O objetivo desse trabalho é apresentar as características de um Sistema de Apoio ao Diagnóstico em Sistema Hospitalar Suportando Busca por Imagens Similares, a ser desenvolvido e implantado no Hospital das Clínicas de Ribeirão Preto. A recuperação de imagens baseada no conteúdo é uma área de pesquisa que tem evoluído bastante nos últimos anos. Assim, um sistema de busca e obtenção de imagens, utilizando tal técnica, deve ser extensível aos novos algoritmos de extração de características e métodos de indexação. A extração de características de imagens, tais como informações de cor, textura, forma e o relacionamento entre elas são utilizadas para descrever o conteúdo das imagens. Essas características são então utilizadas para indexar e possibilitar a comparação de imagens no processo de recuperação. O sistema proposto utilizará um método de indexação de dados recém-desenvolvido – a Slim-tree – para indexar as características extraídas das imagens. Através desse método o Sistema de Apoio ao Diagnóstico possibilitará a consulta por conteúdo em imagens médicas. / This works presents the main characteristics of a diagnosis support system based on image similarity search for medical applications. This system was developed to be used in the Clinical Hospital of Ribeirao Preto of the University of Sao Paulo. The content-based image retrieval (CBIR) researching area has evolved greatly in the last years. Thus, a CBIR system should be able to incorporate the new techniques developed, such as, new feature extraction algorithms and indexing methods among others. Traditionally, the main features extracted from images to get the image essence are color, texture, shape and the relationship among them. Therefore, such features describe the images under analysis, and are used to index and to compare images during the content-based retrieval process. The proposed system takes advantage of a new metric access method - the Slim-tree, which allows the indexing and the retrieval of the images through their extracted features.

Content-based retrieval of multimedia data has been still an active research area. The efficient retrieval of video data is proven a difficult task for content-based video retrieval systems. In this thesis study, a Content-Based Video Retrieval (CBVR) system that adapts two different index structures, namely Slim-Tree and BitMatrix, for efficiently retrieving videos based on low-level features such as color, texture, shape and motion is presented. The system represents low-level features of video data with MPEG-7 Descriptors extracted from video shots by using MPEG-7 reference software and stored in a native XML database. The low-level descriptors used in the study are Color Layout (CL), Dominant Color (DC), Edge Histogram (EH), Region Shape (RS) and Motion Activity (MA). Ordered Weighted Averaging (OWA) operator in Slim-Tree and BitMatrix aggregates these features to find final similarity between any two objects. The system supports three different types of queries: exact match queries, k-NN queries and range queries. The experiments included in this study are in terms of index construction, index update, query response time and retrieval efficiency using ANMRR performance metric and precision/recall scores. The experimental results show that using BitMatrix along with Ordered Weighted Averaging method is superior in content-based video retrieval systems.

Content-based retrieval of multimedia data has been still an active research area. The efficient retrieval of video data is proven a difficult task for content-based video retrieval systems. In this thesis study, a Content-Based Video Retrieval (CBVR) system that adapts two different index structures, namely Slim-Tree and BitMatrix, for efficiently retrieving videos based on low-level features such as color, texture, shape and motion is presented. The system represents low-level features of video data with MPEG-7 Descriptors extracted from video shots by using MPEG-7 reference software and stored in a native XML database. The low-level descriptors used in the study are Color Layout (CL), Dominant Color (DC), Edge Histogram (EH), Region Shape (RS) and Motion Activity (MA). Ordered Weighted Averaging (OWA) operator in Slim-Tree and BitMatrix aggregates these features to find final similarity between any two objects. The system supports three different types of queries: exact match queries, k-NN queries and range queries. The experiments included in this study are in terms of index construction, index update, query response time and retrieval efficiency using ANMRR performance metric and precision/recall scores. The experimental results show that using BitMatrix along with Ordered Weighted Averaging method is superior in content-based video retrieval systems.

O objetivo desse trabalho é apresentar as características de um Sistema de Apoio ao Diagnóstico em Sistema Hospitalar Suportando Busca por Imagens Similares, a ser desenvolvido e implantado no Hospital das Clínicas de Ribeirão Preto. A recuperação de imagens baseada no conteúdo é uma área de pesquisa que tem evoluído bastante nos últimos anos. Assim, um sistema de busca e obtenção de imagens, utilizando tal técnica, deve ser extensível aos novos algoritmos de extração de características e métodos de indexação. A extração de características de imagens, tais como informações de cor, textura, forma e o relacionamento entre elas são utilizadas para descrever o conteúdo das imagens. Essas características são então utilizadas para indexar e possibilitar a comparação de imagens no processo de recuperação. O sistema proposto utilizará um método de indexação de dados recém-desenvolvido – a Slim-tree – para indexar as características extraídas das imagens. Através desse método o Sistema de Apoio ao Diagnóstico possibilitará a consulta por conteúdo em imagens médicas. / This works presents the main characteristics of a diagnosis support system based on image similarity search for medical applications. This system was developed to be used in the Clinical Hospital of Ribeirao Preto of the University of Sao Paulo. The content-based image retrieval (CBIR) researching area has evolved greatly in the last years. Thus, a CBIR system should be able to incorporate the new techniques developed, such as, new feature extraction algorithms and indexing methods among others. Traditionally, the main features extracted from images to get the image essence are color, texture, shape and the relationship among them. Therefore, such features describe the images under analysis, and are used to index and to compare images during the content-based retrieval process. The proposed system takes advantage of a new metric access method - the Slim-tree, which allows the indexing and the retrieval of the images through their extracted features.