Facial expressions are visible signs of person's affective state, cognitive activity and personality. Automatic recognition of facial expressions is an important component for a wide spectrum of applications including human-computer interfaces, video conferencing, augmented reality and human activity monitoring to mention a few. Facial expression representation is an essential part in the automatic recognition of facial expressions. It is concerned with finding distinguishable features that can be utilised for representing different facial expressions without constraints of age, ethnicity or gender. This thesis reports on research and development in the facial expression representation. The author has proposed two novel methods for representing facial expressions. One is based on the shape space vector (SSV) of the statistical shape model (SSM); the other is based on the SSV of the B-spline statistical shape model (BSSM). The first proposed method uses the SSV of the SSM as a significant feature for representing facial expressions embedded in 3-D facial surfaces. In order to obtain the SSV, a novel model-based surface registration method is proposed that iteratively deforms and matches the model to an unseen new facial surface. Two major stages are included in this method, namely, model building and model fitting. In the model building stage, a SSM is built by using a training data set with estimated correspondences. In the model fitting stage, the built model is adapted to represent the shape of the new facial surface, which has not been included in the training data set. To build the model, the thin plate spline warping has been used so that all of the facial surfaces in the training data set are aligned into a common reference facial surface and the dense correspondences of points between these facial surfaces can be calculated. To fit the model to the new facial surface a modified iterative closest point (ICP) algorithm and least-squares projection on to the estimated shape space, constructed using the training data set, are applied. The second proposed method uses the SSV of the BSSM for facial expression representation. The mddel is built using B-spline control points instead of the surface points as in the SSM based method. In order to obtain the control points of B-spline, a novel method for the B-spline surface fitting has been proposed. The robustness and efficiency of both model-based facial expression representation methods are improved by introducing a multi-resolution scheme in the model fitting stage. The experimental results on simulated and real 3-D facial surfaces show that the proposed methods can effectively provide distinguishable features for facial expression analysis and recognition.

the Ashes and the Portal is an immersive stereoscopic animated short capturing the burned library after a fire disaster at Mzuzu University, Malawi, Africa, and it also witnesses the new design of the library from Virginia Tech architecture students. This animated short recreates the burned library and presents the new library design with photo-real image sequences which can immersively bring the audiences onto the site. The Ashes and the Portal utilizes the Cyclorama system, which is a 32 feet diameter and 16 feet tall cylindrical screen with four projectors that can display visual content. The surrounding panels with rendered footage could provide an immersive experience within this semi-public space. This is a collaboration project between the School of Visual Arts and the School of Architecture + Design, also with technical support from the Institute for Creativity, Arts, and Technology. This project explores the potential use of Cyclorama system as a platform for CG works, especially for stereoscopic animation. / Master of Fine Arts / The Ashes and The Portal is a computer generated animation tells a story about burned library at Mzuzu University, Malawi, Africa and a new library design from Virginia Tech architecture students. Audience is required to wear a pair of 3D goggles to view the animation inside a giant curved screen which is surrounding the viewer. The photo-real footage of burned library and new library design can visually bring audiences onto the site and provide an immersive experience. This project is a collaboration project between the School of Visual Arts and the School of Architecture + Design, also with technical support from the Institute for Creativity, Arts, and Technology. This is an educational project that explores the potential use of the Cyclorama system as a platform for computer generated media works, especially for stereoscopic animation.

The objective of this study is to apply Computer-generated imagery for knowledge and skills in daily life. There are some Computer-generated imagery study on traditional education training; however, fewer professional image processing courses of Synchronous Learning Networking are carried out in practice. The feasibility of using lecture video or practice on line in teaching Computer-generated imagery concepts is important. How do teachers examine students¡¦ performance and make good use of Synchronous Learning Networking? In this study, we will propose the following dimensions to discuss: (1) the difference on Computer-generated imagery between Synchronous Learning Networking and traditional teaching (2) the difficulty on Computer-generated imagery when teaching and learning (3) how to make better performance on Computer-generated imagery under Synchronous Learning Networking. Comparative Case Study is conducted at Tainan Training Center and LMS (Learning Management System) of K12 digital school for the adults who actively study Computer-generated imagery by the means of traditional learning and E-learning. We put Computer-generated imagery under traditional teaching and Synchronous Learning Networking, and we make questionnaires for examining the detailed factors regarding to the performance of Computer-generated imagery.The results indicates that lecture on Synchronous Learning Networking is something about practice on line, whiteboard, slides show, top desk share and homepage browse with office hours and paper work in replace of real discussion. Sometimes teachers and students are meeting the information and interaction delay under Synchronous Learning Networking. Therefore, we are offering seven suggestions to get Computer-generated imagery under Synchronous Learning Networking improved: (1) Teachers suggest that the standard of hardware and Net environment is required. (2) Students should develop active attitude for learning under Synchronous Learning Networking. (3) Teachers should perform on line teaching and stream video is auxiliary. (4) Multiple material for the topic is available for students to choose and adjust their learning model. (5) Dividing into groups is not good for teaching and office hour or guest board is much better for discussion and interaction. (6) Teachers should create new Computer-generated imagery courses to inspire students¡¦ motivation. (7) Continued materials and platform for students to review and interact are required.

Technologies in digital cinema are quickly changing the way contemporary filmmakers create films and how audiences currently perceive them. As we move onward into the digital turn, it becomes ever more apparent that the medium of film has been emancipated from its dependence on the photograph. Directors are no longer required to capture the objectively real as it sits before the photographic lens, but can essentially construct it via groundbreaking advancements in computer-generated imagery, motion capture technology, and digital 3D camera systems and display technologies. Since the origins of film, spectators and filmmakers have assumed an existing relationship between reality and the photographic image. Yet digital film technologies now provide us with hyper-facsimiles of reality that are perceived as photographic, but are often created by way of computer processes. Digital cinema currently allows the viewer to inhabit and interact with cinematic realities in unprecedented ways, and it is this contemporary paradigmatic shift from the analog to the digital that has catalyzed fundamentally new ways of looking at the filmic image. In this paper, I will examine the perceptual complexities of contemporary digital film through the lens of these cinematic technologies by examining their impact on the viewer’s experience.

Background. In computer graphics, it can be a time-consuming process to render photorealistic images. This rendering process, called “physically based rendering” uses complex algorithms to calculate the behavior of light. Fortunately, most renderers offer the possibility to alter the render-settings, allowing for a decrease in render time, but this usually comes at the cost of a lower quality image. Objectives. This study aims to identify what setting has the highest impact on the rendering process in the V-Ray renderer. It also examines if a perceived difference can be seen when reducing this setting. Methods. To achieve this, an experiment was done where 22 participants would indicate their preference for rendered images. The images were rendered in V-Ray with different settings, which affected their respective render time differently. Additionally, an objective image metric was used to analyze the images and try to form a correlation with the subjective results. Results. The results show that the anti-aliasing setting had the highest impact on render time as well as user preference. It was found that participants preferred images with at least 25% to 50% anti-aliasing depending on the scene. The objective results also coincided well enough with the subjective results that it could be used as a faster analytical tool to measure the quality of a computer-generated image. Prior knowledge of rendering was also taken into account but did not give conclusive results about user preferences. Conclusions. From the results it can be concluded that anti-aliasing is the most important setting for achieving good subjective image quality in V-Ray. Additionally, the use of an objective image assessment tool can drastically speed up the process for targeting a specific visual quality goal.

Virtual influencers (VIs), computer-generated characters, can act as a medium to influence followers on social media platforms. This is a relatively novel phenomenon, with popular VIs having over six million followers. This study investigates VIs from the perspective of human-computer interaction. Nine participants from four countries were interviewed about their interactions with a variety of fictional VIs in different settings. The study uncovers new user perceptions and attitudes towards VIs, including pessimism towards VIs, loss of trust and likeability towards virtual characters, and the perception of VIs as being run by artificial intelligence (AI). It was found that content relating to fitness, personal tips, and social activism demands more transparency about the authority and agency of the VI from the users. Finally, this study discusses the ethical implications of VIs, highlights an avenue of research in the AI domain, and makes suggestions for human-computer interaction (HCI) practitioners curating social media experiences. / Virtuella influencers (VI), datorgenererade karaktärer, kan fungera som ett medium för att påverka följare på sociala medieplattformar. Detta är ett relativt nytt fenomen, där populära VI har över sex miljoner följare. Denna studie undersöker fenomenet VI ur människa-datorinteraktions perspektiv. Nio deltagare från fyra länder intervjuades om deras interaktioner med olika fiktiva VI i olika miljöer. Studien visar på nya uppfattningar och attityder från användare gentemot VI, inklusive pessimism gentemot VI, förlust av förtroende och gillande gentemot virtuella karaktärer, samt uppfattningen om att VI drivs av artificiell intelligens (AI). Det visade sig att användarna kräver att innehåll relaterat till träning, personliga tips och social aktivism kräver mer öppenhet om VI:s befogenhet och agenda. Slutligen diskuterar denna studie de etiska konsekvenserna av VI, belyser ett forskningsområde inom AI och ger förslag till utövare inom människa-datorinteraktion (HCI) som kuraterar sociala medieupplevelser

Made available in DSpace on 2016-06-02T19:39:53Z (GMT). No. of bitstreams: 1 6587.pdf: 1812199 bytes, checksum: 1dabca73767edd87c867bdd4e17ab882 (MD5) Previous issue date: 2015-02-27 / The art goes through transformations on elapse of time, as do the resources and techniques used to produce it, and it s transformed as well as the predominant medium of communication alleged experience mediation. At the beginning of the 20th century Benjamin identified this process and analysed its effects, particularly through movies (BENJAMIN, 1987) and nowadays, with digital movie development, we observe several transformations which impact movie s language and the ways that spectators interact with it. Under the hypothesis that techniques applied to digital movies modify the way that spectators interact with the film, we develop our research on defining a cutout on stereoscopy, which produces the depth effect on 3D movies, and the use of CGI (computer generated imagery), which consists in computer created and animated images, having the target to discuss the impact of these resources on spectator s experience of interaction with movies, and more specifically to investigate new features of digital cinema aiming to understand what are the possible changes on movie s language and broached contents, as well as recognizing features of the ways of perception that might come up on this circumstances. For these purposes we develop a theoretical and empirical research grounded on the theoretical references of Critical Theory of Society. / A arte modifica-se no decorrer da história, bem como os recursos e técnicas pelos quais é produzida, e modifica-se também o meio de comunicação predominante como suposta mediação da experiência. No início do século XX, Benjamin identificou esse processo e analisou seus efeitos, sobretudo por meio do cinema (BENJAMIN, 1987a) e atualmente, com o desenvolvimento do cinema digital, observamos diversas transformações que impactam a linguagem cinematográfica e as formas como os espectadores interagem com as mesmas. Sob a hipótese de que técnicas aplicadas ao cinema digital modificam a forma como o espectador interage com o filme, desenvolvemos a nossa pesquisa delimitando um recorte sobre a estereoscopia, que produz o efeito de profundidade no cinema 3D e o uso das CGI (Computer generated imagery), que consiste em imagens criadas e animadas digitalmente, com objetivo de discutir o impacto de tais recursos sobre a experiência do espectador em interação com as obras cinematográficas, e mais especificamente investigar novas características do cinema digital a fim de compreender quais são as possíveis mudanças na linguagem do cinema e conteúdos abordados, bem como reconhecer características das formas de percepção que possivelmente surjam no cenário específico da cultura audiovisual digital do século XXI. Para tanto, desenvolvemos uma pesquisa teórica e empírica fundamentada no referencial teórico da Teoria Crítica da Sociedade.

No description available.

In the light of the digitalization and the emergence of social media, the concept of influencer marketing has increased significantly in importance on a global scale and is now considered one of the most effective, powerful and cost-effective marketing tools for businesses in today’s society. Nevertheless, despite the effectiveness of influencer marketing, the growing worldwide marketing trend of Computer Generated Imagery (CGI) influencers, also described as human-like influencers, is currently revolutionizing today’s influencer marketing and is expected to become the new way of marketing from a future perspective. With millions of followers on social media, CGI influencers are quickly gaining three times higher follower engagement than prominent celebrities and human influencers, even though their existence is not real. As a result, the organizational use of CGI influencer marketing has intensified markedly on a global scale from several world-leading brands. Although CGI influencers are expected to increase significantly within marketing, the current knowledge and understanding of CGI influencers as a marketing strategy for brands and products is insufficient and is in essential need of further exploration. This thesis contributes to the yet very limited empirical research by focusing on the research gap of differences between CGI influencers and human influencers from a consumer perspective, with the following research question: “How do CGI influencers differ from human influencers in terms of its impact on consumers’ purchase intentions?”  The research purpose of this thesis is to explore whether there is any difference in the impact of CGI influencers and human influencers on consumers’ purchase intentions in order to increase the understanding of the effectiveness of virtual influencer marketing in comparison to influencer marketing on consumer behavior. The research purpose was fulfilled by undertaking a qualitative inductive research approach and performing ten semi-structured interviews with respondents which both follow at least one macro- or mega human influencer and CGI influencer on Instagram. The thesis focuses on CGI influencers in relation to the aspects of motivations to follow, opinion leadership and parasocial relationships, since these are closely linked to purchase intentions. By increasing the understanding of consumers’ view, attitude and behavior, this thesis has discovered multiple key aspects in how CGI influencers differ from human influencers in terms of its impact on consumers’ purchase intentions. The results show that CGI influencers are generally seen as more or less the same as human influencers in terms of inspiration. Followingly, it is possible for consumers to create parasocial relationships with CGI influencers. Nevertheless, this thesis has identified a dominant perspective that CGI influencers affect purchase intentions to a lesser extent than human influencers at present, which is primarily based on higher-developed parasocial relationships, a greater perceived genuineness and higher consumer trust for human influencers. The core theoretical implications are the expanded scientific research on CGI influencers as a marketing phenomenon, and the perceived differences and similarities between CGI influencers and human influencers from a consumer perspective. The key practical implications are the increased understanding of the effectiveness of virtual influencer marketing in comparison to influencer marketing on consumer behavior, and how to implement CGI influencers in the marketing strategy successfully. On a societal level, the most central societal implications are several ethical issues of CGI influencers within marketing.

Em um primeiro momento as novas tecnologias podem impulsionar acentuadamente a interação com um elemento, o que pode levar à um aprendizado significativo, mas esse impulso reduz assim que a interação se torna comum ou até mesmo repetitiva. Quando essa nova tecnologia se torna natural para o usuário ela deixa de ser uma novidade e se torna uma ferramenta. O uso de Imagens Geradas por Computador (IGC) experienciaram exatamente isso, décadas atrás, mas estão constantemente sendo iteradas de acordo com suas necessidades de reavaliação frequentes. Com o desenvolvimento das IGC as imagens tridimensionais deixaram de ser um formato excessivamente complicado, ao passo que hardwares e conceitos foram adentrando objetos do dia-a-dia como smartphones, webcams, câmeras, aplicativos de geração de malhas 3D, etc. O seu uso com objetivos museológicos se tornou evidente no campo da herança cultural para arquivamento e comunicação. Sendo assim, para verificar a viabilidade para uma solução fácil e de baixo custo visando novos usuários, diferentes tipos de métodos não-destrutivos de reconstrução baseadas na superfície foram analisados. Para isso, identificou-se a qualidade do resultado de precisão da malha, a rastreabilidade e a compatibilidade dos mesmos. Com esse objetivo, foi proposto um método com um conjunto de métricas que podem ser aplicadas para determinar a usabilidade de um objeto reconstruído com um fim específico. Quatro artefatos arqueológicos foram escaneados usando métodos de vídeo fotogrametria e vídeo de profundidade, a serem comparados com substitutos escaneados a laser. Depois de analisar os escaneamentos dos mesmos objetos com esses diferentes métodos, concluiu-se que a fotogrametria é capaz de gerar com rapidez um modelo altamente detalhado, mas com várias distorções. A profundidade de câmera gerou superfícies mais suaves e maior incidência de erros. Em última análise, cada método apresentado demonstra múltiplas possibilidades para materialização, dependendo do objetivo, resolução e de quão detalhado o objeto deve ser para ser corretamente compreendido. / At first glance new technologies can provide an engaging way to interact with a subject which may induce a meaningful learning, but it soon falls short when it becomes common or even repetitive. As this new technology becomes natural to the user, it no longer relies on novelty and goes into another condition, as a tool. The use of Computer-Generated Imagery (CGI) experienced exactly this, decades ago, but as it\'s constantly being iterated upon it needs to be reassessed often. As CGI goes, the tridimensional imagery as an overcomplicated format started to fade, as new hardware and concepts made way into everyday objects such as smartphones, webcams, cameras, 3D mesh generation apps, etc. It\'s use for museological purposes became clear in the field of cultural heritage for archiving and communication. So, to verify the viability for a low-cost and easy to use solution aiming to novice users, different types of non-destructive methods surface based reconstructions are analyzed to identify the quality of the resulted mesh based on precision, traceability and compatibility. To this end, it was proposed a method with a set of metrics which can be used to point out the usability of a reconstructed object for a specific end. Four archaeological artifacts were scanned using the video photogrammetry method and the depth video method, to be compared with a laser scanned surrogate. After analyzing the scans of the same objects with these different methods, the conclusion is that photogrammetry has the power to provide a highly detailed model very fast but with several distortions. The depth camera provided smoother surfaces and higher error. Ultimately, each method presented multiple possibilities for materialize itself, depending on target resolution and how detailed the object must be to correctly understand it.