Técnicas de visualização para sistemas de recuperação de imagens por conteúdo / Visualization techniques for content-based image retrieval

AUTOR(ES)
DATA DE PUBLICAÇÃO

2010

RESUMO

A Content-Based Image Retrieval (CBIR) system offers mechanisms needed to search and retrieve images based on visual properties such as color, texture, shape, etc. In an image search process, the presentation of results is an essential component as the retrieval of relevant images is the reason of the system existence. Consequently, the use of appropriate visualization techniques may determine the success of a CBIR system. Visualization techniques are valuable tools for the exploration of a great quantity of data, such as images collections. However, techniques for visualizing images in CBIR systems have been poorly explored. This work presents a comparative study of several visualization techniques for CBIR systems. As a result of this study, several original techniques were proposed trying to fulfill some of the absent characteristics in existing methods, such as the central-based focus and the use of clustering approaches to represent the intrinsic similarity between retrieved images. Experimental results show that the proposed methods overcome other visualization strategies by considering several criteria such as adaptation to show CBIR results, information load, user satisfaction, etc. The main contributions of this work are: (i) comparative study and analysis of seven visualization techniques, four of them from the literature and three new ones; (ii) validation of two techniques never evaluated before: concentric rings and spiral; (iii) specification and implementation of three new techniques of visualization based on clustering; (iv) specification and implementation of a framework for developing new visual structures for content-based image retrieval systems. The studied techniques were implemented by using this framework

ASSUNTO(S)

image visualização - técnicas imagens - recuperação recuperação da informação visualização de informação visualization information retrieval information visualization

Documentos Relacionados