• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 2
  • Tagged with
  • 3
  • 3
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Image based human body rendering via regression & MRF energy minimization

Li, Xinfeng January 2011 (has links)
A machine learning method for synthesising human images is explored to create new images without relying on 3D modelling. Machine learning allows the creation of new images through prediction from existing data based on the use of training images. In the present study, image synthesis is performed at two levels: contour and pixel. A class of learning-based methods is formulated to create object contours from the training image for the synthetic image that allow pixel synthesis within the contours in the second level. The methods rely on applying robust object descriptions, dynamic learning models after appropriate motion segmentation, and machine learning-based frameworks. Image-based human image synthesis using machine learning is a research focus that has recently gained considerable attention in the field of computer graphics. It makes use of techniques from image/motion analysis in computer vision. The problem lies in the estimation of methods for image-based object configuration (i.e. segmentation, contour outline). Using the results of these analysis methods as bases, the research adopts the machine learning approach, in which human images are synthesised by executing the synthesis of contour and pixels through the learning from training image. Firstly, thesis shows how an accurate silhouette is distilled using developed background subtraction for accuracy and efficiency. The traditional vector machine approach is used to avoid ambiguities within the regression process. Images can be represented as a class of accurate and efficient vectors for single images as well as sequences. Secondly, the framework is explored using a unique view of machine learning methods, i.e., support vector regression (SVR), to obtain the convergence result of vectors for contour allocation. The changing relationship between the synthetic image and the training image is expressed as a vector and represented in functions. Finally, a pixel synthesis is performed based on belief propagation. This thesis proposes a novel image-based rendering method for colour image synthesis using SVR and belief propagation for generalisation to enable the prediction of contour and colour information from input colour images. The methods rely on using appropriately defined and robust input colour images, optimising the input contour images within a sparse SVR framework. Firstly, the thesis shows how contour can effectively and efficiently be predicted from small numbers of input contour images. In addition, the thesis exploits the sparse properties of SVR efficiency, and makes use of SVR to estimate regression function. The image-based rendering method employed in this study enables contour synthesis for the prediction of small numbers of input source images. This procedure avoids the use of complex models and geometry information. Secondly, the method used for human body contour colouring is extended to define eight differently connected pixels, and construct a link distance field via the belief propagation method. The link distance, which acts as the message in propagation, is transformed by improving the low-envelope method in fast distance transform. Finally, the methodology is tested by considering human facial and human body clothing information. The accuracy of the test results for the human body model confirms the efficiency of the proposed method.
2

Transfigurações da imagem humana por Personas: em ambiente cultural terrestre e em ambiente de inteligência artificial. / Transfigurations of the human image by the Persona: in terrestrial cultural environment and in artificial intelligence environment

Nunes, Leandro Anderson de Loiola 27 April 2018 (has links)
A interação humana sempre esteve baseada na capacidade de produzir comunicação por meio de signos. Os signos, por sua vez, constituem os diversos textos de cultura, sejam de forma verbal, visual, verbo visual ou audiovisual. O objetivo deste trabalho foi demonstrar que todos esses são resultado da relação direta entre homem e meio ambiente terrestre, a partir de um ponto de vista fenomenológico e semiótico, o que leva à produção de cultura e seus textos. Especificamente sobre a imagem como processo semiótico, entende-se que esta refere-se não somente a imagens visuais produzidas e permitidas por meio da luz natural ou artifical mas, também e principalmente, a imagens encaradas como processos mentais e comunicacionais resultados de diagramação semiótica a partir da informação disponível no meio ambiente terrestre. Isso explica as transfigurações da imagem humana manifestas desde personagens audiovisuais às personas e avatares digitais em ambientes de inteligência artificial. Por isso, o método empregado aqui para entender esses processos foi resgatar antigas práticas culturais, comparando-as com outras mais atuais, sempre à luz de teorias semióticas e daquelas que envolvem a percepção humana como a fenomenologia, por exemplo. Esse foi o percurso para se entender como as informações disponíveis no ambiente propiciam o funcionamento biopsíquico humano em seu processo de tradução sígnica, em diferentes contextos da atuação humana, a exemplo do que tem ocorrido nos meios audiovisuais pela manipulação da imagem do corpo humano. Desde que procurou dominar suas formas de comunicação, o homem tem aprendido e proposto novos métodos que visam possibilitar a sua expressão e intenção. O resultado dessa pesquisa mostra que parece ter feito isso a partir de sua relação com quatro grandezas fenomenológicas disponíveis no ambiente terrestre: a luz, as interfaces, as superfícies e os materiais. Essas ganharam destaque no que se refere à criação de modelos biopsíquicos comunicacionais humanos, a exemplo dos sete textos de cultura apresentados e estudados neste trabalho: a Metoposcopia, a Frenologia, a Morfopsicologia, a Fisiognomonia, a Astrologia, a Cosmologia Xamânica e o Visagismo. Tais produtos culturais permitem ao homem manipular signos da comunicação, principalmente no que se refere às muitas formas em que a imagem humana, assumida como processo semiótico, tem sido manipulada para determinados fins específicos, e isso pode ser comprovado desde o surgimento da fotografia e do cinema, por exemplo. Mesmo antes dessas tecnologias, o homem conseguiu manipular sua imagem semiótica a fim de entender e explicar a existência humana com todas as suas implicações, a exemplo da criação do Mapeamento Astrológico e, mais recentemente, do Mapeamento Cosmológico Xamânico. Esses dois produtos de cultura, juntamente com os outros cinco já citados, fornecem evidências da capacidade humana em produzir significação e comunicação, a partir dos fenômenos e informações disponíveis em ambiente terrestre, projetando aquilo que entende por imagem humana, em todas as suas dimensões, como o que tem acontecido atualmente pela humanização de ambientes virtuais e digitais, frutos da inteligência artificial, por meio da criação de Personas e Avatares. / Human interaction has always been based on the ability to produce communication through signs. The signs, in turn, constitute the various cultural texts, whether verbal, visual, verbovisual or audiovisual. The objective of this work was to demonstrate that all these are the result of the direct relationship between man and the terrestrial environment, from a phenomenological and semiotic point of view, which leads to the production of culture and its texts. Specifically about the image as a semiotic process, it is understood that it refers not only to visual images produced and allowed by means of natural or artificial light, but also and mainly, to images regarded as mental processes and communicational results of semiotic diagramming from the information available in the terrestrial environment. This explains the transfigurations of the human image manifested from audiovisual characters to personas and digital avatars in artificial intelligence environments. Therefore, the method used here to understand these processes was to rescue old cultural practices, comparing them with more current ones, always in the light of semiotic theories and those that involve human perception like phenomenology, for example. This was the course to understand how the information available in the environment propitiates the human biopsychic functioning in its process of sign translation, in different contexts of human performance, such as what has occurred in the audiovisual media by manipulating the image of the human body. Since he has sought to dominate his forms of communication, man has learned and proposed new methods to enable his expression and intention. The result of this research shows that man seems to have done so from his relation with four phenomenological events available in the terrestrial environment: light, interfaces, surfaces and materials. These have gained prominence in the creation of human communicational biopsychic models, such as what has occurred through the seven culture texts presented and studied in this work: Metoposcopy, Phrenology, Morphopsychology, Physiognomy, Astrology, Shamanic Cosmology and Visagism. Such cultural products allow man to manipulate communicational signs, especially in regard to the many ways in which the human image, assumed here as a semiotic process, has been manipulated for certain specific purposes, and this can be proven since the beginning of photography and cinema, for example. Nevertheless, even before these technologies, man was able to manipulate his semiotic image in order to understand and explain human existence with all its implications, such as the creation of the Astrological Mapping and, more recently, the Shamanic Cosmological Mapping. These two culture products, along with the other five already cited, provide evidence of the human capacity to produce meaning and communication, from the phenomena and information available in the terrestrial environment, projecting what he understands by human image, in all its dimensions, such as what has happened today by the humanization of virtual and digital environments, fruits of artificial intelligence, through the creation of Personas and Avatars.
3

Transfigurações da imagem humana por Personas: em ambiente cultural terrestre e em ambiente de inteligência artificial. / Transfigurations of the human image by the Persona: in terrestrial cultural environment and in artificial intelligence environment

Leandro Anderson de Loiola Nunes 27 April 2018 (has links)
A interação humana sempre esteve baseada na capacidade de produzir comunicação por meio de signos. Os signos, por sua vez, constituem os diversos textos de cultura, sejam de forma verbal, visual, verbo visual ou audiovisual. O objetivo deste trabalho foi demonstrar que todos esses são resultado da relação direta entre homem e meio ambiente terrestre, a partir de um ponto de vista fenomenológico e semiótico, o que leva à produção de cultura e seus textos. Especificamente sobre a imagem como processo semiótico, entende-se que esta refere-se não somente a imagens visuais produzidas e permitidas por meio da luz natural ou artifical mas, também e principalmente, a imagens encaradas como processos mentais e comunicacionais resultados de diagramação semiótica a partir da informação disponível no meio ambiente terrestre. Isso explica as transfigurações da imagem humana manifestas desde personagens audiovisuais às personas e avatares digitais em ambientes de inteligência artificial. Por isso, o método empregado aqui para entender esses processos foi resgatar antigas práticas culturais, comparando-as com outras mais atuais, sempre à luz de teorias semióticas e daquelas que envolvem a percepção humana como a fenomenologia, por exemplo. Esse foi o percurso para se entender como as informações disponíveis no ambiente propiciam o funcionamento biopsíquico humano em seu processo de tradução sígnica, em diferentes contextos da atuação humana, a exemplo do que tem ocorrido nos meios audiovisuais pela manipulação da imagem do corpo humano. Desde que procurou dominar suas formas de comunicação, o homem tem aprendido e proposto novos métodos que visam possibilitar a sua expressão e intenção. O resultado dessa pesquisa mostra que parece ter feito isso a partir de sua relação com quatro grandezas fenomenológicas disponíveis no ambiente terrestre: a luz, as interfaces, as superfícies e os materiais. Essas ganharam destaque no que se refere à criação de modelos biopsíquicos comunicacionais humanos, a exemplo dos sete textos de cultura apresentados e estudados neste trabalho: a Metoposcopia, a Frenologia, a Morfopsicologia, a Fisiognomonia, a Astrologia, a Cosmologia Xamânica e o Visagismo. Tais produtos culturais permitem ao homem manipular signos da comunicação, principalmente no que se refere às muitas formas em que a imagem humana, assumida como processo semiótico, tem sido manipulada para determinados fins específicos, e isso pode ser comprovado desde o surgimento da fotografia e do cinema, por exemplo. Mesmo antes dessas tecnologias, o homem conseguiu manipular sua imagem semiótica a fim de entender e explicar a existência humana com todas as suas implicações, a exemplo da criação do Mapeamento Astrológico e, mais recentemente, do Mapeamento Cosmológico Xamânico. Esses dois produtos de cultura, juntamente com os outros cinco já citados, fornecem evidências da capacidade humana em produzir significação e comunicação, a partir dos fenômenos e informações disponíveis em ambiente terrestre, projetando aquilo que entende por imagem humana, em todas as suas dimensões, como o que tem acontecido atualmente pela humanização de ambientes virtuais e digitais, frutos da inteligência artificial, por meio da criação de Personas e Avatares. / Human interaction has always been based on the ability to produce communication through signs. The signs, in turn, constitute the various cultural texts, whether verbal, visual, verbovisual or audiovisual. The objective of this work was to demonstrate that all these are the result of the direct relationship between man and the terrestrial environment, from a phenomenological and semiotic point of view, which leads to the production of culture and its texts. Specifically about the image as a semiotic process, it is understood that it refers not only to visual images produced and allowed by means of natural or artificial light, but also and mainly, to images regarded as mental processes and communicational results of semiotic diagramming from the information available in the terrestrial environment. This explains the transfigurations of the human image manifested from audiovisual characters to personas and digital avatars in artificial intelligence environments. Therefore, the method used here to understand these processes was to rescue old cultural practices, comparing them with more current ones, always in the light of semiotic theories and those that involve human perception like phenomenology, for example. This was the course to understand how the information available in the environment propitiates the human biopsychic functioning in its process of sign translation, in different contexts of human performance, such as what has occurred in the audiovisual media by manipulating the image of the human body. Since he has sought to dominate his forms of communication, man has learned and proposed new methods to enable his expression and intention. The result of this research shows that man seems to have done so from his relation with four phenomenological events available in the terrestrial environment: light, interfaces, surfaces and materials. These have gained prominence in the creation of human communicational biopsychic models, such as what has occurred through the seven culture texts presented and studied in this work: Metoposcopy, Phrenology, Morphopsychology, Physiognomy, Astrology, Shamanic Cosmology and Visagism. Such cultural products allow man to manipulate communicational signs, especially in regard to the many ways in which the human image, assumed here as a semiotic process, has been manipulated for certain specific purposes, and this can be proven since the beginning of photography and cinema, for example. Nevertheless, even before these technologies, man was able to manipulate his semiotic image in order to understand and explain human existence with all its implications, such as the creation of the Astrological Mapping and, more recently, the Shamanic Cosmological Mapping. These two culture products, along with the other five already cited, provide evidence of the human capacity to produce meaning and communication, from the phenomena and information available in the terrestrial environment, projecting what he understands by human image, in all its dimensions, such as what has happened today by the humanization of virtual and digital environments, fruits of artificial intelligence, through the creation of Personas and Avatars.

Page generated in 0.0649 seconds