Η ραγδαία αύξηση των εικόνων, σε συνδυασμό με την αδυναμία των συστημάτων ανάκτησης εικόνας βάσει περιεχομένου να εξάγουν σημασιολογικά χαρακτηριστικά, οδήγησαν στην εισαγωγή του ανθρώπινου παράγοντα στην πειραματική διαδικασία. Ένας πολύ συνηθισμένος και επιτυχημένος τρόπος χρησιμοποίησης του ανθρώπινου συστήματος όρασης είναι μέσω της καταγραφής των οφθαλμικών κινήσεων. Στο σύστημα ανάκτησης το οποίο προτείνεται στην παρούσα εργασία γίνεται καταγραφή των σημείων εστίασης που προέκυψαν κατά την παρατήρηση των εικόνων βάσεως. Από τα σημεία αυτά, γίνεται εξαγωγή χαρακτηριστικών υφής με δύο μεθόδους, τα φίλτρα Gabor και το διακριτό μετασχηματισμό συνημιτόνου (DCT), παράγοντας πολυδιάστατα διανύσματα. Τα διανύσματα αυτά συγκρίνονται ανά δύο μέσω του μη παραμετρικού WW test, δημιουργώντας έναν πίνακα αποστάσεων. Με την εισαγωγή μιας ζητούμενης εικόνας στο σύστημα, τα χαρακτηριστικά υφής της συγκρίνονται με αυτά της βάσης προσθέτοντας μια επιπλέον διάσταση στον πίνακα απόστασης. Η απεικόνιση της σχέσης μεταξύ όλων των εικόνων (συμπεριλαμβανομένης και της αιτούμενης) γίνεται σε ένα χάρτη τριών διαστάσεων μέσω πολυδιάστατης κλιμάκωσης (MDS αλγόριθμος). Τα αποτελέσματα τα οποία προέρχονται από τα φίλτρα Gabor παρουσιάζουν μεγαλύτερη αξιοπιστία, κάνοντας εφικτή την επέκταση του συστήματος με χρήση μίας μεγαλύτερης βάσης εικόνων. / The rapid increase of images, combined with the weakness of the Content Based Image Retrieval (CBIR) systems to extract semantic features, led to the introduction of the human factor into the experimental procedure. A very common and successful way of using the human vision system is through the record of eye movements. In the retrieval system which is proposed in the present thesis, the fixation points that arose from viewing the database images are recorded. From these points, the texture features are extracted using two methods, Gabor filters and Discrete Cosine Transform (DCT), producing multidimensional vectors. These vectors are compared through the non parametric WW test, creating a distance matrix. By producing a query image in the system, its’ texture features are compared to those of the database, adding an extra dimension to the distance matrix. The visual representation of the relation among all the images (query image included), is depicted in a three dimensional map using multidimensional scaling (MDS algorithm). The results obtained from Gabor filters are characterized by higher robustness, making the expansion of the system possible, by using a bigger image database.

L’interrogation efficace d’images en utilisant un système de recherche d’image est un problème qui a attiré l’attention de la communauté de recherche depuis une longue période. Dans le domaine médical, les images sont de plus en plus produites en grandes quantités en raison de leur intérêt croissant pour de nombreuses pratiques médicales comme le diagnostic, la rédaction de rapports et l’enseignement. Cette thèse propose un système d’annotation et recherche sémantique d’images gastroentérologiques basé sur une nouvelle ontologie des polypes qui peut être utilisée pour aider les médecins à décider comment traiter un polype. La solution proposée utilise une ontologie de polype et se base sur une adaptation des raisonnements standard des logiques de description pour permettre une construction semi-automatique de requêtes et d’annotation d’images. Une deuxième contribution de ce travail consiste dans la proposition d’une nouvelle approche pour le calcul de réponses relaxées des requêtes ontologiques basée sur une notion de distance entre un individu donné et une requête donnée. Cette distance est calculée en comptant le nombre d’opérations élémentaires à appliquer à une ABox afin de rendre un individu donné x, une réponse correcte à une requête. Ces opérations élémentaires sont l’ajout à ou la suppression d’une ABox, d’assertions sur des concepts atomiques (ou leur négation) et/ou des rôles atomiques. La thèse propose plusieurs sémantiques formelles pour la relaxation de requêtes et étudie les problèmes de décision et d’optimisation sous-jacents. / Querying efficiently images using an image retrieval system is a long standing and challenging research problem.In the medical domain, images are increasingly produced in large quantities due their increasing interests for many medical practices such as diagnosis, report writing and teaching. This thesis proposes a semantic-based gastroenterological images annotation and retrieval system based on a new polyp ontology that can be used to support physicians to decide how to deal with a polyp. The proposed solution uses a polyp ontology and rests on an adaptation of standard reasonings in description logic to enable semi automatic construction of queries and image annotation.A second contribution of this work lies in the proposition of a new approach for computing relaxed answers of ontological queries based on a notion of an edit distance of a given individual w.r.t. a given query. Such a distance is computed by counting the number of elementary operations needed to be applied to an ABox in order to make a given individual a correct answer to a given query. The considered elementary operations are adding to or removing from an ABox, assertions on atomic concept, a negation of an atomic concept or an atomic role. The thesis proposes several formal semantics for such query approximation and investigates the underlying decision and optimisation problems.

Este trabalho apresenta o estudo e implementação de um banco de conhecimentos para auxiliar o diagnóstico de lesões da mama por inspeção visual, permitindo ao médico consultas através de características pictóricas da imagem e a comparação visual entre imagem investigada e imagens previamente classificadas e suas informações clínicas. As imagens encontram-se classificadas no banco de conhecimentos segundo o padrão \"Breast imaging reporting and data systems\" (BI-RADS) do Colégio Americano de Radiologia. A seleção das imagens, informações clínicas representativas, bem como sua classificação foram realizada em conjunto com médicos radiologistas do Centro de Ciências das Imagens e Física Médica (CCIFM) da Faculdade de Medicina de Ribeirão Preto (FMRP) da Universidade de São Paulo (USP). O processo de indexação e recuperação das imagens é baseado em atributos de textura extraídos de \"Regions of interest\" (ROIs) previamente estabelecidas em mamogramas digitalizados. Para simplificar este processo, foi utilizado a Análise de Componentes Principais (PCA), que visa a redução do número de atributos de textura e as informações redundantes existentes. Os melhores resultados obtidos foram para as ROIs 139 (Precisão = 0.80), 59 (Precisão = 0.86) e um valor de 100% de acerto para a ROI 40. / This work presents the survey and implementation of a database of knowledge to aid the diagnostic of breast lesions through visual inspection, allowing the physician a seach through the characteristics of the contents of the image and the visual comparison between the analysed image and the previously classified images and its clinical information. The images are classified into the database of knowledge according to the pattern Breast Imaging Reporting and Data Systems (BI-RADS) of the American College of Radiology. The selection of the images, the representative clinical information, as well as its classification have been performed in conjunction with practictioners radiologists of the Centro de Ciências das Imagens e Física Médica (CCIFM) from Faculdade de Medicina de Ribeirão Preto (FMRP) from Universidade de São Paulo (USP). The process of indexing and retrieving the images is based on characteristic of the texture extracted from the regions of interest (ROIs) previously established through scanned mammograms. To simplify this path, the Principal Components Analysis (PCA) was used it aims the reduction of the number of features of texture and the existing redundant information. The best results obtained were to the ROIs 139 (precision = 0.80), 59 (precision = 0.86) and a value of 100% of precision for ROI 40.

Two novel contributions to Content Based Image Retrieval are presented and discussed. The first is a search engine for font recognition. The intended usage is the search in very large font databases. The input to the search engine is an image of a text line, and the output is the name of the font used when printing the text. After pre-processing and segmentation of the input image, a local approach is used, where features are calculated for individual characters. The method is based on eigenimages calculated from edge filtered character images, which enables compact feature vectors that can be computed rapidly. A system for visualizing the entire font database is also proposed. Applying geometry preserving linear- and non-linear manifold learning methods, the structure of the high-dimensional feature space is mapped to a two-dimensional representation, which can be reorganized into a grid-based display. The performance of the search engine and the visualization tool is illustrated with a large database containing more than 2700 fonts. The second contribution is the inclusion of color-based emotion-related properties in image retrieval. The color emotion metric used is derived from psychophysical experiments and uses three scales: activity, weight and heat. It was originally designed for single-color combinations and later extended to include pairs of colors. A modified approach for statistical analysis of color emotions in images, involving transformations of ordinary RGB-histograms, is used for image classification and retrieval. The methods are very fast in feature extraction, and descriptor vectors are very short. This is essential in our application where the intended use is the search in huge image databases containing millions or billions of images. The proposed method is evaluated in psychophysical experiments, using both category scaling and interval scaling. The results show that people in general perceive color emotions for multi-colored images in similar ways, and that observer judgments correlate with derived values. Both the font search engine and the emotion based retrieval system are implemented in publicly available search engines. User statistics gathered during a period of 20 respectively 14 months are presented and discussed.

Cette thèse a pour objectif de proposer un système de reconnaissance d’images utilisant des informations attentionnelles. Nous nous intéressons à la capacité d’une telle approche à améliorer la complexité en temps de calcul et en utilisation mémoire pour la reconnaissance d’objets. Dans un premier temps, nous avons proposé d’utiliser un système d’attention visuelle comme filtre pour réduire le nombre de points d’intérêt générés par les détecteurs traditionnels [Awad 12]. En utilisant l’architecture attentionnelle proposée par Perreira da Silva comme filtre [Awad 12] sur la base d’images de VOC 2005, nous avons montré qu’un filtrage de 60% des points d’intérêt (extraits par Harris-Laplace et Laplacien) ne fait diminuer que légèrement la performance d’un système de reconnaissance d’objets (différence moyenne de AUC ~ 1%) alors que le gain en complexité est important (40% de gain en vitesse de calcul et 60% en complexité). Par la suite, nous avons proposé un descripteur hybride perceptuel-texture [Awad 14] qui caractérise les informations fréquentielles de certaines caractéristiques considérées comme perceptuellement intéressantes dans le domaine de l’attention visuelle, comme la couleur, le contraste ou l’orientation. Notre descripteur a l’avantage de fournir des vecteurs de caractéristiques ayant une dimension deux fois moindre que celle des descripteurs proposés dans l’état de l’art. L’expérimentation de ce descripteur sur un système de reconnaissance d’objets (le détecteur restant SIFT), sur la base d’images de VOC 2007, a montré une légère baisse de performance (différence moyenne de précision ~5%) par rapport à l’algorithme original, basé sur SIFT mais gain de 50% en complexité. Pour aller encore plus loin, nous avons proposé une autre expérimentation permettant de tester l’efficacité globale de notre descripteur en utilisant cette fois le système d’attention visuelle comme détecteur des points d’intérêt sur la base d’images de VOC 2005. Là encore, le système n’a montré qu’une légère baisse de performance (différence moyenne de précision ~3%) alors que la complexité est réduite de manière drastique (environ 50% de gain en temps de calcul et 70% en complexité). / The main objective of this thesis is to propose a pipeline for an object recognition algorithm, near to human perception, and at the same time, address the problems of Content Based image retrieval (CBIR) algorithm complexity : query run time and memory allocation. In this context, we propose a filter based on visual attention system to select salient points according to human interests from the interest points extracted by a traditionnal interest points detectors. The test of our approach, using Perreira Da Silva’s system as filter, on VOC 2005 databases, demonstrated that we can maintain approximately the same performance of a object recognition system by selecting only 40% of interest points (extracted by Harris-Laplace and Laplacian), while having an important gain in complexity (40% gain in query-run time and 60% in complexity). Furthermore, we address the problem of high dimensionality of descriptor in object recognition system. We proposed a new hybrid texture descriptor, representing the spatial frequency of some perceptual features extracted by a visual attention system. This descriptor has the advantage of being lower dimension vs. traditional descriptors. Evaluating our descriptor with an object recognition system (interest points detectors are Harris-Laplace & Laplacian) on VOC 2007 databases showed a slightly decrease in the performance (with 5% loss in Average Precision) compared to the original system, based on SIFT descriptor (with 50% complexity gain). In addition, we evaluated our descriptor using a visual attention system as interest point detector, on VOC 2005 databases. The experiment showed a slightly decrease in performance (with 3% loss in performance), meanwhile we reduced drastically the complexity of the system (with 50% gain in run-query time and 70% in complexity).

This thesis is focused on comparing methods for similarity image retrieval. Common techniques and testing sets are introduced. The testing sets are there to measure the accuracy of the searching systems based on similarity image retrieval. Measurements are done on those models which are implemented on the basis of presented techniques. These measurements examine their results depending on the input data, used components and parameters settings, especially the impact of image resolution on the retrieval precision is examined. These results are analysed and the models are compared. Powered by TCPDF (www.tcpdf.org)

Online shopping has become an important part of people’s daily life with the rapid development of e-commerce. In some domains such as books, electronics, and CD/DVDs, online shopping has surpassed or even replaced the traditional shopping method. Compared with traditional retailing, e-commerce is information intensive. One of the key factors to succeed in e-business is how to facilitate the consumers’ approaches to discover a product. Conventionally a product search engine based on a keyword search or category browser is provided to help users find the product information they need. The general goal of a product search system is to enable users to quickly locate information of interest and to minimize users’ efforts in search and navigation. In this process human factors play a significant role. Finding product information could be a tricky task and may require an intelligent use of search engines, and a non-trivial navigation of multilayer categories. Searching for useful product information can be frustrating for many users, especially those inexperienced users. This dissertation focuses on developing a new visual product search system that effectively extracts the properties of unstructured products, and presents the possible items of attraction to users so that the users can quickly locate the ones they would be most likely interested in. We designed and developed a feature extraction algorithm that retains product color and local pattern features, and the experimental evaluation on the benchmark dataset demonstrated that it is robust against common geometric and photometric visual distortions. Besides, instead of ignoring product text information, we investigated and developed a ranking model learned via a unified probabilistic hypergraph that is capable of capturing correlations among product visual content and textual content. Moreover, we proposed and designed a fuzzy hierarchical co-clustering algorithm for the collaborative filtering product recommendation. Via this method, users can be automatically grouped into different interest communities based on their behaviors. Then, a customized recommendation can be performed according to these implicitly detected relations. In summary, the developed search system performs much better in a visual unstructured product search when compared with state-of-art approaches. With the comprehensive ranking scheme and the collaborative filtering recommendation module, the user’s overhead in locating the information of value is reduced, and the user’s experience of seeking for useful product information is optimized.

This study investigates the relationships between the use of a zoom tool, the terms they supply to describe the image, and the type of image being viewed. Participants were assigned to two groups, one with access to the tool and one without, and were asked to supply terms to describe forty images, divided into four categories: landscape, portrait, news, and cityscape. The terms provided by participants were categorized according to models proposed in earlier image studies. Findings of the study suggest that there was not a significant difference in the number of terms supplied in relation to access to the tool, but a large variety in use of the tool was demonstrated by the participants. The study shows that there are differences in the level of meaning of the terms supplied in some of the models. The type of image being viewed was related to the number of zooms and relationships between the type of image and the number of terms supplied as well as their level of meaning in the various models from previous studies exist. The results of this study provide further insight into how people think about images and how the manipulation of those images may affect the terms they assign to describe images. The inclusion of these tools in search and retrieval scenarios may affect the outcome of the process and the more collection managers know about how people interact with images will improve their ability to provide access to the growing amount of pictorial information.

Orientadores: Ricardo da Silva Torres, Hélio Pedrini / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-27T11:52:06Z (GMT). No. of bitstreams: 1 RoccaLayza_VladimirJaime_M.pdf: 7769260 bytes, checksum: a60ae46083facfc74cd79a4ab0c83c23 (MD5) Previous issue date: 2015 / Resumo: Vários sistemas de vigilância baseados no uso de múltiplas câmeras têm sido propostos recentemente. No entanto, a identificação de pessoas em sequências de vídeos obtidas por várias câmeras com vistas não sobrepostas, comumente conhecida como reidentificação de pessoas, é um problema em aberto. As razões para que este problema seja considerado desafiador referem-se principalmente às restrições nas quais o problema deve ser resolvido. Estas restrições são definidas a partir das características do cenário e dos objetos de interesse (as pessoas): primeiro, as características biométricas de pessoas não podem ser utilizadas como características discriminantes; segundo, a aparência das pessoas muda drasticamente em virtude de variações na posição, iluminação e parâmetros de câmera. Tais restrições fazem com que uma mesma pessoa possa ser observada por múltiplas câmeras como uma pessoa diferente para cada uma delas. Nesta pesquisa, busca-se investigar alternativas para a criação de sistemas de vigilância visando à reidentificação de pessoas. Foram empregadas técnicas de recuperação de imagens por conteúdo tais como descritores de imagens tradicionais e propostos recentemente, análise multiescala, e técnicas de rank aggregation. Os experimentos realizados consideram a utilização de quatro bases de dados comumente utilizadas na avaliação de sistemas de reidentificação de pessoas. Os resultados obtidos mostraram que as técnicas de recuperação de imagens por conteúdo são promissoras para a reidentificação de pessoas, obtendo resultados comparáveis aos métodos do estado da arte / Abstract: Several surveillance systems based on the use of multiple cameras have been proposed recently. However, the identification of people in video sequences obtained from several cameras with non-overlapping views, commonly known as the person reidentification problem, is still an open problem. Person reidentification is a challenging problem due to the constraints under which the problem should be solved. These constraints come from the characteristics of the scenario and the objects of interest (people): first, biometric features may not be used as discriminant information; second, appearance is dramatically modified by changes in position, lighting conditions, and camera parameters. Therefore, in these conditions a unique person can be ''seen'' as a distinct person by different cameras. This research is focused on the investigation of alternatives for the creation of surveillance systems aiming at person reidentification. We intend to use content-based image retrieval techniques, such as traditional and recently proposed image descriptors, multiscale analysis, and rank aggregation approaches. Conducted experiments considered the use of four different datasets, commonly used in the evaluation of person reidentification systems. Obtained results show that the content-based image retrieval techniques are promising to reidentify people, producing equivalent results to the state-of-the-art methods / Mestrado / Ciência da Computação / Mestre em Ciência da Computação

O aumento da geração e do intercâmbio de imagens médicas digitais tem incentivado profissionais da computação a criarem ferramentas para manipulação, armazenamento e busca por similaridade dessas imagens. As ferramentas de recuperação de imagens por conteúdo, foco desse trabalho, têm a função de auxiliar na tomada de decisão e na prática da medicina baseada em estudo de casos semelhantes. Porém, seus principais obstáculos são conseguir uma rápida recuperação de imagens armazenadas em grandes bases e reduzir o gap semântico, caracterizado pela divergência entre o resultado obtido pelo computador e aquele esperado pelo médico. No presente trabalho, uma análise das funções de distância e dos descritores computacionais de características está sendo realizada com o objetivo de encontrar uma aproximação eficiente entre os métodos de extração de características de baixo nível e os parâmetros de percepção do médico (de alto nível) envolvidos na análise de imagens. O trabalho de integração desses três elementos (Extratores de Características, Função de Distância e Parâmetro Perceptual) resultou na criação de operadores de similaridade, que podem ser utilizados para aproximar o sistema computacional ao usuário final, visto que serão recuperadas imagens de acordo com a percepção de similaridade do médico, usuário final do sistema / The continuous growth of the medical images generation and their use in the day-to-day procedures in hospitals and medical centers has motivated the computer science researchers to develop algorithms, methods and tools to store, search and retrieve images by their content. Therefore, the content-based image retrieval (CBIR) field is also growing at a very fast pace. Algorithms and tools for CBIR, which are at the core of this work, can help on the decision making process when the specialist is composing the images analysis. This is based on the fact that the specialist can retrieve similar cases to the one under evaluation. However, the main reservation about the use of CBIR is to achieve a fast and effective retrieval, in the sense that the specialist gets what is expected for. That is, the problem is to bridge the semantic gap given by the divergence among the result automatically delivered by the system and what the user is expecting. In this work it is proposed the perceptual parameter, which adds to the relationship between the feature extraction algorithms and distance functions aimed at finding the best combination to deliver to the user what he/she expected from the query. Therefore, this research integrated the three main elements of similarity queries: the image features, the distance function and the perceptual parameter, what resulted in searching operators. The experiments performed show that these operators can narrow the distance between the system and the specialist, contributing to bridge the semantic gap