Recognition of Facial Expressions with Autoencoders and Convolutional-Nets

Les humains communiquent via différents types de canaux: les mots, la voix, les gestes du corps, des émotions, etc. Pour cette raison, un ordinateur doit percevoir ces divers canaux de communication pour pouvoir interagir intelligemment avec les humains, par exemple en faisant usage de microphones et de webcams. Dans cette thèse, nous nous intéressons à déterminer les émotions humaines à partir d’images ou de vidéo de visages afin d’ensuite utiliser ces informations dans différents domaines d’applications. Ce mémoire débute par une brève introduction à l'apprentissage machine en s’attardant aux modèles et algorithmes que nous avons utilisés tels que les perceptrons multicouches, réseaux de neurones à convolution et autoencodeurs. Elle présente ensuite les résultats de l'application de ces modèles sur plusieurs ensembles de données d'expressions et émotions faciales. Nous nous concentrons sur l'étude des différents types d’autoencodeurs (autoencodeur débruitant, autoencodeur contractant, etc) afin de révéler certaines de leurs limitations, comme la possibilité d'obtenir de la coadaptation entre les filtres ou encore d’obtenir une courbe spectrale trop lisse, et étudions de nouvelles idées pour répondre à ces problèmes. Nous proposons également une nouvelle approche pour surmonter une limite des autoencodeurs traditionnellement entrainés de façon purement non-supervisée, c'est-à-dire sans utiliser aucune connaissance de la tâche que nous voulons finalement résoudre (comme la prévision des étiquettes de classe) en développant un nouveau critère d'apprentissage semi-supervisé qui exploite un faible nombre de données étiquetées en combinaison avec une grande quantité de données non-étiquetées afin d'apprendre une représentation adaptée à la tâche de classification, et d'obtenir une meilleure performance de classification. Finalement, nous décrivons le fonctionnement général de notre système de détection d'émotions et proposons de nouvelles idées pouvant mener à de futurs travaux.

The intangible aspects of architectural spaces that influence human well-being

En utilisant des approches qualitative and quantitative cette thèse démontre que les aspects intangibles des espaces architecturaux influencent le bien-être humain. Le but est de faire savoir que les espaces intérieurs ont un impact sur le bien-être et que l’architecture peut être considérée comme une solution pour satisfaire les besoins des usagers. Dans la première étude, l’approche qualitative est explorée en utilisant la narration pour identifier les aspects intangibles des espaces intérieurs qui affectent le bien-être. Une discussion s’articule autour du Modèle de Réponses Expérientielles des Humains (Model of Human Experiential Responses to Space) et de son importance comme outil pour déterrer les caractéristiques environnementales qui influencent le bien-être et qui peut être utile pour les professionnels du design. Les résultats démontrent que 43 catégories sont interprétées comme étant des aspects intangibles et servent de canevas pour trois autres études. Les résultats démontrent que certaines caractéristiques environnementales similaires dans les résidences et les bureaux augmentent le sentiment de satisfaction et de bien-être. Dans la deuxième étude, une approche quantitative est explorée en utilisant les neurosciences et l’architecture afin de mesurer comment les espaces architecturaux affectent le bien-être. Le concept de neuroscience / environnement / comportement est utilisé où huit corrélats neuroscientifiques (Zeisel 2006) sont investigués afin de mesurer les effets du cerveau sur les espaces architecturaux. Les résultats démontrent que l’environnement peut affecter l’humeur, le niveau d’attention et le niveau de stress chez les humains et peut également augmenter leur performance. Les deux études contribuent aux connaissances que les caractéristiques environnementales affectent l’humeur et le niveau de satisfaction de la même façon dans les espaces résidentiels et dans les espaces de bureaux. Un bon environnement qui énergise les employés peut affecter leur performance au travail de façon positive (Vischer 2005).

Indigenous knowledges and power in friction with human rights and development discourses : the case of the Witoto Ethnic Safeguarding Plan in the Colombian Amazon

Cette thèse analyse les négociations interculturelles des Gens du Centre (groupe amazonien multi-ethnique) avec les discours universels de droits humains et de développement mobilisés par l’État colombien. L’analyse se concentre sur le Plan de sauvegarde ethnique Witoto chapitre Leticia (ESP), qui est un des 73 plans formulés et implémentés par l’État colombien pour reconnaître les droits des peuples autochtones en danger par le déplacement forcé causé par les conflits armés internes. J’analyse l’ESP à travers la notion de friction (Tsing, 2005) qui fait référence aux caractéristiques complexes, inégalitaires et changeantes des rencontres contemporaines entre les différences des savoirs locaux et globaux. Mon analyse se base aussi sur des approches foucaldiennes et/ou subalternes de pouvoir comme la recherche anticoloniale et de la décolonisation, les perspectives critiques et contre-hégémoniques des droits humains, le post-développement, et les critiques du féminisme au développement. L’objectif de la thèse est d’analyser les savoirs (concepts de loi, de justice et de développement); les logiques de pensée (pratiques, épistémologies, rôles et espaces pour partager et produire des savoirs); et les relations de pouvoir (formes de leadership, associations, réseaux, et formes d’empowerment et disempowerment) produits et recréés par les Gens du Centre au sein des frictions avec les discours de droits humains et du développement. La thèse introduit comment la région habitée par les Gens du Centre (le Milieu Amazone transfrontalier) a été historiquement connectée aux relations inégalitaires de pouvoir qui influencent les luttes actuelles de ce groupe autochtone pour la reconnaissance de leurs droits à travers l’ESP. L’analyse se base à la fois sur une recherche documentaire et sur deux terrains ethnographiques, réalisés selon une perspective critique et autoréflexive. Ma réflexion méthodologique explore comment la position des chercheurs sur le terrain influence le savoir ethnographique et peut contribuer à la création des relations interculturelles inclusives, flexibles et connectées aux besoins des groupes locaux. La section analytique se concentre sur comment le pouvoir circule simultanément à travers des échelles nationale, régionale et locale dans l’ESP. J’y analyse comment ces formes de pouvoir produisent des sujets individuels et collectifs et s’articulent à des savoirs globaux ou locaux pour donner lieu à de nouvelles formes d’exclusion ou d’émancipation des autochtones déplacés. Les résultats de la recherche suggèrent que les Gens du Centre approchent le discours des droits humains à travers leurs savoirs autochtones sur la « loi de l’origine ». Cette loi établit leur différence culturelle comme étant à la base du processus de reconnaissance de leurs droits comme peuple déplacé. D’ailleurs, les Gens du Centre approprient les discours et les projets de développement à travers la notion d’abondance qui, comprise comme une habileté collective qui connecte la spiritualité, les valeurs culturelles, et les rôles de genre, contribue à assurer l’existence physique et culturelle des groupes autochtones. Ma thèse soutient que, même si ces savoirs et logiques de pensée autochtones sont liés à des inégalités et à formes de pouvoir local, ils peuvent contribuer à des pratiques de droits humains et de développement plurielles, égalitaires et inclusives.

Innovative Human Resource Practices and Selected HR Outcomes in Software Firms in Kerala

In this study the relationship between Innovative HR practices and selected HR outcomes is investigated.The current study represents a unique attempt to study the effects of innovative HR practices,with job satisfaction,organisational commitment and organisational citizenship bahaviour considered as the consequent variables.Results have affirmed the role of intervening variables such as job satisfaction and organisational commitment in establishing the link between IHRP and OCB obliterating any direct relation between IHRP and organisational citizenship behaviour.This finding may enable researchers in the human resource management to develop more robust understandings of the positive effects of innnovative HR practices on HR outcomes.Thus the present study provides the obvious contribution of weaving up yet another linkage between the two complimentary disciplines of Human Resource Management and Organisational Behaviour.The present study also contributes to the understanding of OCB by exploring its antecedents and extending the intervening role of job satisfaction and organisational commitment.The findings indicate that a higher level of introduction/initiation and satisfaction of innovative HR practices produces high job satisfaction and organisational commitment which lead to OCB.The researcher drew upon the perception-attitude-behaviour model to further realise the expected relationship among innovative HR practices,job satisfaction,organisational commitment and organisational citizenship behaviour.Consequently,this study makes a contribution to the broader organisational citizenship behaviour literature by manifesting the extended relationship path from innovative HR practices to organisational citizenship behaviour,and demonstrating that innovative Hr practices at the organisational level has an effect on employee attitudes and behaviours as well.

IRIS BIOMETRIC RECOGNITION SYSTEM EMPLOYING CANNY OPERATOR

Biometrics has become important in security applications. In comparison with many other biometric features, iris recognition has very high recognition accuracy because it depends on iris which is located in a place that still stable throughout human life and the probability to find two identical iris's is close to zero. The identification system consists of several stages including segmentation stage which is the most serious and critical one. The current segmentation methods still have limitation in localizing the iris due to circular shape consideration of the pupil. In this research, Daugman method is done to investigate the segmentation techniques. Eyelid detection is another step that has been included in this study as a part of segmentation stage to localize the iris accurately and remove unwanted area that might be included. The obtained iris region is encoded using haar wavelets to construct the iris code, which contains the most discriminating feature in the iris pattern. Hamming distance is used for comparison of iris templates in the recognition stage. The dataset which is used for the study is UBIRIS database. A comparative study of different edge detector operator is performed. It is observed that canny operator is best suited to extract most of the edges to generate the iris code for comparison. Recognition rate of 89% and rejection rate of 95% is achieved

PERFORMANCE OF DIFFERENT CLASSIFIERS IN SPEECH RECOGNITION

Speech is the most natural means of communication among human beings and speech processing and recognition are intensive areas of research for the last five decades. Since speech recognition is a pattern recognition problem, classification is an important part of any speech recognition system. In this work, a speech recognition system is developed for recognizing speaker independent spoken digits in Malayalam. Voice signals are sampled directly from the microphone. The proposed method is implemented for 1000 speakers uttering 10 digits each. Since the speech signals are affected by background noise, the signals are tuned by removing the noise from it using wavelet denoising method based on Soft Thresholding. Here, the features from the signals are extracted using Discrete Wavelet Transforms (DWT) because they are well suitable for processing non-stationary signals like speech. This is due to their multi- resolutional, multi-scale analysis characteristics. Speech recognition is a multiclass classification problem. So, the feature vector set obtained are classified using three classifiers namely, Artificial Neural Networks (ANN), Support Vector Machines (SVM) and Naive Bayes classifiers which are capable of handling multiclasses. During classification stage, the input feature vector data is trained using information relating to known patterns and then they are tested using the test data set. The performances of all these classifiers are evaluated based on recognition accuracy. All the three methods produced good recognition accuracy. DWT and ANN produced a recognition accuracy of 89%, SVM and DWT combination produced an accuracy of 86.6% and Naive Bayes and DWT combination produced an accuracy of 83.5%. ANN is found to be better among the three methods.

Unconstrained Handwritten Malayalam Character Recognition using Wavelet Transform and Support vector Machine Classifier

This paper presents the application of wavelet processing in the domain of handwritten character recognition. To attain high recognition rate, robust feature extractors and powerful classifiers that are invariant to degree of variability of human writing are needed. The proposed scheme consists of two stages: a feature extraction stage, which is based on Haar wavelet transform and a classification stage that uses support vector machine classifier. Experimental results show that the proposed method is effective

A Comparative study of HMM and SVM in Malayalam Digit Recognition

A primary medium for the human beings to communicate through language is Speech. Automatic Speech Recognition is wide spread today. Recognizing single digits is vital to a number of applications such as voice dialling of telephone numbers, automatic data entry, credit card entry, PIN (personal identification number) entry, entry of access codes for transactions, etc. In this paper we present a comparative study of SVM (Support Vector Machine) and HMM (Hidden Markov Model) to recognize and identify the digits used in Malayalam speech.

The Human in the Loop: User Participation in Self-Adaptive Software

Self-adaptive software provides a profound solution for adapting applications to changing contexts in dynamic and heterogeneous environments. Having emerged from Autonomic Computing, it incorporates fully autonomous decision making based on predefined structural and behavioural models. The most common approach for architectural runtime adaptation is the MAPE-K adaptation loop implementing an external adaptation manager without manual user control. However, it has turned out that adaptation behaviour lacks acceptance if it does not correspond to a user’s expectations – particularly for Ubiquitous Computing scenarios with user interaction. Adaptations can be irritating and distracting if they are not appropriate for a certain situation. In general, uncertainty during development and at run-time causes problems with users being outside the adaptation loop. In a literature study, we analyse publications about self-adaptive software research. The results show a discrepancy between the motivated application domains, the maturity of examples, and the quality of evaluations on the one hand and the provided solutions on the other hand. Only few publications analysed the impact of their work on the user, but many employ user-oriented examples for motivation and demonstration. To incorporate the user within the adaptation loop and to deal with uncertainty, our proposed solutions enable user participation for interactive selfadaptive software while at the same time maintaining the benefits of intelligent autonomous behaviour. We define three dimensions of user participation, namely temporal, behavioural, and structural user participation. This dissertation contributes solutions for user participation in the temporal and behavioural dimension. The temporal dimension addresses the moment of adaptation which is classically determined by the self-adaptive system. We provide mechanisms allowing users to influence or to define the moment of adaptation. With our solution, users can have full control over the moment of adaptation or the self-adaptive software considers the user’s situation more appropriately. The behavioural dimension addresses the actual adaptation logic and the resulting run-time behaviour. Application behaviour is established during development and does not necessarily match the run-time expectations. Our contributions are three distinct solutions which allow users to make changes to the application’s runtime behaviour: dynamic utility functions, fuzzy-based reasoning, and learning-based reasoning. The foundation of our work is a notification and feedback solution that improves intelligibility and controllability of self-adaptive applications by implementing a bi-directional communication between self-adaptive software and the user. The different mechanisms from the temporal and behavioural participation dimension require the notification and feedback solution to inform users on adaptation actions and to provide a mechanism to influence adaptations. Case studies show the feasibility of the developed solutions. Moreover, an extensive user study with 62 participants was conducted to evaluate the impact of notifications before and after adaptations. Although the study revealed that there is no preference for a particular notification design, participants clearly appreciated intelligibility and controllability over autonomous adaptations.

Object Recognition with Pictorial Structures

This thesis presents a statistical framework for object recognition. The framework is motivated by the pictorial structure models introduced by Fischler and Elschlager nearly 30 years ago. The basic idea is to model an object by a collection of parts arranged in a deformable configuration. The appearance of each part is modeled separately, and the deformable configuration is represented by spring-like connections between pairs of parts. These models allow for qualitative descriptions of visual appearance, and are suitable for generic recognition problems. The problem of detecting an object in an image and the problem of learning an object model using training examples are naturally formulated under a statistical approach. We present efficient algorithms to solve these problems in our framework. We demonstrate our techniques by training models to represent faces and human bodies. The models are then used to locate the corresponding objects in novel images.

Surface Reflectance Recognition and Real-World Illumination Statistics

Humans distinguish materials such as metal, plastic, and paper effortlessly at a glance. Traditional computer vision systems cannot solve this problem at all. Recognizing surface reflectance properties from a single photograph is difficult because the observed image depends heavily on the amount of light incident from every direction. A mirrored sphere, for example, produces a different image in every environment. To make matters worse, two surfaces with different reflectance properties could produce identical images. The mirrored sphere simply reflects its surroundings, so in the right artificial setting, it could mimic the appearance of a matte ping-pong ball. Yet, humans possess an intuitive sense of what materials typically "look like" in the real world. This thesis develops computational algorithms with a similar ability to recognize reflectance properties from photographs under unknown, real-world illumination conditions. Real-world illumination is complex, with light typically incident on a surface from every direction. We find, however, that real-world illumination patterns are not arbitrary. They exhibit highly predictable spatial structure, which we describe largely in the wavelet domain. Although they differ in several respects from the typical photographs, illumination patterns share much of the regularity described in the natural image statistics literature. These properties of real-world illumination lead to predictable image statistics for a surface with given reflectance properties. We construct a system that classifies a surface according to its reflectance from a single photograph under unknown illuminination. Our algorithm learns relationships between surface reflectance and certain statistics computed from the observed image. Like the human visual system, we solve the otherwise underconstrained inverse problem of reflectance estimation by taking advantage of the statistical regularity of illumination. For surfaces with homogeneous reflectance properties and known geometry, our system rivals human performance.

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.

View-Based Strategies for 3D Object Recognition

A persistent issue of debate in the area of 3D object recognition concerns the nature of the experientially acquired object models in the primate visual system. One prominent proposal in this regard has expounded the use of object centered models, such as representations of the objects' 3D structures in a coordinate frame independent of the viewing parameters [Marr and Nishihara, 1978]. In contrast to this is another proposal which suggests that the viewing parameters encountered during the learning phase might be inextricably linked to subsequent performance on a recognition task [Tarr and Pinker, 1989; Poggio and Edelman, 1990]. The 'object model', according to this idea, is simply a collection of the sample views encountered during training. Given that object centered recognition strategies have the attractive feature of leading to viewpoint independence, they have garnered much of the research effort in the field of computational vision. Furthermore, since human recognition performance seems remarkably robust in the face of imaging variations [Ellis et al., 1989], it has often been implicitly assumed that the visual system employs an object centered strategy. In the present study we examine this assumption more closely. Our experimental results with a class of novel 3D structures strongly suggest the use of a view-based strategy by the human visual system even when it has the opportunity of constructing and using object-centered models. In fact, for our chosen class of objects, the results seem to support a stronger claim: 3D object recognition is 2D view-based.

3D Object Recognition: Symmetry and Virtual Views

Many 3D objects in the world around us are strongly constrained. For instance, not only cultural artifacts but also many natural objects are bilaterally symmetric. Thoretical arguments suggest and psychophysical experiments confirm that humans may be better in the recognition of symmetric objects. The hypothesis of symmetry-induced virtual views together with a network model that successfully accounts for human recognition of generic 3D objects leads to predictions that we have verified with psychophysical experiments.

Model-based objects recognition in man-made environments

We describe a model-based objects recognition system which is part of an image interpretation system intended to assist autonomous vehicles navigation. The system is intended to operate in man-made environments. Behavior-based navigation of autonomous vehicles involves the recognition of navigable areas and the potential obstacles. The recognition system integrates color, shape and texture information together with the location of the vanishing point. The recognition process starts from some prior scene knowledge, that is, a generic model of the expected scene and the potential objects. The recognition system constitutes an approach where different low-level vision techniques extract a multitude of image descriptors which are then analyzed using a rule-based reasoning system to interpret the image content. This system has been implemented using CEES, the C++ embedded expert system shell developed in the Systems Engineering and Automatic Control Laboratory (University of Girona) as a specific rule-based problem solving tool. It has been especially conceived for supporting cooperative expert systems, and uses the object oriented programming paradigm