Medical image retrieval and analysis by Markov random fields and multi-scale fractal dimension

Autor(es)

Backes, Andre Ricardo ^[1] ; Gerhardinger, Leandro Cavaleri ^[2] ; Santo Batista Neto, Joao do Espirito ^[2] ; Bruno, Odemir Martinez ^[3]

Afiliação do(s) autor(es)

^[1] Univ Fed Uberlandia, Dept Comp Sci, BR-38408100 Uberlandia, MG - Brazil

^[2] Univ Sao Paulo, Inst Math & Comp Sci, BR-13566590 Sao Carlos, SP - Brazil

^[3] Univ Sao Paulo, Sci Comp Grp, Sao Carlos Inst Phys, BR-13560970 Sao Carlos, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: Physics in Medicine and Biology; v. 60, n. 3, p. 1125-1139, FEB 7 2015.
• Citações Web of Science: 3

Resumo

Many Content-based Image Retrieval (CBIR) systems and image analysis tools employ color, shape and texture (in a combined fashion or not) as attributes, or signatures, to retrieve images from databases or to perform image analysis in general. Among these attributes, texture has turned out to be the most relevant, as it allows the identification of a larger number of images of a different nature. This paper introduces a novel signature which can be used for image analysis and retrieval. It combines texture with complexity extracted from objects within the images. The approach consists of a texture segmentation step, modeled as a Markov Random Field process, followed by the estimation of the complexity of each computed region. The complexity is given by a Multi-scale Fractal Dimension. Experiments have been conducted using an MRI database in both pattern recognition and image retrieval contexts. The results show the accuracy of the proposed method in comparison with other traditional texture descriptors and also indicate how the performance changes as the level of complexity is altered. (AU)

• Processo FAPESP: 11/01523-1 - Métodos de visão computacional aplicados à identificação e análise de plantas
• Beneficiário: Odemir Martinez Bruno
• Linha de fomento: Auxílio à Pesquisa - Regular