager une représentation dense des attributs faciaux. Hormis la représentation faciale, la principale difficulté d'un système, qui se veut être général, est la mise en œuvre d'un modèle générique indépendamment de l'identité de la personne, de la géométrie et de la taille des visages. La démarche qu'on propose repose sur l'élaboration d'un référentiel prototypique à partir d'un recalage par SIFT-flow dont on démontre, dans cette thèse, la supériorité par rapport à un alignement conventionnel utilisant la position des yeux. Dans une deuxième approche, on fait appel à un modèle géométrique à travers lequel les primitives faciales sont représentées par un filtrage de Gabor. Motivé par le fait que les expressions faciales sont non seulement ambigües et incohérentes d'une personne à une autre mais aussi dépendantes du contexte lui-même, à travers cette approche, on présente un système personnalisé de reconnaissance d'expressions faciales, dont la performance globale dépend directement de la performance du suivi d'un ensemble de points caractéristiques du visage. Ce suivi est effectué par une forme modifiée d'une technique d'estimation de disparité faisant intervenir la phase de Gabor. Dans cette thèse, on propose une redéfinition de la mesure de confiance et introduisons une procédure itérative et conditionnelle d'estimation du déplacement qui offrent un suivi plus robuste que les méthodes originales.

The typic in Kant’s critique of practical reason : moral judgment and symbolic representation

Comment pouvons-nous représenter un principe moral universel de manière à le rendre applicable à des cas concrets ? Ce problème revêt une forme aiguë dans la philosophie morale d’Emmanuel Kant (1724-1804), tout particulièrement dans sa théorie du jugement moral, car il soutient que l’on doit appliquer la loi morale « suprasensible » à des actions dans le monde sensible afin de déterminer celles-ci comme moralement bonnes ou mauvaises. Kant aborde ce problème dans un chapitre de la Critique de la raison pratique (1788) intitulé « De la typique de la faculté de juger pratique pure » (KpV 5: 67-71). La première partie de la thèse vise à fournir un commentaire compréhensif et détaillé de ce texte important, mais trop peu étudié. Étant donné que la loi morale, en tant qu’Idée suprasensible de la raison, ne peut pas être appliquée directement à des actions dans l’intuition sensible, Kant a recours à une forme particulière de représentation indirecte et symbolique. Sa solution inédite consiste à fournir la faculté de juger avec un « type [Typus] », ou analogue formel, de la loi morale. Ce type est la loi de la causalité naturelle : en tant que loi, il sert d’étalon formel pour tester l’universalisabilité des maximes ; et, en tant que loi de la nature, il peut aussi s’appliquer à toute action dans l’expérience sensible. Dès lors, le jugement moral s’effectue par le biais d’une expérience de pensée dans laquelle on se demande si l’on peut vouloir que sa maxime devienne une loi universelle d’une nature contrefactuelle dont on ferait soi-même partie. Cette expérience de pensée fonctionne comme une « épreuve [Probe] » de la forme des maximes et, par ce moyen, du statut moral des actions. Kant soutient que tout un chacun, même « l’entendement le plus commun », emploie cette procédure pour l’appréciation morale. De plus, la typique prémunit contre deux menaces à l’éthique rationaliste de Kant, à savoir l’empirisme (c’est-à-dire le conséquentialisme) et le mysticisme. La seconde partie de la thèse se penche sur l’indication de Kant que la typique « ne sert que comme un symbole ». Un bon nombre de commentateurs ont voulu assimiler la typique à la notion d’« hypotypose symbolique » présentée dans le § 59 de la Critique de la faculté de juger (1790). La typique serait un processus de symbolisation esthétique consistant à présenter, de façon indirecte, la représentation abstraite de la loi morale sous la forme d’un symbole concret et intuitif. Dans un premier chapitre, cette interprétation est présentée et soumise à un examen critique qui cherche à montrer qu’elle est erronée et peu judicieuse. Dans le second chapitre, nous poursuivons une voie d’interprétation jusqu’ici ignorée, montrant que la typique a de plus grandes continuités avec la notion d’« anthropomorphisme symbolique », une procédure strictement analogique introduite auparavant dans les Prolégomènes (1783). Nous en concluons, d’une part, que la typique fut un moment décisif dans l’évolution de la théorie kantienne de la représentation symbolique et que, d’autre part, elle marque la réalisation, chez Kant, d’une conception proprement critique de la nature et de la morale comme deux sphères distinctes, dont la médiation s’opère par le biais des concepts de loi et de conformité à la loi (Gesetzmässigkeit). En un mot, la typique s’avère l’instrument par excellence du « rationalisme de la faculté de juger ».

Learning-Based Approach to Real Time Tracking and Analysis of Faces

This paper describes a trainable system capable of tracking faces and facialsfeatures like eyes and nostrils and estimating basic mouth features such as sdegrees of openness and smile in real time. In developing this system, we have addressed the twin issues of image representation and algorithms for learning. We have used the invariance properties of image representations based on Haar wavelets to robustly capture various facial features. Similarly, unlike previous approaches this system is entirely trained using examples and does not rely on a priori (hand-crafted) models of facial features based on optical flow or facial musculature. The system works in several stages that begin with face detection, followed by localization of facial features and estimation of mouth parameters. Each of these stages is formulated as a problem in supervised learning from examples. We apply the new and robust technique of support vector machines (SVM) for classification in the stage of skin segmentation, face detection and eye detection. Estimation of mouth parameters is modeled as a regression from a sparse subset of coefficients (basis functions) of an overcomplete dictionary of Haar wavelets.

Example Based Learning for View-Based Human Face Detection

We present an example-based learning approach for locating vertical frontal views of human faces in complex scenes. The technique models the distribution of human face patterns by means of a few view-based "face'' and "non-face'' prototype clusters. At each image location, the local pattern is matched against the distribution-based model, and a trained classifier determines, based on the local difference measurements, whether or not a human face exists at the current image location. We provide an analysis that helps identify the critical components of our system.

Reduced face preference in infancy: a developmental precursor to callous-unemotional traits?

Background Children with callous-unemotional (CU) traits, a proposed precursor to adult psychopathy, are characterized by impaired emotion recognition, reduced responsiveness to others’ distress, and a lack of guilt or empathy. Reduced attention to faces, and more specifically to the eye region, has been proposed to underlie these difficulties, although this has never been tested longitudinally from infancy. Attention to faces occurs within the context of dyadic caregiver interactions, and early environment including parenting characteristics has been associated with CU traits. The present study tested whether infants’ preferential tracking of a face with direct gaze and levels of maternal sensitivity predict later CU traits. Methods Data were analyzed from a stratified random sample of 213 participants drawn from a population-based sample of 1233 first-time mothers. Infants’ preferential face tracking at 5 weeks and maternal sensitivity at 29 weeks were entered into a weighted linear regression as predictors of CU traits at 2.5 years. Results Controlling for a range of confounders (e.g., deprivation), lower preferential face tracking predicted higher CU traits (p = .001). Higher maternal sensitivity predicted lower CU traits in girls (p = .009), but not boys. No significant interaction between face tracking and maternal sensitivity was found. Conclusions This is the first study to show that attention to social features during infancy as well as early sensitive parenting predict the subsequent development of CU traits. Identifying such early atypicalities offers the potential for developing parent-mediated interventions in children at risk for developing CU traits.

Interactional dynamics in on-line and face-to-face peer-tutoring sessions for second language writers

This paper reports the results of a study comparing the interactional dynamics of face-to-face and on-line peer-tutoring in writing by university students in Hong Kong. Transcripts of face-to-face tutoring sessions, as well as logs of on-line sessions conducted by the same peer-tutors, were coded for speech functions using a system based on Halliday's functional-semantic view of dialogue. Results show considerable differences between the interactional dynamics in on-line and face-to-face tutoring sessions. In particular, face-to-face interactions involved more hierarchal encounters in which tutors took control of the discourse, whereas on-line interactions were more egalitarian, with clients controlling the discourse more. Differences were also found in the topics participants chose to focus on in the two modes, with issues of grammar, vocabulary, and style taking precedence in face-to-face sessions and more “global” writing concerns like content and process being discussed more in on-line sessions.

Voice, appropriation and discourse representation in a student writing task

We investigate the practices by which bilingual university students in Hong Kong appropriate texts in producing utterances, particularly written texts. Following Wertsch and his colleagues we ask: • To what extent do our students appropriate texts in constructing their own discourses? • What linguistic means do they use to do this? • What can these processes tell us about what they now can do with discourse representation; and • What do we need to teach them? This research shows that our students' writing displays considerable intertextuality and interdiscursivity. Responses to this writing in tutorial sessions indicate that they are skilled at orchestrating the multiple voices within their own discourses. The commonly stated concern that our students do not know how to do quotation and citation correctly is somewhat misplaced and researchers need to move the focus away from the mechanisms of citation and attribution to the social practices of textual appropriation.

U-curve: A branch-and-bound optimization algorithm for U-shaped cost functions on Boolean lattices applied to the feature selection problem

This paper presents the formulation of a combinatorial optimization problem with the following characteristics: (i) the search space is the power set of a finite set structured as a Boolean lattice; (ii) the cost function forms a U-shaped curve when applied to any lattice chain. This formulation applies for feature selection in the context of pattern recognition. The known approaches for this problem are branch-and-bound algorithms and heuristics that explore partially the search space. Branch-and-bound algorithms are equivalent to the full search, while heuristics are not. This paper presents a branch-and-bound algorithm that differs from the others known by exploring the lattice structure and the U-shaped chain curves of the search space. The main contribution of this paper is the architecture of this algorithm that is based on the representation and exploration of the search space by new lattice properties proven here. Several experiments, with well known public data, indicate the superiority of the proposed method to the sequential floating forward selection (SFFS), which is a popular heuristic that gives good results in very short computational time. In all experiments, the proposed method got better or equal results in similar or even smaller computational time. (C) 2009 Elsevier Ltd. All rights reserved.

Road and Traffic Signs Recognition using Vector Machines

Intelligent Transportation System (ITS) is a system that builds a safe, effective and integrated transportation environment based on advanced technologies. Road signs detection and recognition is an important part of ITS, which offer ways to collect the real time traffic data for processing at a central facility.This project is to implement a road sign recognition model based on AI and image analysis technologies, which applies a machine learning method, Support Vector Machines, to recognize road signs. We focus on recognizing seven categories of road sign shapes and five categories of speed limit signs. Two kinds of features, binary image and Zernike moments, are used for representing the data to the SVM for training and test. We compared and analyzed the performances of SVM recognition model using different features and different kernels. Moreover, the performances using different recognition models, SVM and Fuzzy ARTMAP, are observed.

A percepção das características da face infantil por adultos e crianças sob uma perspectiva evolucionista

Child facial cues evoke attention, parental care behaviors and modulate for infant- caretaker interactions. Lorenz described the baby schema ( Kindchenschema ) as a set of infantile physical features such as the large head, round face, high and protruding forehead, big eyes, chubby cheeks, small nose and mouth. Previous work on this fundamental concept was restricted to positive perception to infant face, and did not show consistent results about the development individuals perceptions, regarding the physical attributes that worked as markers of cuteness. Here, we experimentally tested the effects of baby schema on the perception of cuteness of infant faces by children and adults. We used 60 none graphically manipulated photos of different stimulus children faces from 4 to 9 years old. In the first task for the adults experimental subjects, ten stimulus photos were shown, whereas for children experimental subjects, four stimulus photos were shown at a time, with a total of six rounds. The second task involved only adults, who indicated the motivation of affective behaviors and care directed to children through a Likert scale. Our results suggest that both participants judged similarly the cuteness of children's faces, and the physical features markers of this perception were observed only for younger stimulus children. Adults have attributed more motivations of positive behaviors to cuter stimulus children. The recognition of the baby schema by individuals of different ages and genders confers the universality and power of children's physical attributes. From the evolutionary perspective the responsiveness to baby schema is significant to ensure aloparental and parental investment, and the consequent children survival

Tests of one Brazilian facial reconstruction method using three soft tissue depth sets and familiar assessors

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Husserl on Geometry and Spatial Representation

Husserl left many unpublished drafts explaining (or trying to) his views on spatial representation and geometry, such as, particularly, those collected in the second part of Studien zur Arithmetik und Geometrie (Hua XXI), but no completely articulate work on the subject. In this paper, I put forward an interpretation of what those views might have been. Husserl, I claim, distinguished among different conceptions of space, the space of perception (constituted from sensorial data by intentionally motivated psychic functions), that of physical geometry (or idealized perceptual space), the space of the mathematical science of physical nature (in which science, not only raw perception has a word) and the abstract spaces of mathematics (free creations of the mathematical mind), each of them with its peculiar geometrical structure. Perceptual space is proto-Euclidean and the space of physical geometry Euclidean, but mathematical physics, Husserl allowed, may find it convenient to represent physical space with a non-Euclidean structure. Mathematical spaces, on their turn, can be endowed, he thinks, with any geometry mathematicians may find interesting. Many other related questions are addressed here, in particular those concerning the a priori or a posteriori character of the many geometric features of perceptual space (bearing in mind that there are at least two different notions of a priori in Husserl, which we may call the conceptual and the transcendental a priori). I conclude with an overview of Weyl's ideas on the matter, since his philosophical conceptions are often traceable back to his former master, Husserl.

Extended Hierarchical Censored Production Rules (EHCPRs) system: An approach toward generalized knowledge representation

One common problem in all basic techniques of knowledge representation is the handling of the trade-off between precision of inferences and resource constraints, such as time and memory. Michalski and Winston (1986) suggested the Censored Production Rule (CPR) as an underlying representation and computational mechanism to enable logic based systems to exhibit variable precision in which certainty varies while specificity stays constant. As an extension of CPR, the Hierarchical Censored Production Rules (HCPRs) system of knowledge representation, proposed by Bharadwaj & Jain (1992), exhibits both variable certainty as well as variable specificity and offers mechanisms for handling the trade-off between the two. An HCPR has the form: Decision If(preconditions) Unless(censor) Generality(general_information) Specificity(specific_information). As an attempt towards evolving a generalized knowledge representation, an Extended Hierarchical Censored Production Rules (EHCPRs) system is suggested in this paper. With the inclusion of new operators, an Extended Hierarchical Censored Production Rule (EHCPR) takes the general form: Concept If (Preconditions) Unless (Exceptions) Generality (General-Concept) Specificity (Specific Concepts) Has_part (default: structural-parts) Has_property (default:characteristic-properties) Has_instance (instances). How semantic networks and frames are represented in terms of an EHCPRs is shown. Multiple inheritance, inheritance with and without cancellation, recognition with partial match, and a few default logic problems are shown to be tackled efficiently in the proposed system.

Automatic segmentation and classification of human intestinal parasites from microscopy images

Human intestinal parasites constitute a problem in most tropical countries, causing death or physical and mental disorders. Their diagnosis usually relies on the visual analysis of microscopy images, with error rates that may range from moderate to high. The problem has been addressed via computational image analysis, but only for a few species and images free of fecal impurities. In routine, fecal impurities are a real challenge for automatic image analysis. We have circumvented this problem by a method that can segment and classify, from bright field microscopy images with fecal impurities, the 15 most common species of protozoan cysts, helminth eggs, and larvae in Brazil. Our approach exploits ellipse matching and image foresting transform for image segmentation, multiple object descriptors and their optimum combination by genetic programming for object representation, and the optimum-path forest classifier for object recognition. The results indicate that our method is a promising approach toward the fully automation of the enteroparasitosis diagnosis. © 2012 IEEE.

Frontal sinus recognition for human identification

Many methods based on biometrics such as fingerprint, face, iris, and retina have been proposed for person identification. However, for deceased individuals, such biometric measurements are not available. In such cases, parts of the human skeleton can be used for identification, such as dental records, thorax, vertebrae, shoulder, and frontal sinus. It has been established in prior investigations that the radiographic pattern of frontal sinus is highly variable and unique for every individual. This has stimulated the proposition of measurements of the frontal sinus pattern, obtained from x-ray films, for skeletal identification. This paper presents a frontal sinus recognition method for human identification based on Image Foresting Transform and shape context. Experimental results (ERR = 5,82%) have shown the effectiveness of the proposed method.