誇張肖像畫是以誇張與諷刺的手法來表現模特兒的特徵。現今這類畫作比起以寫實手法繪製的肖像畫，更受到大眾的喜愛；但是人們若想要自己模仿繪製出這類的肖像畫，除了要有繪畫天賦之外，也必須經過長時間的繪畫訓練以及對人臉的觀察，才能抓出模特兒的臉部特徵，並用生動的手法誇飾出來。 因此，如果電腦能做到代替誇張肖像畫家的工作，自動模仿繪製出誇張化的卡通肖像畫，將能替人們節省大量的時間及經費。本研究主要在設計一套能誇張肖像畫的系統，以根據使用者輸入的臉部影像，自動擷取臉部的特徵（包括特徵點的相對位置、絕對位置、形狀及大小等），並藉由分析這些特徵與常人相異之處，以一致的方式自動將特徵誇張化。這個系統並能以藝術家的作品為輸入，將使用者的臉部影像轉換成具有畫家卡通風格的誇張肖像畫。除了人臉的效果外，我們也進行了頭髮分離與模擬的研究，以強化畫像風格模擬的完整性。最後，我們以實做出了系統對數個具特徵的人臉影像進行實驗，以驗證其可行性及有效性。 / Caricaturists are good at drawing sketches which express the exaggerated likeness of a person with a bit flavor of humor or sarcasm. People are willing to pay for this kind of work because it requires a lot of practice to achieve excellence. Acute observation is needed to extract the distinct features from the subject, and decent painting skill is essential to depict these features vividly. It will save much time and effort if computers can be trained used to draw caricatures. In this thesis, we developed a system which can extract and analyze facial features from simple an input facial images. The main purpose of this system is to generate the user-own caricature model by exaggerating his/her unique facial features. Different types of features, including relative locations and sizes, absolute locations and sizes, and each the shape of features are all taken in accountwill be considered. Unlike the complex process reported in the literature, we develop a transformative process that can handle different types of features in a more uniform fashion. Using an artist’s finished work as the source image; the proposed system is capable of producing cartoon-like colorful caricatures of a similar style effectively and efficiently. Besides the caricature painting of the face part, we also present some approaches for hair segmentation and hair style painting to increase make the system more the completeness of our system. Finally, we prove the feasibility and effectiveness of our system by showing several experimental results.

Em nossa vida diária, são utilizadas identidades digitais (IDDs) para acessar contas de e-mail, bancos e lojas virtuais, locais restritos, computadores compartilhados, e outros. Garantir que apenas usuários autorizados tenham o acesso permitido é um aspecto fundamental no desenvolvimento destas aplicações. Atualmente, os métodos de controle de acesso simples como senhas ou números de identificação pessoal não devem ser considerados suficientemente seguros, já que um impostor pode conseguir estas informações sem o conhecimento do usuário. Ainda, no caso de utilização de dispositivos físicos como cartões de identificação, estes podem ser roubados ou forjados. Para tornar estes sistemas mais confiáveis, técnicas de autenticação de identidades utilizando múltiplas verificações são propostas. A utilização de características biométricas surge como a alternativa mais confiável para tratar este problema, pois são, teoricamente, únicas para cada pessoa. Contudo, algumas características biométricas como a aparência facial podem variar com o tempo, implicando em um grande desafio para os sistemas de reconhecimento facial. Neste trabalho é combinado o acesso tradicional por senha com a análise da face para realizar a autenticação. Um método de aprendizagem supervisionada é apresentado e sua adaptação é baseada na melhora contínua dos modelos faciais, que são representados por misturas de gaussianas. Os resultados experimentais, obtidos sobre um conjunto de teste reduzido, são encorajadores, com 98% de identificação correta dos usuários e custo computacional relativamente baixo. Ainda, a comparação com um método apresentado na literatura indicou vantagens do método proposto quando usado como um pré-selecionador de faces. / In our daily life, we use digital identities (DIDs) to access e-mails, e-banks, e-shops, physical environments, shared computers, and so on. Guarantee that only authorized users are granted access is an important aspect in the development of such applications. Nowadays, the simple access control methods like passwords or personal identification numbers can not be considered secure enough, because an impostor can obtain and use these information without user knowledge. Also, physical devices like ID cards can be stolen. To make these systems more reliable, multimodal DID authentication techniques combining different verification steps are proposed. Biometric features appears as one of the most reliable alternatives to deal with this problem because, theoretically, they are unique for each person. Nevertheless, some biometric features like face appearances may change in time, posing a serious challenge for a face recognition system. In this thesis work, we use the traditional password access combined with human face analysis to perform the authentication task. An intuitive supervised appearance learning method is presented, and its adaptation is based on continuously improving face models represented using the Gaussian mixture modeling approach. The experimental results over a reduced test set show encouraging results, with 98% of the users correctly identified, with a relatively small computational effort. Still, the comparison with a method presented in the literature indicated advantages of the proposed method when used as a pre-selector of faces.

Em nossa vida diária, são utilizadas identidades digitais (IDDs) para acessar contas de e-mail, bancos e lojas virtuais, locais restritos, computadores compartilhados, e outros. Garantir que apenas usuários autorizados tenham o acesso permitido é um aspecto fundamental no desenvolvimento destas aplicações. Atualmente, os métodos de controle de acesso simples como senhas ou números de identificação pessoal não devem ser considerados suficientemente seguros, já que um impostor pode conseguir estas informações sem o conhecimento do usuário. Ainda, no caso de utilização de dispositivos físicos como cartões de identificação, estes podem ser roubados ou forjados. Para tornar estes sistemas mais confiáveis, técnicas de autenticação de identidades utilizando múltiplas verificações são propostas. A utilização de características biométricas surge como a alternativa mais confiável para tratar este problema, pois são, teoricamente, únicas para cada pessoa. Contudo, algumas características biométricas como a aparência facial podem variar com o tempo, implicando em um grande desafio para os sistemas de reconhecimento facial. Neste trabalho é combinado o acesso tradicional por senha com a análise da face para realizar a autenticação. Um método de aprendizagem supervisionada é apresentado e sua adaptação é baseada na melhora contínua dos modelos faciais, que são representados por misturas de gaussianas. Os resultados experimentais, obtidos sobre um conjunto de teste reduzido, são encorajadores, com 98% de identificação correta dos usuários e custo computacional relativamente baixo. Ainda, a comparação com um método apresentado na literatura indicou vantagens do método proposto quando usado como um pré-selecionador de faces. / In our daily life, we use digital identities (DIDs) to access e-mails, e-banks, e-shops, physical environments, shared computers, and so on. Guarantee that only authorized users are granted access is an important aspect in the development of such applications. Nowadays, the simple access control methods like passwords or personal identification numbers can not be considered secure enough, because an impostor can obtain and use these information without user knowledge. Also, physical devices like ID cards can be stolen. To make these systems more reliable, multimodal DID authentication techniques combining different verification steps are proposed. Biometric features appears as one of the most reliable alternatives to deal with this problem because, theoretically, they are unique for each person. Nevertheless, some biometric features like face appearances may change in time, posing a serious challenge for a face recognition system. In this thesis work, we use the traditional password access combined with human face analysis to perform the authentication task. An intuitive supervised appearance learning method is presented, and its adaptation is based on continuously improving face models represented using the Gaussian mixture modeling approach. The experimental results over a reduced test set show encouraging results, with 98% of the users correctly identified, with a relatively small computational effort. Still, the comparison with a method presented in the literature indicated advantages of the proposed method when used as a pre-selector of faces.

Em nossa vida diária, são utilizadas identidades digitais (IDDs) para acessar contas de e-mail, bancos e lojas virtuais, locais restritos, computadores compartilhados, e outros. Garantir que apenas usuários autorizados tenham o acesso permitido é um aspecto fundamental no desenvolvimento destas aplicações. Atualmente, os métodos de controle de acesso simples como senhas ou números de identificação pessoal não devem ser considerados suficientemente seguros, já que um impostor pode conseguir estas informações sem o conhecimento do usuário. Ainda, no caso de utilização de dispositivos físicos como cartões de identificação, estes podem ser roubados ou forjados. Para tornar estes sistemas mais confiáveis, técnicas de autenticação de identidades utilizando múltiplas verificações são propostas. A utilização de características biométricas surge como a alternativa mais confiável para tratar este problema, pois são, teoricamente, únicas para cada pessoa. Contudo, algumas características biométricas como a aparência facial podem variar com o tempo, implicando em um grande desafio para os sistemas de reconhecimento facial. Neste trabalho é combinado o acesso tradicional por senha com a análise da face para realizar a autenticação. Um método de aprendizagem supervisionada é apresentado e sua adaptação é baseada na melhora contínua dos modelos faciais, que são representados por misturas de gaussianas. Os resultados experimentais, obtidos sobre um conjunto de teste reduzido, são encorajadores, com 98% de identificação correta dos usuários e custo computacional relativamente baixo. Ainda, a comparação com um método apresentado na literatura indicou vantagens do método proposto quando usado como um pré-selecionador de faces. / In our daily life, we use digital identities (DIDs) to access e-mails, e-banks, e-shops, physical environments, shared computers, and so on. Guarantee that only authorized users are granted access is an important aspect in the development of such applications. Nowadays, the simple access control methods like passwords or personal identification numbers can not be considered secure enough, because an impostor can obtain and use these information without user knowledge. Also, physical devices like ID cards can be stolen. To make these systems more reliable, multimodal DID authentication techniques combining different verification steps are proposed. Biometric features appears as one of the most reliable alternatives to deal with this problem because, theoretically, they are unique for each person. Nevertheless, some biometric features like face appearances may change in time, posing a serious challenge for a face recognition system. In this thesis work, we use the traditional password access combined with human face analysis to perform the authentication task. An intuitive supervised appearance learning method is presented, and its adaptation is based on continuously improving face models represented using the Gaussian mixture modeling approach. The experimental results over a reduced test set show encouraging results, with 98% of the users correctly identified, with a relatively small computational effort. Still, the comparison with a method presented in the literature indicated advantages of the proposed method when used as a pre-selector of faces.

Emotions are an essential part of development. There is evidence that young children understand and express emotions through facial expressions. Correct identification and recognition of facial expressions is important to facilitate communication and social interaction. Emotions are represented in a wide variety of symbol sets and systems in Alternative and Augmentative Communication (AAC) to enable a person with little or no functional speech to express emotion. These symbols consist of a facial expression with facial features to distinguish between emotions. In spite of the importance of expressing and understanding emotions to facilitate communication, there is limited research on young children’s ability to recognize emotions represented by graphic symbols. The purpose of this study was to investigate the ability of typically developing fouryearold children to recognize basic emotions as represented by graphic symbols. In order to determine their ability to recognize emotions on graphic symbols, their ability to understand emotions had to be determined. Participants were then required to recognize four basic emotions (happy, sad, afraid, angry) represented by various graphic symbols, taken from PCS (Johnson, 1981), PICSYMS (Carlson, 1985) and Makaton (Grove&Walker, 1990). The purpose was to determine which graphic symbol the children recognized as representation of an emotion. Results showed that the emotion of happy was easier to recognize, which might be because it was the only emotion in the pleasure dimension of emotions. Sad, afraid and angry were more difficult to recognize which might be because they fall in the displeasure dimension. It is also evident from the findings that the facial features in the graphic symbol play an important part in conveying a specific emotion. The results that were obtained are discussed in relation to previous findings. Finally, recommendations for future use are made. / Dissertation (MA (Augumentative and Alternative Communication))--University of Pretoria, 2008. / Centre for Augmentative and Alternative Communication (CAAC) / MA / unrestricted

This MSc Thesis deals with face detection in image. In this approach, facial features (eyes, nose, mouth corners) are detected first and then joined to the whole face. For the facial features detection, classifiers trained with AdaBoost algorithm are used. Haar wavelets are used as features for classification.

The fitting room is an important part of a clothing store, it's often where the customer decides if they want to buy the garment or not. Therefore it is important that the customer can feel safe and comfortable when they are trying the clothing. A typical fitting room in Sweden today has only one bright spotlight that emits light either towards the face or from the ceiling above. This study explores possible lighting solutions that take into account the customer's experience in the fitting room. The study aim to increase understanding of the importance of a good light in fitting rooms, so that customers gets a nice experience and that clothes, body shape and facial features are shown in a natural way. The issue therefore included how lighting can affect the customer's perception of the clothing and how the perception of body shape, facial features and the clothes change in different lighting solutions. To answer these questions, observations were made in various clothing stores, followed by an experimental study divided into two parts. The first part was a practical part where trying different lighting directions were tested on a mannequin, which resulted in three selected lighting solutions. The second part was a full-scale study. 15 people evaluated a fitting room with three different lighting solutions. The result demonstrates the importance of natural shadows and contrasts on the face and body and that it is important to consider how light falls and avoid glare. This is done by well-placed or shielded fixtures and by using several different lighting directions. The lighting in fitting rooms should be adapted to the type of clothes and customer group. / Provrummet är en viktig del i en klädbutik, det är ofta där kunden beslutar om plagget ska köpas eller inte. Det är därför viktigt att kunden kan känna sig trygg och bekväm vid klädprovningen. Ett typiskt provrum i Sverige idag har endast en ljuspunkt som belyser kunden antingen rakt framifrån eller ovanifrån. I denna studie undersöks tänkbara belysningslösningar som tar hänsyn till kundens upplevelse i provrummet. Studiens syfte var att öka förståelsen för hur viktigt det är med en god belysning i provrum, för att kunden ska få en bra upplevelse och att kläderna, kroppens form och anletsdrag ska framhävas på ett naturligt sätt. Frågeställningen innefattade därför hur belysningen kan påverka kundens upplevelse av klädprovningen och hur upplevelsen av kroppens form, anletsdrag och kläderna förändras i olika belysningslösningar. För att besvara dessa frågor gjordes observationer i olika klädbutiker, därefter genomfördes en experimentell studie som delades in i två delar. Första delen var en praktiskt prövande del där olika ljusriktningar testades på en skyltdocka. Denna resulterade i tre belysningslösningar att gå vidare med. Andra delen var en fullskalestudie där ett provrum byggdes upp med de tre olika belysningslösningar som sedan 15 stycken personer fick studera med hjälp av ett frågeformulär. Resultatet visar på vikten av att belysningen skapar naturliga skuggor och kontraster på kropp och ansikte, och att det är viktigt att tänka på hur ljuset faller, samt att belysningen inte är bländande. Detta görs genom välplacerade eller avskärmade armaturer och med flera olika ljusriktningar. Studien visar att belysningen i provrum bör anpassas efter typ av kläder och kundgrupp.

La trisomie 21 (t21) est l'anomalie génétique la plus fréquente à l'origine d'une déficience intellectuelle. Bien que la recherche concernant le stéréotype social de la t21 soit limitée, les personnes porteuses de t21, et particulièrement les enfants, semblent être associées à des traits de personnalité tels que « affectueux » et « heureux », les caractéristiques positives l'emportant sur les négatives comme « retardé ». Cependant, ce stéréotype positif coexiste avec des attitudes ambivalentes notamment à propos de l'intégration scolaire de ces enfants. L'objectif principal de cette thèse est d'étudier ce stéréotype au niveau implicite ainsi que l'impact des caractéristiques faciales sur le stéréotype au niveau explicite et implicite. Nos résultats confirment d'une part, un stéréotype social positif explicite dans des échantillons d'étudiants, d'adultes non étudiant et de professionnels du handicap intellectuel. Les visages d'enfants présentant plus de traits faciaux associés à la t21 sont associés à un stéréotype moins positif que ceux en présentant moins. D'autre part, nous mettons en évidence un stéréotype négatif au niveau implicite, même chez les professionnels du handicap. Nous étudions l'influence des variables individuelles sexe, familiarité avec la t21 et théories implicites de l'intelligence sur le stéréotype explicite et implicite. Puis, nous montrons une relation négative entre la typicalité des visages et le jugement sur l'intelligence alors que nous n'observons pas de relation significative entre la typicalité des visages et le niveau cognitif. Nous discutons l'implication de ces résultats sur l'étude du stéréotype et sur les personnes stigmatisées. / Trisomy 21 (t21) or Down syndrome is the most frequent genetic disorder associated with intellectual disability. Although research on the social stereotype toward t21 is very limited, it seems that persons with t21 are typically viewed as “affectionate” and “happy”; with positive personality traits prevailing over the negative ones (e.g., “mentally retarded”). However, this positive stereotype coexists with ambivalent attitudes. The main objective of this study was to investigate the stereotype at the implicit level and the impact of t21 facial features on the stereotype of t21 at the both explicit and implicit levels. Our results confirm, on one hand, a positive social stereotype explicit in samples of young adult students, non-student adults and professional caregivers working with intellectually disabled persons. The positive bias typically found in explicit judgments of children with t21 is smaller for those whose facial features are highly characteristic of this disorder, compared to their counterparts with less distinctive features and to typically developing children. On the other hand, we also show that this bias can coexist with negative evaluations at the implicit level, even among professional caregivers but to a lesser extent. We study the influence of individual variables sex, familiarity with the t21 and implicit theories of intelligence on explicit and implicit stereotypes. Finally, we show a negative relationship between t21 typicality of faces and the judgment of the intelligence as we do not observe a significant relationship between typicality and the cognitive level. We discuss the implications of these results.

Understanding of the shape and size of different features of human body from the scanned data is necessary for automated design and evaluation of product ergonomics. The traditional method of finding required body dimensions by manual measurements (Anthropometry) has many sociological, logistical and technical drawbacks such as prolonged time, skilled researcher for consistency and accuracy of measurements, undesirable physical contact between the subject and the researcher, required presence of people from different demographic categories or travel of researcher with equipments. If these di- mensions are extracted from the stored digital human models, above drawbacks can be eliminated. With the emergence of laser based 3d scanners, it is now possible generate a large database of surface models of humans from different demographic backgrounds but the automatic processing of 3d meshes is under development. Though some commercial packages are available for extraction of a limited number of dimensions from full body scans, mostly belonging to topologically separable body parts like hands and legs, the dimensions associated with head and face are particularly not available in public domain. The processing of surface models of head and face from the automatic measurement point of view is also not discussed in literature though this type of data has many practical applications like ergonomic design of close-fitting products like respiratory masks,ophthalmic frames (spectacles), helmets and similar head-mounted devices; Creation of a facial feature database for face modeling coding and reconstruction and for use in forensic sciences; Automated anthropological surveys and Medical growth analysis and aesthetic surgery planning. Hence, in this thesis, a computational framework is developed for automatic detection, recognition and measurement of important facial features namely eyes, eyebrows, nose, mouth and moustache (if applicable) from scanned head and shoulder polyhedral models. After preprocessing the scanned mesh manually to fill holes and remove singular vertices, discrete differential geometric operators were implemented to compute surface normals and curvatures. Mean curvature magnitude was used as the primary metric to segment the mesh using morphological watershed algorithms which treat the mesh as a height map and separate the regions according to the water catchment basins. After visualization it was hypothesized that the important facial features consist of relatively high curvature regions and based on this hypothesis a much faster approach was then employed based on mathematical morphology to group the high curvature vertices into regions based on adjacency. The important feature regions isolated this way were then identified and labeled to be belonging to different facial features by a decision tree based on their relative spatial disposition. Adaptive selection of parameters was incorporated later to ensure robustness of this algorithm. Critical points of these identified features are recognized as the standard landmarks associated with those primary facial features. A number of clinically identified landmarks lie on the facial mid-line. An efficient algorithm is proposed for detection and processing of the mid-line using a point sampling technique which is fast and has immunity to noise in the data. An algorithm to find shortest path between two vertices while traveling along the edges is implemented to measure on-surface distances and to isolate the nose. Complete program comprising of curvature and surface normal computations, seg- mentation and identification of 6 important features, facial mid-line processing, detection of total 17 landmarks and shortest path computations to separate nose takes about 2 minutes to work including visualization on a full resolution mesh of typically 2,15,521 Vertices and 4,30,560 Faces. The algorithm was tested successfully on more than 40 faces with minor exceptions. The results match human perception. The computed measurements were also compared with the physical measurements for a few subjects, the measurements were found to be in good agreement and satisfactory for its usage in product ergonomics and clinical applications.

Los seres humanos han desarrollado especialmente su capacidad perceptiva para procesar caras y extraer información de las características faciales. Usando nuestra capacidad conductual para percibir rostros, hacemos atribuciones tales como personalidad, inteligencia o confiabilidad basadas en la apariencia facial que a menudo tienen un fuerte impacto en el comportamiento social en diferentes dominios. Por lo tanto, las caras desempeñan un papel fundamental en nuestras relaciones con otras personas y en nuestras decisiones cotidianas. Con la popularización de Internet, las personas participan en muchos tipos de interacciones virtuales, desde experiencias sociales, como juegos, citas o comunidades, hasta actividades profesionales, como e-commerce, e-learning, e-therapy o e-health. Estas interacciones virtuales manifiestan la necesidad de caras que representen a las personas reales que interactúan en el mundo digital: así surgió el concepto de avatar. Los avatares se utilizan para representar a los usuarios en diferentes escenarios y ámbitos, desde la vida personal hasta situaciones profesionales. En todos estos casos, la aparición del avatar puede tener un efecto no solo en la opinión y percepción de otra persona, sino en la autopercepción, que influye en la actitud y el comportamiento del sujeto. De hecho, los avatares a menudo se emplean para obtener impresiones o emociones a través de expresiones no verbales, y pueden mejorar las interacciones en línea o incluso son útiles para fines educativos o terapéuticos. Por lo tanto, la posibilidad de generar avatares de aspecto realista que provoquen un determinado conjunto de impresiones sociales supone una herramienta muy interesante y novedosa, útil en un amplio abanico de campos. Esta tesis propone un método novedoso para generar caras de aspecto realistas con un perfil social asociado que comprende 15 impresiones diferentes. Para este propósito, se completaron varios objetivos parciales. En primer lugar, las características faciales se extrajeron de una base de datos de caras reales y se agruparon por aspecto de una manera automática y objetiva empleando técnicas de reducción de dimensionalidad y agrupamiento. Esto produjo una taxonomía que permite codificar de manera sistemática y objetiva las caras de acuerdo con los grupos obtenidos previamente. Además, el uso del método propuesto no se limita a las características faciales, y se podría extender su uso para agrupar automáticamente cualquier otro tipo de imágenes por apariencia. En segundo lugar, se encontraron las relaciones existentes entre las diferentes características faciales y las impresiones sociales. Esto ayuda a saber en qué medida una determinada característica facial influye en la percepción de una determinada impresión social, lo que permite centrarse en la característica o características más importantes al diseñar rostros con una percepción social deseada. En tercer lugar, se implementó un método de edición de imágenes para generar una cara totalmente nueva y realista a partir de una definición de rostro utilizando la taxonomía de rasgos faciales antes mencionada. Finalmente, se desarrolló un sistema para generar caras realistas con un perfil de rasgo social asociado, lo cual cumple el objetivo principal de la presente tesis. La principal novedad de este trabajo reside en la capacidad de trabajar con varias dimensiones de rasgos a la vez en caras realistas. Por lo tanto, en contraste con los trabajos anteriores que usan imágenes con ruido, o caras de dibujos animados o sintéticas, el sistema desarrollado en esta tesis permite generar caras de aspecto realista eligiendo los niveles deseados de quince impresiones: Miedo, Enfado, Atractivo, Cara de niño, Disgustado, Dominante, Femenino, Feliz, Masculino, Prototípico, Triste, Sorprendido, Amenazante, Confiable e Inusual. Los prometedores resultados obtenidos permitirán investigar más a fondo cómo modelar l / Humans have specially developed their perceptual capacity to process faces and to extract information from facial features. Using our behavioral capacity to perceive faces, we make attributions such as personality, intelligence or trustworthiness based on facial appearance that often have a strong impact on social behavior in different domains. Therefore, faces play a central role in our relationships with other people and in our everyday decisions. With the popularization of the Internet, people participate in many kinds of virtual interactions, from social experiences, such as games, dating or communities, to professional activities, such as e-commerce, e-learning, e-therapy or e-health. These virtual interactions manifest the need for faces that represent the actual people interacting in the digital world: thus the concept of avatar emerged. Avatars are used to represent users in different scenarios and scopes, from personal life to professional situations. In all these cases, the appearance of the avatar may have an effect not only on other person's opinion and perception but on self-perception, influencing the subject's own attitude and behavior. In fact, avatars are often employed to elicit impressions or emotions through non-verbal expressions, and are able to improve online interactions or even useful for education purposes or therapy. Then, being able to generate realistic looking avatars which elicit a certain set of desired social impressions poses a very interesting and novel tool, useful in a wide range of fields. This thesis proposes a novel method for generating realistic looking faces with an associated social profile comprising 15 different impressions. For this purpose, several partial objectives were accomplished. First, facial features were extracted from a database of real faces and grouped by appearance in an automatic and objective manner employing dimensionality reduction and clustering techniques. This yielded a taxonomy which allows to systematically and objectively codify faces according to the previously obtained clusters. Furthermore, the use of the proposed method is not restricted to facial features, and it should be possible to extend its use to automatically group any other kind of images by appearance. Second, the existing relationships among the different facial features and the social impressions were found. This helps to know how much a certain facial feature influences the perception of a given social impression, allowing to focus on the most important feature or features when designing faces with a sought social perception. Third, an image editing method was implemented to generate a completely new, realistic face from just a face definition using the aforementioned facial feature taxonomy. Finally, a system to generate realistic faces with an associated social trait profile was developed, which fulfills the main objective of the present thesis. The main novelty of this work resides in the ability to work with several trait dimensions at a time on realistic faces. Thus, in contrast with the previous works that use noisy images, or cartoon-like or synthetic faces, the system developed in this thesis allows to generate realistic looking faces choosing the desired levels of fifteen impressions, namely Afraid, Angry, Attractive, Babyface, Disgusted, Dominant, Feminine, Happy, Masculine, Prototypical, Sad, Surprised, Threatening, Trustworthy and Unusual. The promising results obtained in this thesis will allow to further investigate how to model social perception in faces using a completely new approach. / Els sers humans han desenvolupat especialment la seua capacitat perceptiva per a processar cares i extraure informació de les característiques facials. Usant la nostra capacitat conductual per a percebre rostres, fem atribucions com ara personalitat, intel·ligència o confiabilitat basades en l'aparença facial que sovint tenen un fort impacte en el comportament social en diferents dominis. Per tant, les cares exercixen un paper fonamental en les nostres relacions amb altres persones i en les nostres decisions quotidianes. Amb la popularització d'Internet, les persones participen en molts tipus d'inter- accions virtuals, des d'experiències socials, com a jocs, cites o comunitats, fins a activitats professionals, com e-commerce, e-learning, e-therapy o e-health. Estes interaccions virtuals manifesten la necessitat de cares que representen a les persones reals que interactuen en el món digital: així va sorgir el concepte d'avatar. Els avatars s'utilitzen per a representar als usuaris en diferents escenaris i àmbits, des de la vida personal fins a situacions professionals. En tots estos casos, l'aparició de l'avatar pot tindre un efecte no sols en l'opinió i percepció d'una altra persona, sinó en l'autopercepció, que influïx en l'actitud i el comportament del subjecte. De fet, els avatars sovint s'empren per a obtindre impressions o emocions a través d'expressions no verbals, i poden millorar les interaccions en línia o inclús són útils per a fins educatius o terapèutics. Per tant, la possibilitat de generar avatars d'aspecte realista que provoquen un determinat conjunt d'impressions socials planteja una ferramenta molt interessant i nova, útil en un ampla varietat de camps. Esta tesi proposa un mètode nou per a generar cares d'aspecte realistes amb un perfil social associat que comprén 15 impressions diferents. Per a este propòsit, es van completar diversos objectius parcials. En primer lloc, les característiques facials es van extraure d'una base de dades de cares reals i es van agrupar per aspecte d'una manera automàtica i objectiva emprant tècniques de reducció de dimensionalidad i agrupament. Açò va produir una taxonomia que permet codificar de manera sistemàtica i objectiva les cares d'acord amb els grups obtinguts prèviament. A més, l'ús del mètode proposat no es limita a les característiques facials, i es podria estendre el seu ús per a agrupar automàticament qualsevol altre tipus d'imatges per aparença. En segon lloc, es van trobar les relacions existents entre les diferents característiques facials i les impressions socials. Açò ajuda a saber en quina mesura una determinada característica facial influïx en la percepció d'una determinada impressió social, la qual cosa permet centrar-se en la característica o característiques més importants al dissenyar rostres amb una percepció social desitjada. En tercer lloc, es va implementar un mètode d'edició d'imatges per a generar una cara totalment nova i realista a partir d'una definició de rostre utilitzant la taxonomia de trets facials abans mencionada. Finalment, es va desenrotllar un sistema per a generar cares realistes amb un perfil de tret social associat, la qual cosa complix l'objectiu principal de la present tesi. La principal novetat d'este treball residix en la capacitat de treballar amb diverses dimensions de trets al mateix temps en cares realistes. Per tant, en contrast amb els treballs anteriors que usen imatges amb soroll, o cares de dibuixos animats o sintètiques, el sistema desenrotllat en esta tesi permet generar cares d'aspecte realista triant els nivells desitjats de quinze impressions: Por, Enuig, Atractiu, Cara de xiquet, Disgustat, Dominant, Femení, Feliç, Masculí, Prototípic, Trist, Sorprés, Amenaçador, Confiable i Inusual. Els prometedors resultats obtinguts en esta tesi permetran investigar més a fons com modelar la percepció social en les cares utilitzant un enfocament complet / Fuentes Hurtado, FJ. (2018). A system for modeling social traits in realistic faces with artificial intelligence [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/101943