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.

A Prototype for a Multimodal Biometric Security system based on Face and Audio Signatures

Any automatically measurable, robust and distinctive physical characteristic or personal trait that can be used to identify an individual or verify the claimed identity of an individual, referred to as biometrics, has gained significant interest in the wake of heightened concerns about security and rapid advancements in networking, communication and mobility. Multimodal biometrics is expected to be ultra-secure and reliable, due to the presence of multiple and independent—verification clues. In this study, a multimodal biometric system utilising audio and facial signatures has been implemented and error analysis has been carried out. A total of one thousand face images and 250 sound tracks of 50 users are used for training the proposed system. To account for the attempts of the unregistered signatures data of 25 new users are tested. The short term spectral features were extracted from the sound data and Vector Quantization was done using K-means algorithm. Face images are identified based on Eigen face approach using Principal Component Analysis. The success rate of multimodal system using speech and face is higher when compared to individual unimodal recognition systems

A Trainable Object Detection System: Car Detection in Static Images

This paper describes a general, trainable architecture for object detection that has previously been applied to face and peoplesdetection with a new application to car detection in static images. Our technique is a learning based approach that uses a set of labeled training data from which an implicit model of an object class -- here, cars -- is learned. Instead of pixel representations that may be noisy and therefore not provide a compact representation for learning, our training images are transformed from pixel space to that of Haar wavelets that respond to local, oriented, multiscale intensity differences. These feature vectors are then used to train a support vector machine classifier. The detection of cars in images is an important step in applications such as traffic monitoring, driver assistance systems, and surveillance, among others. We show several examples of car detection on out-of-sample images and show an ROC curve that highlights the performance of our system.

Face and content validity of smoking-related and matched control pictures

Smoking-related pictures and matched controls are useful tools in experimental tasks of attentional bias. Noteworthy the procedures used to produce and validate these pairs of pictures are poorly reported. This study aimed to describe the production and evidence of validity of a set of smoking-related pictures and their matched controls. Two studies were conducted to assess validity. An online internet-based survey was used to assess face validity of 12 pictures related to smoking behavior and 12 matched controls. All pictures were colored and were 95mm length x 130mm width. Participants were asked if the pictures were related or not to the smoking behavior and also rated how much each picture was related to smoking behavior. The second study investigated attentional bias in smokers (n = 47) and non-smokers (n = 50), and examined how they assessed all pictures in terms of pleasantness and the 12 smoking-related pictures in terms of relevance to their own smoking behavior. Craving was assessed before and after the experiment. Results indicate that this set of pictures are valid since smoking-related pictures were considered more related to smoking behavior compared to their matched controls. Moreover, smokers showed greater attentional bias for smoking-related pictures than non-smokers. Craving and relevance of the smoking-related pictures were higher in smokers than in non-smokers. Smokers considered smoking-related pictures them less unpleasant than non-smokers. These findings provide evidence of face and content validity of this set of pictures, which will be available to researchers, contributing to maximize the standardization of future investigations.

Gender differences among undergraduates in the recognition of emotional facial expressions

The perceptive accuracy of university students was compared between men and women, from sciences and humanities courses, to recognize emotional facial expressions. emotional expressions have had increased interest in several areas involved with human interaction, reflecting the importance of perceptive skills in human expression of emotions for the effectiveness of communication. Two tests were taken: one was a quick exposure (0.5 s) of 12 faces with an emotional expression, followed by a neutral face. subjects had to tell if happiness, sadness, anger, fear, disgust or surprise was flashed, and each emotion was shown twice, at random. on the second test 15 faces with the combination of two emotional expressions were shown without a time limit, and the subject had to name one of the emotions of the previous list. in this study, women perceived sad expressions better while men realized more happy faces. there was no significant difference in other emotions detection like anger, fear, surprise, disgust. Students of humanities and sciences areas of both sexes, when compared, had similar capacities to perceive emotional expressions

A atitude dos professores face à inclusão de alunos com deficiência : a influência do nível de ensino

RESUMO: A conjuntura actual veicula a necessidade de reflexão e de mudança acerca da concepção do modelo educativo, que se reformulam em novas realidades e ajustam a incumbência de adaptar. É certo que as necessidades de mudança devem partir de uma reflexão séria, fundamentando-se e difundindo o seu propósito em valores superiores. Estes desafios, que se cruzam na moralização social, tornam a discussão acerca do Paradigma Inclusivo substancial. O carácter quantitativo do estudo, assume o pressuposto de encontrar uma forma de monitorização de dados, decorrentes da aplicação de um inquérito por questionário, que para além da recolha de informações, visava também promover a reflexão dos professores, acerca das suas atitudes. Numa lógica de investigação em mosaico, obteve-se uma amostra total de 741 inquiridos, seleccionados no universo docente de forma aleatória. O tratamento estatístico foi desenvolvido por meio do suplemento EZanalyze, recorrendo-nos do teste paramétrico de análise de variância – ANOVA. Assim, pareceu-nos pertinente, centrar este estudo na figura activa do professor, no processo ensino-aprendizagem em contexto de sala de aula, propondo-nos a procurar eventuais analogias entre as variáveis Nível de Ensino e Grupo Disciplinar em estreita relação com a atitude dos docentes, relativas às vantagens da educação inclusiva, tanto para os alunos ditos normais como para os alunos portadores de deficiência, averiguando tanto a deficiência no seu âmbito geral, como especificando ainda a Deficiência Mental e a Deficiência Motora. Verificou-se que as variáveis Nível de Ensino e o Grupo Disciplinar influenciam directamente a atitude dos professores face aos benefícios para os alunos, que advêm da implementação do Paradigma Inclusivo. Verificou-se ainda que as vantagens que a inclusão proporciona, vão-se esbatendo à medida que o nível de ensino vai avançando. Naturalmente, destacam-se de forma positiva, os Educadores de Infância e os professores do 1º ciclo como os que se aproximam de atitudes mais inclusivas. Por sua vez constatou-se que as atitudes dos docentes do 2º ciclo ao ensino secundário evidenciavam atitudes bastante idênticas. ABSTRACT: The present context conveys the need for reflection and transformation on the educational model, which will reshape into new realities and readapt. It is true that the need for change must start from a serious enquiry, basing himself and his purpose on spreading higher standards. These challenges are intertwined in social moralizing which makes the discussion surrounding the Inclusive Paradigm substantial. The quantitative nature of the study, assumes the purpose of finding a way to monitor data from the application of a questionnaire that in addition to the collection of information, also aimed at promoting teachers reflection about their attitudes. In the logics of mosaic research, we obtained a total sample of 741 respondents, all of them were teachers selected at random. Statistical analysis was developed through EZanalyze, using the parametric test analysis of variance - ANOVA. Thus, it seemed appropriate that this study focused on the teacher's active figure on the teaching-learning process in the classroom, offering us a look for possible analogies between the variables Education Degree and Discipline Group in close relation with the teacher’s attitude concerning the advantages of inclusive education, for normal students as for students with disabilities, examining the deficiency within the general scope, such as specifying mentally and physical disabled. It was concluded that the variables Level of Education and Discipline Group directly influence teacher’s attitude, towards student’s benefits, coming from implementation of the Inclusive Paradigm. It was also concluded that the benefits of inclusion, are blurred as the education level progresses. Standing in a positive way, Early Childhood Educators and First Degree Teachers have more inclusive attitudes. Also, teachers from Second Degree to Secondary Degree has evidenced has being fairly homogeneous related to their attitudes towards the benefits of implementing a truly Inclusive Paradigm.

A atitude dos alunos face à inclusão dos seus pares com deficiência

RESUMO: A escola actual encontra-se perante o desafio de responder com afectividade às necessidades educativas especiais de uma população cada vez mais heterogénea, onde se adopte um modelo de atendimento adequado a cada um. Neste contexto, consideramos os alunos, os professores e os encarregados de educação elementos chave de todo o processo, sobre os quais recaem responsabilidades acrescidas na concretização da filosofia inclusiva. O presente estudo tem como objectivo averiguar a atitude dos alunos face à inclusão dos seus pares com deficiência, determinando o modo como estes percepcionam as atitudes dos professores e dos pais face à inclusão de alunos com NEE de carácter permanente, vantagens e desvantagens da inclusão de alunos com NEE de carácter permanente e a cooperação entre alunos com e sem deficiência, tendo em conta a tipologia da deficiência (motora e mental). No caso do nosso estudo, contámos com a participação de 520 alunos (N= 270 género feminino e N=250 do género masculino), uma amostra distribuída pelo 2ºciclo, 3º ciclo e secundário dos distritos de Setúbal e Lisboa. A recolha de dados concretizou-se pela aplicação do AID – EF, questionário da autoria de Ramos Leitão, 2011.Esta metodologia de recolha e tratamento de informação permitiu-nos concluir que, na opinião dos alunos ditos normais a atitude dos professores face à inclusão de alunos com NEE de carácter permanente (dimensão d1), não varia em função da tipologia da deficiência (deficiência motora e mental). Da mesma forma, não foram encontradas diferenças significativas entre os dois grupos (deficiência motora e mental), na opinião dos alunos ditos normais, no que respeita às vantagens da inclusão dos alunos com NEE de carácter permanente (dimensão d2). Na opinião dos alunos ditos normais os resultados demonstraram que a cooperação entre alunos com e sem deficiência (dimensão d3), varia em função da tipologia da deficiência (deficiência motora e mental), apontando esses resultados para uma maior cooperação entre os alunos ditos normais e os seus pares com deficiência mental. Não foram igualmente encontradas diferenças significativas no que respeita às desvantagens da inclusão dos alunos com NEE de carácter permanente (dimensão 4), quando temos em consideração a tipologia da deficiência (deficiência motora e mental). Da mesma forma, na opinião dos alunos normais ditos normais a atitude dos pais face à inclusão de alunos com NEE de carácter permanente (dimensão d5) não variam em função da tipologia da deficiência (deficiência motora e mental).ABSTRACT: Currently the school is faced with the challenge of responding affectionately to the special educational needs of an increasingly heterogeneous population, where a standard model is adopted for each individual. In this context, we consider the students, teachers and guardians, key elements in the whole process, over which fall increased responsibilities in the implementation of the inclusive philosophy. The present study aims to determine the attitude of students towards the inclusion of peers with disabilities, determining how they perceive the attitudes of teachers and parents towards the inclusion of pupils with permanent special education needs, advantages and disadvantages of including students with permanent special education needs and the cooperation between students with and without disabilities, taking into account the type of disability (mental and motor). In the case of our study, we had the participation of 520 students (N = 270 N = female and 250 male), a sample distributed to the 2nd cycle, 3rd cycle and Secondary schools in the districts of Setúbal and Lisbon. The data collected was enabled by the application of the IDA - EF, questionnaire by Ramos Leitão, 2011. This methodology of collecting and processing information allowed us to conclude that, in the opinion of the so-called normal students the teachers´ attitude towards the inclusion of pupils with permanent special education needs (dimension d1) does not vary according to the type of disability (motor and mental). Likewise, no significant differences were found between the two groups (mental and motor), in the opinion of the so-called normal students, with regard to the benefits of the inclusion of pupils with permanent special education needs (dimension d2). In the opinion of the so-called normal students, the results demonstrated that the cooperation between students with and without disabilities (dimension d3), vary depending on the type of disability (mental and motor), these results pointing to a greater cooperation between the so-called normal students and their peers with mental disabilities. There were also no significant differences with respect to the disadvantages of inclusion of pupils with permanent special education needs (dimension d4), when we take into account the type of disability (mental and motor). Similarly, in the opinion of the so-called normal students, the parents´ attitude towards the inclusion of pupils with permanent special education needs (dimension d5) does not vary according to the type of disability (mental and motor).

Visual search for basic emotional expressions in autism; impaired processing of anger, fear and sadness, but a typical happy face advantage

Facial expression recognition was investigated in 20 males with high functioning autism (HFA) or Asperger syndrome (AS), compared to typically developing individuals matched for chronological age (TD CA group) and verbal and non-verbal ability (TD V/NV group). This was the first study to employ a visual search, “face in the crowd” paradigm with a HFA/AS group, which explored responses to numerous facial expressions using real-face stimuli. Results showed slower response times for processing fear, anger and sad expressions in the HFA/AS group, relative to the TD CA group, but not the TD V/NV group. Reponses to happy, disgust and surprise expressions showed no group differences. Results are discussed with reference to the amygdala theory of autism.

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.

3D face computational photography using PCA spaces

In this paper, we present a 3D face photography system based on a facial expression training dataset, composed of both facial range images (3D geometry) and facial texture (2D photography). The proposed system allows one to obtain a 3D geometry representation of a given face provided as a 2D photography, which undergoes a series of transformations through the texture and geometry spaces estimated. In the training phase of the system, the facial landmarks are obtained by an active shape model (ASM) extracted from the 2D gray-level photography. Principal components analysis (PCA) is then used to represent the face dataset, thus defining an orthonormal basis of texture and another of geometry. In the reconstruction phase, an input is given by a face image to which the ASM is matched. The extracted facial landmarks and the face image are fed to the PCA basis transform, and a 3D version of the 2D input image is built. Experimental tests using a new dataset of 70 facial expressions belonging to ten subjects as training set show rapid reconstructed 3D faces which maintain spatial coherence similar to the human perception, thus corroborating the efficiency and the applicability of the proposed system.

Exame físico : uma face reveladora do cuidado humano

Este é um estudo qualitativo, fenomenológico, com sustentação filosófica à luz de Maurice Merleau-Ponty. Tem por objeto o conhecimento, a compreensão e o significado do procedimento do exame físico como uma face reveladora do cuidado humano. Foi desenvolvido entre enfermeiras que cuidam de crianças hospitalizadas, na Clínica Pediátrica do Hospital Universitário da Fundação Universidade Federal do Rio Grande, RS. O estudo foi norteado por quatro questões: sobre a seqüência das partes do corpo da criança examinadas pela enfermeira; as bases de sustentação teórica e a defesa da prática da execução do exame físico no cotidiano; sobre como é compreendido o procedimento e o significado do exame físico. As enfermeiras possibilitaram compreender o fenômeno como um procedimento que é ensinado e aprendido no curso de graduação em enfermagem; que é aperfeiçoado durante a prática profissional; que exige estudo específico e rigor científico na técnica de execução, interpretação e registro. As bases de sustentação do procedimento estão na literatura e na continuidade do exercício; são defendidas na prática pelas suas finalidades e por se constituir fundamento para o processo de cuidado humano. É compreendido como linguagem e prática humanizada e a sua não execução é interpretada como falha da enfermeira no processo de cuidado. O fenômeno alerta às instituições formadoras no que tange à importância do rigor no ensino do exame físico, às instituições cuidadoras por se referir como fundamento ao processo de cuidado e para as enfermeiras como uma revisão dos conceitos e valores sobre o conhecimento e o exercício contínuo do exame físico.

Faculdade do espírito e riqueza material : face e verso do conceito "vermögen" na filosofia de Hegel

Resumo não disponível

Avaliação da resposta autonômica simpática à exposição da face ao frio de indivíduos normais e de pacientes com diabetes mellitus com e sem microangiopatia

Resumo não disponível.