Página 1 dos resultados de 67772 itens digitais encontrados em 0.037 segundos

Contribuição para o estudo da memória de reconhecimento social em ratos; Contributions to the study of social recognition memory in rats

Moura, Paula Jaqueline de
Fonte: Biblioteca Digitais de Teses e Dissertações da USP Publicador: Biblioteca Digitais de Teses e Dissertações da USP
Tipo: Tese de Doutorado Formato: application/pdf
Publicado em 21/07/2008 PT
Relevância na Pesquisa
36.38%
O paradigma intruso-residente vem sendo intensamente empregado em estudos para avaliar a memória de reconhecimento social em roedores. Tipicamente, ratos adultos, denominados residentes, são expostos a dois encontros sucessivos, de 5 minutos cada, com um mesmo rato juvenil ou com ratos juvenis diferentes, denominados intrusos; o intervalo de tempo entre encontros é 30 minutos. A quantidade de comportamentos sociais do residente (no segundo encontro) em relação a um intruso familiar é substancialmente menor do que o observado no primeiro encontro, o que não ocorre quando o segundo encontro envolve um juvenil novo; esse resultado caracteriza a memoria de reconhecimento social. Se o intervalo de tempo entre os encontros é aumentado para 60 minutos, a redução da investigação social do intruso familiar por parte do residente desaparece, levando à conclusão de que a memória de reconhecimento social seria um mecanismo para retenção temporária de informações. O objetivo central do presente trabalho foi contribuir para o entendimento da memória de reconhecimento social em ratos. Foram realizados três experimentos. No primeiro experimento avaliou-se se a expressão de comportamentos sociais e também da memória de reconhecimento social estão sujeitos à modulação temporal. No segundo experimento avaliou-se em que extensão o aumento do tempo de exposição ao intruso durante o primeiro encontro resulta num aumento da duração da memoria de reconhecimento social. No terceiro experimento avaliou-se se um procedimento de rotina na maioria dos laboratorios...

Investigação de fatores implicados na diferença entre os sexos no reconhecimento de expressões faciais: emoção despertada e fases do ciclo menstrual; Investigation of factors implicated in sex difference in the recognition of facial expressions: aroused emotionand phases of the menstrual cycle

Guapo, Vinicius Guandalini
Fonte: Biblioteca Digitais de Teses e Dissertações da USP Publicador: Biblioteca Digitais de Teses e Dissertações da USP
Tipo: Tese de Doutorado Formato: application/pdf
Publicado em 18/01/2013 PT
Relevância na Pesquisa
36.35%
As diferenças entre os sexos e o impacto dos hormônios sexuais no processamento emocional normal e patológico destacam-se na investigação do dimorfismo sexual na frequência, diagnóstico e terapêutica de patologias psiquiátricas. Transtornos depressivos e ansiosos não apenas são mais comuns em mulheres, quando comparadas aos homens, como parecem ser influenciados pelas concentrações hormonais séricas das mulheres em diferentes fases do ciclo reprodutivo. Ao mesmo tempo, o sexo e as concentrações dos hormônios sexuais, mostram influência na função do cérebro em uma diversidade de tarefas cognitivas e emocionais. O reconhecimento de expressões faciais de emoções básicas tem sido visto como função de extrema importância na adaptação social do indivíduo e existem evidências de que esteja relacionado com o desenvolvimento de transtornos psiquiátricos. Já foi demonstrado que esta tarefa é influenciada pelo sexo do indivíduo e seu ambiente hormonal, no entanto, a literatura carece de resposta sobre os mecanismos pelos quais estas diferenças acontecem. Em dois experimentos buscamos maior entendimento de como se dão as diferenças entre os sexos no reconhecimento de expressões faciais de emoções básicas (raiva...

Sistema de reconhecimento de caracteres numéricos manuscritos baseado nas redes neurais artificiais paraconsistentes; Handwritten numeric character recognition system based on paraconsistent artificial neural network

Souza, Sheila
Fonte: Biblioteca Digitais de Teses e Dissertações da USP Publicador: Biblioteca Digitais de Teses e Dissertações da USP
Tipo: Dissertação de Mestrado Formato: application/pdf
Publicado em 26/11/2013 PT
Relevância na Pesquisa
36.35%
O reconhecimento de padrões por computador é uma das mais importantes ferramentas da Inteligência Artificial presente em inúmeras áreas do conhecimento com aplicações em diversos setores, incluindo o reconhecimento de caracteres. O objetivo da dissertação se concentra na investigação de um processo computacional automatizado - Sistema Computacional Paraconsistente - capaz de reconhecer Caracteres Numéricos Manuscritos e Caracteres Magnéticos Codificados em 7 Barras utilizados em cheques bancários brasileiros, fornecendo uma fundamentação técnica para reconhecer documentos e imagens digitalizadas e, também, sinais biológicos. Embora haja vários estudos em reconhecimento de caracteres, optou-se pelo estudo desse tema devido à sua intrínseca importância e constante desenvolvimento, além de possibilitar adaptações para fazer o reconhecimento de diferentes tipos de sinais como, por exemplo, sinais biológicos. A metodologia adotada para essa tarefa se baseia nas Redes Neurais Artificiais Paraconsistentes por se tratar de uma ferramenta com capacidade de trabalhar com dados imprecisos, inconsistentes e paracompletos sem o perigo de trivialização. O processo de reconhecimento desse sistema é realizado a partir de algumas características do caractere previamente selecionadas com base em algumas técnicas do Grafismo e realiza-se a análise dessas características bem como o reconhecimento do caractere através das Redes Neurais Artificiais Paraconsistentes O sistema foi construído para reconhecer caracteres numéricos com um padrão previamente definido...

Improving face recognition with multispectral fusion and support vector machines

Chiachia, Giovani
Fonte: Universidade Estadual Paulista (UNESP) Publicador: Universidade Estadual Paulista (UNESP)
Tipo: Dissertação de Mestrado Formato: 86 f. : il. color.
ENG
Relevância na Pesquisa
36.36%
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES); Pós-graduação em Ciência da Computação - IBILCE; O reconhecimento facial é uma das principais formas de identificação humana. Apesar das pesquisas em reconhecimento facial automático terem crescido substancialmente ao longo dos últimos 35 anos, identificar pessoas a partir da face continua sendo um desafio para as áreas de Visão Computacional e Reconhecimento de Padrões. Em função dos cenários variarem desde a identificação a partir de fotografias até o reconhecimento baseado em vídeos sem nenhum tipo de controle ao serem gravados, os maiores desafios estão relacionados à independência contra diferentes tipos de iluminação, pose e expressão. O objetivo desta dissertação é propor técnicas que possam contribuir para a melhoria dos sistemas de reconhecimento facial. A primeira técnica endereça o problema da iluminação através da fusão dos espectros visível e infravermelho da face. Através desta abordagem, as taxas de reconhecimento foram melhoradas em 2.07% enquanto a taxa de erro igual (EER) foi reduzida em 45.47%. A segunda técnica trata do caso da extração e classificação de características faciais. Ela propõe um novo modelo para reconhecimento facial através do uso de características extraídas por Histogramas Census e de uma técnica de reconhecimento de padrões baseada em Máquinas de Vetores de Suporte (SVMs). Este outro grupo de experimentos nos possibilitou aumentar a precisão do reconhecimento no teste FERET fa/fb em 0.5%. Além destes resultados...

The recognition of work

Nierling, Linda
Fonte: IET Publicador: IET
Tipo: Artigo de Revista Científica
Publicado em /11/2007 ENG
Relevância na Pesquisa
36.38%
The following article argues that recognition structures in work relations differ significantly in the sphere of paid work in contrast to unpaid work in private spheres. According to the systematic approach on recognition of Axel Honneth three different levels of recognition are identified: the interpersonal recognition, organisational recognition and societal recognition. Based on this framework it can be stated that recognition structures in the sphere of paid work and in private spheres differ very much. Whereas recognition in private spheres depends very much on personal relations, thus on the interpersonal level, recognition in employment relationships can be moreover built on organisational structures. Comparing recognition structures in both fields it becomes apparent, that recognition in field of employment can be characterised as much more concrete, comparable and measurable. Therefore, it can be concluded that the structural differences of recognition contribute to the high societal and individual importance of employment in contrast to unpaid work in private spheres.

The contribution of color during object recognition: behavioral, electrophysiological and neuroimaging evidence

Bramão, Inês
Fonte: Universidade do Algarve Publicador: Universidade do Algarve
Tipo: Tese de Doutorado
Publicado em //2011 ENG
Relevância na Pesquisa
36.35%
Tese de dout., Psicologia, Faculdade de Ciências Humanas e Sociais, Univ. do Algarve, 2011; In this thesis, we present six studies that investigated the role of color information during visual object recognition. The interactions between surface color and color knowledge information were investigated in two studies (chapters 2 and 3). In chapters 4 and 5, we present data that identify the visual processing stage at which color information improves color and non-color diagnostic object recognition. In chapter 6, the neural pathways supporting color object recognition were investigated. Additionally, in an attempt to bring some consistency to the literature, we performed a systematic meta-analysis on the effects of color on object recognition in chapter 7. Chapter 2 and 3 provided data suggesting that surface color information is more influential than color knowledge information during object recognition. Chapter 4 and 5 showed that color information improves the recognition of color and non-color diagnostic objects at different stages of visual processing. Although color information is an important cue for both of these types of objects in the early visual processes, it is also important in later stages of visual processing for color diagnostic object recognition. In chapter 6...

Analysis and Applications of Feature-Based Object Recognition

Selinger, Andrea ; Nelson, Randal C.
Fonte: University of Rochester. Computer Science Department. Publicador: University of Rochester. Computer Science Department.
Tipo: Technical Report; Thesis
ENG
Relevância na Pesquisa
36.35%
Thesis (Ph. D.)--University of Rochester. Dept. of Computer Science, 2001. Simultaneously published in the Technical Report series.; Due to recent advances in the art, object recognition may soon replace low-level feature extraction processes in automatic image database annotation. However, improvement in performance is still an important consideration. In addition, model acquisition for appearance-based object recognition is tedious, since such systems usually require training on a large set of segmentable example views that cover variation among class exemplars. These views have to be labeled with object identity and pose. In this thesis we first develop and analyze a feature-based object recognition system that demonstrates good recognition of a variety of 3D shapes, with full orthographic invariance. We report the results of large-scale tests that evaluate recognition performance in conditions of background clutter and partial occlusion, as well as generic capabilities of the system. We develop a statistical framework for predicting the performance in a variety of situations from a few basic measurements. We investigate the performance of object recognition systems to see which, if any, design axes of such systems hold the greatest potential for improving performance. One conclusion is that the greatest leverage seems to lie at the level of intermediate feature construction. We also analyze the effect of other improvements...

State-trace analysis of associative recognition: comparing single-process and dual-process models.

Hamm, Nicholas
Fonte: Universidade de Adelaide Publicador: Universidade de Adelaide
Tipo: Tese de Doutorado
Publicado em //2014
Relevância na Pesquisa
36.39%
The aim of this thesis is to investigate competing explanations of the processes underlying associative recognition. Like recognition memory for individual items, associative recognition is currently understood through two different classes of model. The first is the single-process model class which holds that associative recognition decisions are based on a continuum of associative memory strength. The second is the dual-process model class, which holds that associative recognition decisions are based on two sources of information, called familiarity and recollection. Familiarity is conceptualised as a fast-acting, context-free „feeling of knowing‟, while recollection is said to be a slower, more conscious process allowing for the recall of detail and context. Familiarity may play a role in associative recognition through a mechanism called unitisation, whereby two distinct stimuli are bound into a single individual memory trace. State-trace analysis is a method to determine the number of latent variables or processes that contribute to performance on a set of tasks, under mild assumptions. A critical diagnostic feature is the dimensionality of the state-trace plot – a plot of performance on one dependent variable against the other. If associative recognition depends on a single latent variable then manipulation of experimental factors affecting memory should result in a unidimensional state-trace plot. If associative recognition depends on two or more latent variables which are differentially affected by the experimental factors then a bidimensional state-trace will result. State-trace analysis therefore provides a method of discriminating a class of single-process models from a class of dual-process models. State-trace analysis was applied to associative recognition in four experiments. Each experiment utilised two independent variables that previous research had suggested could differentially affect familiarity and recollection. Experiment 1 investigated associative recognition of word pairs by manipulating attention and study presentation frequency. Experiments 2 investigated associative recognition of word pairs under conditions designed to encourage unitisation by pairing an encoding-based unitisation manipulation with a working memory load manipulation. Experiment 3 manipulated the same unitisation instructions as well as varying study time. Experiment 4 examined the effect of unitisation using pairs of faces and manipulated visual similarity and study time. State-trace analysis of the four experiments consistently revealed unidimensional state-trace plots. Using a recently developed monotonic regression statistical test...

Visual speech recognition for European Portuguese; Reconhecimento visual da fala para português europeu

Abreu, Hélder Paulo Monteiro
Fonte: Universidade do Minho Publicador: Universidade do Minho
Tipo: Dissertação de Mestrado
Publicado em 18/12/2014 ENG
Relevância na Pesquisa
36.36%
Dissertação de mestrado em Engenharia Informática; O reconhecimento da fala baseado em características visuais teve início na década de 80, integrado em sistemas de reconhecimento audiovisual da fala. De facto, o objetivo inicial do recurso a características visuais foi o de aumentar a robustez dos sistemas de reconhecimento automático da fala, que perdem precisão rapidamente em ambientes ruidosos. Contudo, o potencial para manter um bom desempenho de reconhecimento de fala em situações em que os dados acústicos estão comprometidos ou em qualquer outra situação em que é necessária uma pessoa capaz de ler os lábios, levou os investigadores e a criar e desenvolver a área de reconhecimento visual da fala. Os sistemas tradicionais de reconhecimento visual da fala usam apenas informação RGB, seguindo uma abordagem unimodal, uma vez que o recurso a outras modalidades é dispendioso e implica problemas de sincronização entre as mesmas. O lançamento do Microsoft Kinect, que inclui um microfone, uma câmara RGB e um sensor de profundidade, abriu novas portas às áreas de reconhecimento da fala. Para além disso, todas as modalidades podem ser sincronizadas usando as funcionalidades do SDK. Recentemente...

Towards an integrative framework of brand country of origin recognition determinants : a cross-classified hierarchical model

Cerviño, Julio
Fonte: Emerald Publicador: Emerald
Tipo: info:eu-repo/semantics/acceptedVersion; info:eu-repo/semantics/article Formato: text/plain; application/pdf
Publicado em //2011 ENG
Relevância na Pesquisa
36.38%
To propose a framework integrating the types and levels of the determinants of brand CO recognition and to provide evidence on Internet users’ brand CO recognition rates using a sample of multi-regional and global brands from a variety of product categories and countries. We integrate 'level-1' consumer and brand characteristics and 'level-2' product category and country effects in a single framework. Data obtained through an original on-line survey hosted by Yahoo provide the basis for the empirical analysis. Seven hypotheses are tested using a two-level cross-classified random-effect model (‘HCM2’) : (a) Education is positively related with brand CO recognition; (b) experience with brands is positively related with brand CO recognition; (c) integration between the consumer and the country of a foreign brand is positively related with brand CO recognition; (d) Internet users’ classification performance is significantly better for domestic than for foreign brands; (e) brand-name congruence with true brand origin is positively related with brand CO recognition; (f) brand equity explains brand CO recognition, and (g) product categories with higher consumer involvement enhance brand CO recognition. Brand CO recognition performance by Internet users is in line with classification performance rates reported in other studies dealing with well-know and global brands. The main limitation is the cross-sectional study design. The research implications suggest that scholars should consider level-2 product category and country characteristics in their models...

Item noise versus context noise: using the list length effect to investigate the source of interference in recognition memory.

Kinnell, Angela
Fonte: Universidade de Adelaide Publicador: Universidade de Adelaide
Tipo: Tese de Doutorado
Publicado em //2009
Relevância na Pesquisa
36.37%
The present thesis aimed to investigate the source of interference in recognition memory. There are two primary alternatives – the item noise approach, in which interference comes about as a consequence of the other items on the study list, and the context noise approach, wherein interference arises from the previous contexts in which an item has been encountered. Alternatively, interference may occur through a combination of both item and context noise. There are many mathematical models designed to simulate the recognition process that incorporate either item or context noise, or both. Item noise models predict a significant list length effect, that is, that memory for an item that was part of a short list at study is better than that for an item that was part of a long list. Context noise models no not predict a significant difference in memory based on the length of the study list. The presence or absence of the list length effect can therefore be used as a mechanism by which to differentiate item and context noise models. The list length effect is among the most documented and replicated findings in the recognition memory literature (Gronlund & Elam, 1994). Yet, while many experiments have been conducted which have identified a significant list length effect in recognition (e.g. Bowles & Glanzer...

A Few Days of A Robot's Life in the Human's World: Toward Incremental Individual Recognition

Aryananda, Lijin
Fonte: MIT - Massachusetts Institute of Technology Publicador: MIT - Massachusetts Institute of Technology
Formato: 244 p.
Relevância na Pesquisa
36.35%
This thesis presents an integrated framework and implementation for Mertz, an expressive robotic creature for exploring the task of face recognition through natural interaction in an incremental and unsupervised fashion. The goal of this thesis is to advance toward a framework which would allow robots to incrementally ``get to know'' a set of familiar individuals in a natural and extendable way. This thesis is motivated by the increasingly popular goal of integrating robots in the home. In order to be effective in human-centric tasks, the robots must be able to not only recognize each family member, but also to learn about the roles of various people in the household.In this thesis, we focus on two particular limitations of the current technology. Firstly, most of face recognition research concentrate on the supervised classification problem. Currently, one of the biggest problems in face recognition is how to generalize the system to be able to recognize new test data that vary from the training data. Thus, until this problem is solved completely, the existing supervised approaches may require multiple manual introduction and labelling sessions to include training data with enough variations. Secondly, there is typically a large gap between research prototypes and commercial products...

Reconocimiento de patrones utilizando técnicas estadísticas y conexionistas aplicadas a la clasificación de dígitos manuscritos; Pattern recognition using statistical techniques and neural networks: application to handwritten digit classification

Seijas, Leticia María
Fonte: Facultad de Ciencias Exactas y Naturales. Universidad de Buenos Aires Publicador: Facultad de Ciencias Exactas y Naturales. Universidad de Buenos Aires
Tipo: info:eu-repo/semantics/doctoralThesis; tesis doctoral; info:eu-repo/semantics/publishedVersion Formato: application/pdf
Publicado em //2011 SPA
Relevância na Pesquisa
36.35%
El Reconocimiento de Patrones es el estudio de cómo las máquinas pueden observar el ambiente o entorno, aprender a distinguir patrones de interés a partir de la experiencia, y tomar decisiones razonables con respecto a las categorías a las que pertenecen dichos patrones. El mejor reconocedor de patrones conocido hasta ahora es el ser humano, no sabiéndose a ciencia cierta cuál es el proceso mediante el cual los humanos realizamos esta tarea. El Reconocimiento Optico de Caracteres (OCR) es uno de los tópicos más antiguos dentro del Reconocimiento de Patrones y una de las areas de investigación más importante y activa, que en la actualidad presenta desafío: la precisión en el reconocimiento asociada tanto a caracteres impresos en una imagen degradada o a caracteres manuscritos es aún insuficiente, existiendo errores en el reconocimiento. El Reconocimiento de Dígitos Manuscritos es un tema destacado dentro de OCR, por las aplicaciones relacionadas, como el procesamiento automático de cheques bancarios, la clasificación de correo en base a la lectura de códigos postales, la lectura automática de formularios y documentos con escritura manuscrita, dispositivos de lectura para ciegos, reconocimiento de escritura en computadoras manuales PDA...

Methodological improvement on local Gabor face recognition based on feature selection and enhanced Borda count

Castillo, Luis E.; Cament, Leonardo A.; Pérez, Claudio A.
Fonte: Elsevier Publicador: Elsevier
Tipo: Artículo de revista
EN
Relevância na Pesquisa
36.36%
Artículo de publicación ISI; Face recognition has a wide range of possible applications in surveillance, human computer interfaces and marketing and advertising goods for selected customers according to age and gender. Because of the high classification rate and reduced computational time, one of the best methods for face recognition is based on Gabor jet feature extraction and Borda count classification. In this paper, we propose methodological improvements to increase face recognition rate by selection of Gabor jets using entropy and genetic algorithms. This selection of jets additionally allows faster processing for real-time face recognition. We also propose improvements in the Borda count classification through a weighted Borda count and a threshold to eliminate low score jets from the voting process to increase the face recognition rate. Combinations of Gabor jet selection and Borda count improvements are also proposed. We compare our results with those published in the literature to date and find significant improvements. Our best results on the FERET database are 99.8%, 99.5%, 89.2% and 86.8% recognition rates on the subsets Fb, Fc, Dup1 and Dup2, respectively. Compared to the best results published in the literature, the total number of recognition errors decreased from 163 to 112 (31%). We also tested the proposed method under illumination changes...

Better Exploiting OS-CNNs for Better Event Recognition in Images

Wang, Limin; Wang, Zhe; Guo, Sheng; Qiao, Yu
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 14/10/2015
Relevância na Pesquisa
36.35%
Event recognition from still images is one of the most important problems for image understanding. However, compared with object recognition and scene recognition, event recognition has received much less research attention in computer vision community. This paper addresses the problem of cultural event recognition in still images and focuses on applying deep learning methods on this problem. In particular, we utilize the successful architecture of Object-Scene Convolutional Neural Networks (OS-CNNs) to perform event recognition. OS-CNNs are composed of object nets and scene nets, which transfer the learned representations from the pre-trained models on large-scale object and scene recognition datasets, respectively. We propose four types of scenarios to explore OS-CNNs for event recognition by treating them as either "end-to-end event predictors" or "generic feature extractors". Our experimental results demonstrate that the global and local representations of OS-CNNs are complementary to each other. Finally, based on our investigation of OS-CNNs, we come up with a solution for the cultural event recognition track at the ICCV ChaLearn Looking at People (LAP) challenge 2015. Our team secures the third place at this challenge and our result is very close to the best performance.; Comment: 8 pages. This work is following our previous work: http://arxiv.org/abs/1505.00296

Fast Neuromimetic Object Recognition using FPGA Outperforms GPU Implementations

Orchard, Garrick; Martin, Jacob G.; Vogelstein, R. Jacob; Etienne-Cummings, Ralph
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 31/10/2015
Relevância na Pesquisa
36.35%
Recognition of objects in still images has traditionally been regarded as a difficult computational problem. Although modern automated methods for visual object recognition have achieved steadily increasing recognition accuracy, even the most advanced computational vision approaches are unable to obtain performance equal to that of humans. This has led to the creation of many biologically-inspired models of visual object recognition, among them the HMAX model. HMAX is traditionally known to achieve high accuracy in visual object recognition tasks at the expense of significant computational complexity. Increasing complexity, in turn, increases computation time, reducing the number of images that can be processed per unit time. In this paper we describe how the computationally intensive, biologically inspired HMAX model for visual object recognition can be modified for implementation on a commercial Field Programmable Gate Array, specifically the Xilinx Virtex 6 ML605 evaluation board with XC6VLX240T FPGA. We show that with minor modifications to the traditional HMAX model we can perform recognition on images of size 128x128 pixels at a rate of 190 images per second with a less than 1% loss in recognition accuracy in both binary and multi-class visual object recognition tasks.; Comment: 14 pages...

Plastic Recognition: The Politics and Aesthetics of Facial Representation from Silent Cinema to Cognitive Neuroscience

Geil, Abraham
Fonte: Universidade Duke Publicador: Universidade Duke
Tipo: Dissertação
Publicado em //2013
Relevância na Pesquisa
36.36%

Plastic Recognition traces a critical genealogy of the human face in cinema and its afterlives. By rethinking the history of film theory through its various investments in the face, it seeks to intervene not only in the discipline of film studies but more broadly within contemporary political and scientific discourse. This dissertation contends that the face is a privileged site for thinking through the question of recognition, a concept that cuts across a range of aesthetic, political, philosophical, and scientific thought. Plastic Recognition examines this intimate link between the face and recognition through a return to "classical" film theory, and specifically to the first generation of European and Soviet film theorists' preoccupation with the face in silent cinema. In the process, it recasts the canonical debate over cinematic specificity between Béla Balázs and Sergei Eisenstein as an antagonism between two opposing conceptions of the face in film: transparent universalism versus plastic typicality. Of these two conceptions, this project contends that the "Balázsian" idea of a transparently expressive face assumes cultural dominance in the latter half of the 20th century by virtue of its essential commensurability with the political and social ideal of mutual recognition that has come to prevail in the United States and Western Europe in the context of neoliberalism. Alongside and against this dominant tendency...

Face recognition with variation in pose angle using face graphs

Kumar, Sooraj
Fonte: Rochester Instituto de Tecnologia Publicador: Rochester Instituto de Tecnologia
Tipo: Tese de Doutorado
EN_US
Relevância na Pesquisa
36.38%
Automatic recognition of human faces is an important and growing field. Several real-world applications have started to rely on the accuracy of computer-based face recognition systems for their own performance in terms of efficiency, safety and reliability. Many algorithms have already been established in terms of frontal face recognition, where the person to be recognized is looking directly at the camera. More recently, methods for non-frontal face recognition have been proposed. These include work related to 3D rigid face models, component-based 3D morphable models, eigenfaces and elastic bunched graph matching (EBGM). This thesis extends recognition algorithm based on EBGM to establish better face recognition across pose variation. Facial features are localized using active shape models and face recognition is based on elastic bunch graph matching. Recognition is performed by comparing feature descriptors based on Gabor wavelets for various orientations and scales, called jets. Two novel recognition schemes, feature weighting and jet-mapping, are proposed for improved performance of the base scheme, and a combination of the two schemes is considered as a further enhancement. The improvements in performance have been evaluated by studying recognition rates on an existing database and comparing the results with the base recognition scheme over which the schemes have been developed. Improvement of up to 20% has been observed for face pose variation as large as 45°.

A Survey of table recognition: Models, observations, transformations, and inferences

Zanibbi, Richard; Blostein, Dorothea; Cordy, James
Fonte: Springer Berlin / Heidelberg: International Journal on Document Analysis and Recognition Publicador: Springer Berlin / Heidelberg: International Journal on Document Analysis and Recognition
Tipo: Artigo de Revista Científica
EN_US
Relevância na Pesquisa
46.21%
Table characteristics vary widely. Consequently, a great variety of computational approaches have been applied to table recognition. In this survey, the table recognition literature is presented as an interaction of table models, observations, transformations, and inferences. A table model defines the physical and logical structure of tables; the model is used to detect tables, and to analyze and decompose the detected tables. Observations perform feature measurements and data lookup, transformations alter or restructure data, and inferences generate and test hypotheses. This presentation clarifies the decisions made by a table recognizer, and the assumptions and inferencing techniques that underlie these decisions.; RIT community members may access full-text via RIT Libraries licensed databases: http://library.rit.edu/databases/

The Recognition strategy language

Zanibbi, Richard; Blostein, Dorothea; Cordy, James
Fonte: IEEE Computer Society : Eighth International Conference on Document Analysis and Recognition Publicador: IEEE Computer Society : Eighth International Conference on Document Analysis and Recognition
Tipo: Proceedings
EN_US
Relevância na Pesquisa
46.34%
The table recognition literature contains many strategies specified informally as a sequence of operations, obscuring both models of table structure and the effects of individual decisions. Decision making is more transparent in formal model-based approaches (e.g. grammar-based) but these approaches are less flexible than informal ones. We propose an intermediate level of formalization, defining strategies as a sequence of basic graph transformations that correspond to recognition operations (e.g. classification, segmentation). Transformations are parameterized by logical types and decision functions, which together define structure models and executable strategies for interpreting input graphs. We provide an overview of our first attempt at this intermediate level of formalization, the Recognition Strategy Language (RSL). As a proof-of-concept, we reimplement two informally specified table recognition strategies from the literature in RSL. The RSL implementations capture descriptions of the formerly implicit table structure models, and automatically capture all decision making.; "The Recognition Strategy Language," Eighth International Conference on Document Analysis and Recognition. Held at Seoul, South Korea: 29 August - 1 September 2005. ©2005 IEEE. Personal use of this material is permitted. However...