Extensão do SGBD PostgreSQL para suportar recuperação de imagens por conteúdo

• Ano de defesa: 2006
• Autor(a) principal: Melo, Ernani Viriato de
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Uberlândia; BR; Programa de Pós-graduação em Ciência da Computação; Ciências Exatas e da Terra; UFU
• Palavras-chave em Português: Extratores de características; Recuperação de imagens por conteúdo; Mamografias digitais e extensão para SGBDR; Processamento de imagens - Técnicas digitais; Feature extractors; Content-based image retrieval; Digital mammograms and extension to RDBMS; CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
• Link de acesso: https://repositorio.ufu.br/handle/123456789/12532

This work presents an extension to RDBMS PostgreSQL for supporting content-based image retrieval. This extension, called PostgreSQL - IE, is independent of application, and takes advantage to be open source and portable. SQL - IE command language extension is composed by a set of functions that includes commands to create new feature extractor procedures, new feature vectors as a combination of previously defined feature extractors, and new access methods for multimedia data. SQL-IE also includes resources for defining queries by combining conventional and visual data. PostgreSQL - IE makes a new image data type available that permits associating various images to one unique attribute. This resource makes the combining of visual features from different images in the same feature vector possible. To illustrate the facilities and power of the proposed RDBMS extension, this work presents SISPRIM, a research system that supports mammographic images retrieval associated to the clinical history and data related to the style of the patient.