Feature extraction on local jet space for texture classification

Autor(es)

da Silva Oliveira, Marcos William ^{[1, 2]} ; da Silva, Nubia Rosa ^{[1, 2]} ; Manzanera, Antoine ^[3] ; Bruno, Odernir Martinez ^{[1, 2]}

Afiliação do(s) autor(es)

^[1] Univ Sao Paulo, Inst Math & Comp Sci, USP, BR-13566590 Sao Carlos, SP - Brazil

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

^[3] Univ Paris Saclay, ENSTA ParisTech, Robot & Vis U2IS, F-91762 Palaiseau - France

• Tipo de documento: Artigo Científico
• Fonte: PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS; v. 439, p. 160-170, DEC 1 2015.
• Citações Web of Science: 7

Resumo

The proposal of this study is to analyze the texture pattern recognition over the local jet space looking forward to improve the texture characterization. Local jets decompose the image based on partial derivatives allowing the texture feature extraction be exploited in different levels of geometrical structures. Each local jet component evidences a different local pattern, such as, flat regions, directional variations and concavity or convexity. Subsequently, a texture descriptor is used to extract features from 0th, 1st and 2nd-derivative components. Four well-known databases (Brodatz, Vistex, Usptex and Outex) and four texture descriptors (Fourier descriptors, Gabor filters, Local Binary Pattern and Local Binary Pattern Variance) were used to validate the idea, showing in most cases an increase of the success rates. (C) 2015 Elsevier B.V. All rights reserved. (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
• Processo FAPESP: 11/21467-9 - Reconhecimento de padrões heterogêneos e suas aplicações em biologia e nanotecnologia
• Beneficiário: Núbia Rosa da Silva
• Linha de fomento: Bolsas no Brasil - Doutorado