国立情報学研究所で電子化したコンテンツを使用している。

This research project is a study of the role of fixation and visual attention in object recognition. In this project, we build an active vision system which can recognize a target object in a cluttered scene efficiently and reliably. Our system integrates visual cues like color and stereo to perform figure/ground separation, yielding candidate regions on which to focus attention. Within each image region, we use stereo to extract features that lie within a narrow disparity range about the fixation position. These selected features are then used as input to an alignment-style recognition system. We show that visual attention and fixation significantly reduce the complexity and the false identifications in model-based recognition using Alignment methods. We also demonstrate that stereo can be used effectively as a figure/ground separator without the need for accurate camera calibration.

O romance The Recognitions (Os Reconhecimentos) do escritor norte-americano William Gaddis é um texto auto—reflexivo que retrata a trajetória de Wyatt Gwyon da infância à maturidade, na medida em que ele rejeita e busca a originalidade. O presente trabalho analisa The Recognitions enfocando a problematização dos conceitos de originalidade e autoria propostos pelo romance através de debates sobre a falsificação e o plágio, que remetem a duas noções maiores e mais importantes: autoria e originalidade. O romance questiona a presente demanda por originalidade e discute a possibilidade de ser original. Ele formula uma estética baseada em reconhecimentos que é defendida no romance e usada pelo autor na tessitura do texto. A fim de atingir seus objetivos, este trabalho apresenta os diferentes conceitos associados aos termos originalidade e original, assim como alguns das principais violações relacionadas a eles na sociedade contemporânea. Também oferece um histórico do desenvolvimento dos conceitos de originalidade e autoria na sociedade ocidental, mostrando a crescente importância da figura do autor e o desenvolvimento paralelo dos conceitos de plágio e direito autoral. Os capítulos seguintes dedicam-se a tentar fornecer um relato do romance enfocando os principais personagens, todos artistas, e também uma análise do romance à luz do background histórico e teórico apresentado nos dois primeiros capítulos. O primeiro desses capítulos de análise enfoca a trajetória de Wyatt e suas concepções artísticas. O segundo os reflexos de Wyatt na narrativa, que reforçam a estrutura auto-reflexiva do romance. E o terceiro exemplifica e analisa a estética de Wyatt baseada na noção de reconhecimento, que nada mais é do que a própria estética usada por Gaddis na composição de sua ficção. / William Gaddis’s The Recognitions (1955) is a selfreflexive novel that portrays Wyatt Gwyon’s trajectory from childhood to maturity, as he rejects and searches for originality. The present work bestows an analysis of William Gaddis’s The Recognitions focusing on the problematization of originality and authorship proposed by the novel by means of the central issues of forgery and plagiarism, which bring with them two larger and more important sister-notions: authorship and originality. The novel questions the prevailing demand for originality and discusses the possibility of being original. It formulates an aesthetics of recognitions defended in the novel and used by the author in the making of this text. In order to do that, this work provides a view on the different concepts associated with the terms originality and original, as well as some of the main infringements related to them in contemporary society. It also offers an account of the development of the concepts of originality and authorship in Western society, showing the growing importance of the figure of the author and the parallel development of the concepts of plagiarism and copyright. The next three chapters are dedicated to attempt to provide an account of William Gaddis’s The Recognitions focusing on the main artist characters and an analysis of the novel in the light of the theoretical and historical background provided. The first of these chapters focuses on Wyatt’s trajectory and his visions of art. The second identifies and analyses Wyatt’s mirrors in the narrative, which reinforce the self-reflective structure of the novel. And the third chapter exemplifies and analyses Wyatt’s aesthetics of recognitions, which turns out to be Gaddis’s own aesthetics in the making of his fiction.

O romance The Recognitions (Os Reconhecimentos) do escritor norte-americano William Gaddis é um texto auto—reflexivo que retrata a trajetória de Wyatt Gwyon da infância à maturidade, na medida em que ele rejeita e busca a originalidade. O presente trabalho analisa The Recognitions enfocando a problematização dos conceitos de originalidade e autoria propostos pelo romance através de debates sobre a falsificação e o plágio, que remetem a duas noções maiores e mais importantes: autoria e originalidade. O romance questiona a presente demanda por originalidade e discute a possibilidade de ser original. Ele formula uma estética baseada em reconhecimentos que é defendida no romance e usada pelo autor na tessitura do texto. A fim de atingir seus objetivos, este trabalho apresenta os diferentes conceitos associados aos termos originalidade e original, assim como alguns das principais violações relacionadas a eles na sociedade contemporânea. Também oferece um histórico do desenvolvimento dos conceitos de originalidade e autoria na sociedade ocidental, mostrando a crescente importância da figura do autor e o desenvolvimento paralelo dos conceitos de plágio e direito autoral. Os capítulos seguintes dedicam-se a tentar fornecer um relato do romance enfocando os principais personagens, todos artistas, e também uma análise do romance à luz do background histórico e teórico apresentado nos dois primeiros capítulos. O primeiro desses capítulos de análise enfoca a trajetória de Wyatt e suas concepções artísticas. O segundo os reflexos de Wyatt na narrativa, que reforçam a estrutura auto-reflexiva do romance. E o terceiro exemplifica e analisa a estética de Wyatt baseada na noção de reconhecimento, que nada mais é do que a própria estética usada por Gaddis na composição de sua ficção. / William Gaddis’s The Recognitions (1955) is a selfreflexive novel that portrays Wyatt Gwyon’s trajectory from childhood to maturity, as he rejects and searches for originality. The present work bestows an analysis of William Gaddis’s The Recognitions focusing on the problematization of originality and authorship proposed by the novel by means of the central issues of forgery and plagiarism, which bring with them two larger and more important sister-notions: authorship and originality. The novel questions the prevailing demand for originality and discusses the possibility of being original. It formulates an aesthetics of recognitions defended in the novel and used by the author in the making of this text. In order to do that, this work provides a view on the different concepts associated with the terms originality and original, as well as some of the main infringements related to them in contemporary society. It also offers an account of the development of the concepts of originality and authorship in Western society, showing the growing importance of the figure of the author and the parallel development of the concepts of plagiarism and copyright. The next three chapters are dedicated to attempt to provide an account of William Gaddis’s The Recognitions focusing on the main artist characters and an analysis of the novel in the light of the theoretical and historical background provided. The first of these chapters focuses on Wyatt’s trajectory and his visions of art. The second identifies and analyses Wyatt’s mirrors in the narrative, which reinforce the self-reflective structure of the novel. And the third chapter exemplifies and analyses Wyatt’s aesthetics of recognitions, which turns out to be Gaddis’s own aesthetics in the making of his fiction.

O romance The Recognitions (Os Reconhecimentos) do escritor norte-americano William Gaddis é um texto auto—reflexivo que retrata a trajetória de Wyatt Gwyon da infância à maturidade, na medida em que ele rejeita e busca a originalidade. O presente trabalho analisa The Recognitions enfocando a problematização dos conceitos de originalidade e autoria propostos pelo romance através de debates sobre a falsificação e o plágio, que remetem a duas noções maiores e mais importantes: autoria e originalidade. O romance questiona a presente demanda por originalidade e discute a possibilidade de ser original. Ele formula uma estética baseada em reconhecimentos que é defendida no romance e usada pelo autor na tessitura do texto. A fim de atingir seus objetivos, este trabalho apresenta os diferentes conceitos associados aos termos originalidade e original, assim como alguns das principais violações relacionadas a eles na sociedade contemporânea. Também oferece um histórico do desenvolvimento dos conceitos de originalidade e autoria na sociedade ocidental, mostrando a crescente importância da figura do autor e o desenvolvimento paralelo dos conceitos de plágio e direito autoral. Os capítulos seguintes dedicam-se a tentar fornecer um relato do romance enfocando os principais personagens, todos artistas, e também uma análise do romance à luz do background histórico e teórico apresentado nos dois primeiros capítulos. O primeiro desses capítulos de análise enfoca a trajetória de Wyatt e suas concepções artísticas. O segundo os reflexos de Wyatt na narrativa, que reforçam a estrutura auto-reflexiva do romance. E o terceiro exemplifica e analisa a estética de Wyatt baseada na noção de reconhecimento, que nada mais é do que a própria estética usada por Gaddis na composição de sua ficção. / William Gaddis’s The Recognitions (1955) is a selfreflexive novel that portrays Wyatt Gwyon’s trajectory from childhood to maturity, as he rejects and searches for originality. The present work bestows an analysis of William Gaddis’s The Recognitions focusing on the problematization of originality and authorship proposed by the novel by means of the central issues of forgery and plagiarism, which bring with them two larger and more important sister-notions: authorship and originality. The novel questions the prevailing demand for originality and discusses the possibility of being original. It formulates an aesthetics of recognitions defended in the novel and used by the author in the making of this text. In order to do that, this work provides a view on the different concepts associated with the terms originality and original, as well as some of the main infringements related to them in contemporary society. It also offers an account of the development of the concepts of originality and authorship in Western society, showing the growing importance of the figure of the author and the parallel development of the concepts of plagiarism and copyright. The next three chapters are dedicated to attempt to provide an account of William Gaddis’s The Recognitions focusing on the main artist characters and an analysis of the novel in the light of the theoretical and historical background provided. The first of these chapters focuses on Wyatt’s trajectory and his visions of art. The second identifies and analyses Wyatt’s mirrors in the narrative, which reinforce the self-reflective structure of the novel. And the third chapter exemplifies and analyses Wyatt’s aesthetics of recognitions, which turns out to be Gaddis’s own aesthetics in the making of his fiction.

[pt] Identificar um indivíduo a partir de uma imagem de face é uma tarefa simples para seres humanos e extremamente difícil para a Visão Computacional. Esta questão tem motivado diversos grupos de pesquisa em todo o mundo, especialmente a partir de 1993. Inúmeros trabalhos realizados até o momento encaram uma imagem digital de n pixels como um vetor num espaço n-dimensional, onde n é em geral muito grande. Imagens de rostos humanos possuem, contudo, grande redundância: todas contém dois olhos, um nariz, uma boca, e etc. É possível, portanto, trabalhar em uma base deste espaço em que faces possam ser adequadamente caracterizadas a partir de um conjunto de p componentes, onde p é muito menor quen. É com este enfoque que o presente trabalho estuda sistemas de reconhecimento de faces que consistem de um estágio de redução de dimensionalidade, realizado pela técnica de Análise de Componentes Principais (PCA), seguido de um modelo classificador. No estágio da PCA, as imagens de n pixels são transformadas em vetores de p características a partir de um conjunto de treinamento. Três classificadores conhecidos na literatura são estudados: os classificadores de distância (EUclideana e de Mahalanobis), a rede neural de Funções Base Radiais (RBF), e o classificador de Fisher. Este trabalho propõe, ainda, um novo classificador que introduz o conceito de Matrizes de Covariança Misturadas (MPM) no classificador gaussiano de Máxima Probabilidade. Os quatros classificadores são avaliados através da variação de seus respectivos parâmetros e utilizam como imagens o banco de faces da Olivetti. Nos experimentos realizados para comparar tais abordagens, o novo classificador proposto atingiu as maiores taxas de reconhecimento e apresentou menorsensibilidade à escolha do conjunto de faces de treinamento. / [en] Identifying an individual based on a face image is a simple task for humans to perform and a very difficult one for Vision Computing. Since 1993, several research groups in all over the world have been studied this problem. Most of the methods proposed for recognizing the identity of an individual represent a n intensity pixel image as a n- dimensional vector, when, in general, n is a very large number value. Face images are highly redundant, since every individual has two eyes, one nose, one mouth and so on. Then, instead of using n intensity values, it is generally possible to characterize an image instance by a set of p features, for p < < n. This work studies face recognition systems consisting of a PCA stage for dimensionality reduction followed by a classifier. The PCA stage takes the n-pixels face images and produces the corresponding p most expensive features, based on the whole available training set. Three classifiers proposed in the literature are studied: the Euclidean and Mahalanobis distances, the RBF neural network, and the Fisher classifier. This work also proposes a new classifier, which introduces the concept of Mixture Covariance Matrices (MPM) in the Minimum Total Probality of Misclassification rule for normal populations. The four classifiers are evaluated using the Olivetti Face Database varying their parameters in a wide range. In the experiments carried out to compare those approaches the new proposed classifier reached the best recognition rates and showed to be less sensitive to the choice of the training set.

Coherent Raman microscopy (CRM) is a powerful nonlinear optical imaging technique based on contrast via Raman active molecular vibrations. CRM has been used in domains ranging from biology to medicine to geology in order to provide quick, sensitive, chemical-specific, and label-free 3D sectioning of samples. The Raman contrast is usually obtained by combining two ultrashort pulse input beams, known as Pump and Stokes, whose frequency difference is adjusted to the Raman vibrational frequency of interest. CRM can be used in conjunction with other imaging modalities such as second harmonic generation, fluorescence, and third harmonic generation microscopy, resulting in a multimodal imaging technique that can capture a massive amount of data. Two fundamental elements are crucial in CRM. First, a laser source which is broadband, stable, rapidly tunable, and low in noise. Second, a strategy for image analysis that can handle denoising and material classification issues in the relatively large datasets obtained by CRM techniques. Stimulated Raman Scattering (SRS) microscopy is a subset of CRM techniques, and this thesis is devoted entirely to it. Although Raman imaging based on a single vibrational resonance can be useful, non-resonant background signals and overlapping bands in SRS can impair contrast and chemical specificity. Tuning over the Raman spectrum is therefore crucial for target identification, which necessitates the use of a broadband and easily tunable laser source. Although supercontinuum generation in a nonlinear fibre could provide extended tunability, it is typically not viable for some CRM techniques, specifically in SRS microscopy. Signal acquisition schemes in SRS microscopy are focused primarily on detecting a tiny modulation transfer between the Pump and Stokes input laser beams. As a result, very low noise source is required. The primary and most important component in hyperspectral SRS microscopy is a low-noise broadband laser source. The second problem in SRS microscopy is poor signal-to-noise (SNR) ratios in some situations, which can be caused by low target-molecule concentrations in the sample and/or scattering losses in deep-tissue imaging, as examples. Furthermore, in some SRS imaging applications (e.g., in vivo), fast imaging, low input laser power or short integration time is required to prevent sample photodamage, typically resulting in low contrast (low SNR) images. Low SNR images also typically suffer from poorly resolved spectral features. Various de-noising techniques have been used to date in image improvement. However, to enable averaging, these often require either previous knowledge of the noise source or numerous images of the same field of view (under better observing conditions), which may result in the image having lower spatial-spectral resolution. Sample segmentation or converting a 2D hyperspectral image to a chemical concentration map, is also a critical issue in SRS microscopy. Raman vibrational bands in heterogeneous samples are likely to overlap, necessitating the use of chemometrics to separate and segment them. We will address the aforementioned issues in SRS microscopy in this thesis. To begin, we demonstrate that a supercontinuum light source based on all normal dispersion (ANDi) fibres generates a stable broadband output with very low incremental source noise. The ANDi fibre output's noise power spectral density was evaluated, and its applicability in hyperspectral SRS microscopy applications was shown. This demonstrates the potential of ANDi fibre sources for broadband SRS imaging as well as their ease of implementation. Second, we demonstrate a deep learning neural net model and unsupervised machine-learning algorithm for rapid and automated de-noising and segmentation of SRS images based on a ten-layer convolutional autoencoder: UHRED (Unsupervised Hyperspectral Resolution Enhancement and De-noising). UHRED is trained in an unsupervised manner using only a single (“one-shot”) hyperspectral image, with no requirements for training on high quality (ground truth) labelled data sets or images.

[pt] A quantidade de vídeos gravados no mundo cresce muito, não somente devido aos interesses e hábitos humanos em relação a esse tipo de mídia, mas também pela diversidade de dispositivos utilizados para criação de vídeos. No entanto, faltam informações sobre conteúdos em vídeo porque a geração de metadados é complexa e requer muito tempo para ser executado por humanos. Do ponto de vista da tecnologia, não é fácil superar os obstáculos relacionados à grande quantidade e diversidade de frames de vídeo. O trabalho propõe um sistema automatizado de reconhecimento facial para detectar personagens em vídeos. Ele foi desenvolvido para reconhecer personagens, a fim de aumentar os metadados de vídeo. Ele combina técnicas padrão de visão computacional para melhorar a precisão, processando os dados de saída dos modelos existentes de maneira complementar. O modelo teve um desempenho satisfatório usando um conjunto de dados da vida real de uma grande empresa de mídia. / [en] The amount of recorded video in the world is increasing a lot due not only to the humans interests and habits regarding this kind of media, but also the diversity of devices used to create them. However, there is a lack of information about video content because generating video meta-data is complex. It demands too much time to be performed by humans, and from the technology perspective, it is not easy to overcome obstacles regarding the huge amount and diversity of video frames. In this work we propose an automated face recognition system to detect and recognize humans within videos. It was developed to recognize characters,in order to increase video meta-data. It combines standard computer vision techniques to improved accuracy by processing existing models output data in a complementary manner. We evaluated the performance of the system in a real data set from a large media company.

[pt] Esta dissertação propõe e avalia estratégias baseadas nos Stacked Supervised Auto-encoders (SSAE) para representação de imagens faciais em aplicações de vídeo vigilância. O estudo foca na identificação de faces a partir de uma amostra por pessoa na galeria (single sample per person - SSPP). Variações em termos de pose, expressão facial, iluminação e oclusão são abordadas de duas formas. Primeiro, o SSAE extrai atributos das imagens de faces que são robustos contra tais variações. Segundo, exploram-se as múltiplas amostras que podem ser coletadas nas sequências de vídeo de uma pessoa (multiple samples per person probe - MSPPP). Os métodos propostos foram avaliados e comparados usando os bancos de vídeos Honda/UCSD e VIDTIMIT. Adicionalmente, foi estudada a influência de parâmetros relacionados com a arquitetura do SSAE utilizando o banco de imagens estáticas Extended Yale B. Os resultados demonstraram que as estratégias que exploram as MSPPP em combinação com o SSAE podem superar o desempenho de outros métodos SSPP, como os Padrões Binários Locais (LBP), para reconhecimento de faces em vídeos. / [en] This work proposes and evaluates strategies based on Stacked Supervised Auto-encoders (SSAE) for face representation in video surveillance applications. The study focuses on the identification task with a single sample per person (SSPP) in the gallery. Variations in terms of pose, facial expression, illumination and occlusion are approached in two ways. First, the SSAE extracts features from face images, which are robust to such variations. Second, multiple samples per persons probes (MSPPP) that can be extracted from video sequences are exploited to improve recognition accuracy. The proposed methods were compared upon Honda/UCSD and VIDTIMIT video datasets. Additionally, the influence of the parameters related to SSAE architecture was studied using the Extended Yale B dataset. The experimental results demonstrated that strategies combining SSAE and MSPPP are able to outperform other SSPP methods, such as local binary patterns, in face recognition from video.

Žmonių mobilumui augant jiems tenka dirbti įvairiose aplinkose. Naudojama šnekos signalų atpažinimo įranga net ir skirtingose aplinkose turi užtikrinti tam tikro lygio signalų atpažinimo kokybę, tikslumą. Besiskiriančios aplinkų savybės gali sukelti nepriimtinus atpažinimo rezultatus. Darbo tikslas – išanalizuoti akustinių signalų atpažinimo įrenginio galimybes prisitaikyti prie kintančių aplinkos sąlygų bei pasiūlyti konstruktyvią prisitaikymo prie pakitusių aplinkos sąlygų metodiką. Darbe aprašomas akustinių signalų atpažintuvų prisitaikymo prie kintančių akustinių erdvių teorinis modelis. Pristatomos uždarų aplinkų akustinių savybių, įtakojančių akustinių signalų atpažinimą, vertinimo priemonės. Pateikiamas originalus akustinių aplinkų pasikeitimo momentų atpažinimo metodas, grindžiamas akustinių signalų atpažintuvų generuojamų signalų panaudojimu. Nustačius akustinių aplinkos savybių pasikeitimo momentą, pateikiami konstruktyvūs metodai akustinių signalų atpažinimo įrenginiui prisitaikyti atpažinti naujomis akustinėmis savybėmis pasižyminčioje aplinkoje generuojamus akustinius signalus. Aprašoma sukurta eksperimentinė sistema, kurios pagalba galima tirti įvairias akustinių signalų atpažinimo situacijas, prisitaikant prie pakitusių akustinių aplinkų savybių. Pateikiami atliktų eksperimentinių tyrimų rezultatai. / Due to the natural increase in everyday mobility, people face various work environments. The speech signal recognition system analysed, thus, has to ensure quality and accuracy in recognizing signals of certain level, even in different environments. Variation in environment qualities can bring unacceptable recognition results. The aim of the thesis is to analyse the potential of the acoustic signal recognition device to adjust to d environment conditions, and to propose a constructive methodology of adjusting to the changed environment conditions. A theoretical model of acoustic signal recognizers’ adjustment to changing acoustic environments is described in the work. Also, tools for evaluating enclosed environment acoustic characteristics that have an impact on acoustic signal recognition are presented. An original method of the shift in acoustic environments momenta is as well given in the work; the method is based on employing signals generated by the acoustic signals recognizers. Once the momentum of change in the acoustic environment characteristics is determined, effective methods for acoustic signal recognizer’s adaptation to recognizing acoustic signals in the environment possessing new acoustic characteristics are issued. The developed experimental system allowing exploration of various acoustic signal recognition situations by adapting to the changed acoustic environment characteristics is described. Results of the experimental investigations conducted are provided... [to full text]