Fractal dimension of bag-of-visual words

Autor(es)

Ribas, Lucas Correia ^[1] ; Goncalves, Diogo Nunes ^[2] ; Silva, Jonathan de Andrade ^[2] ; de Castro, Jr., Amaury Antonio ^[2] ; Bruno, Odemir Martinez ^[3] ; Goncalves, Wesley Nunes ^[2]

Afiliação do(s) autor(es)

^[1] Univ Sao Paulo, Inst Math & Comp Sci, Ave Trabalhador Sao Carlense 400, BR-13566590 Sao Carlos, SP - Brazil

^[2] Univ Fed Mato Grosso do Sul, Rua Itibire Vieira S-N, BR-79907414 Ponta Pora, MS - Brazil

^[3] Univ Sao Paulo, Sao Carlos Inst Phys, Ave Trabalhador Sao Carlense 400, POB 369, BR-13560970 Sao Carlos, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: PATTERN ANALYSIS AND APPLICATIONS; v. 22, n. 1, p. 89-98, FEB 2019.
• Citações Web of Science: 1

Resumo

Scene recognition is an important and challenging problem in computer vision. One of the most used scene recognition methods is the bag-of-visual words. Despite the interesting results, this approach does not capture the detail richness of spatial information of the visual words on the image. In this paper, we propose a new method to describe the visual words using the fractal dimension. Our method estimates the fractal dimension of each visual word on image through box-counting method. The fractal dimension is capable of providing complex and spatial information of the visual words in a simple and efficient way. We validate our method on three well-known scene and object datasets, and the experimental results reveal that our method leads to highly discriminative features of the visual words. In addition, the proposed method has achieved competitive results compared to popular methods in scene classification. (AU)

• Processo FAPESP: 16/18809-9 - Deep learning e redes complexas aplicados em visão computacional
• Beneficiário: Odemir Martinez Bruno
• Modalidade de apoio: Auxílio à Pesquisa - Parceria para Inovação Tecnológica - PITE
• Processo FAPESP: 16/23763-8 - Modelagem e análise de redes complexas para visão computacional
• Beneficiário: Lucas Correia Ribas
• Modalidade de apoio: Bolsas no Brasil - Doutorado
• Processo FAPESP: 14/08026-1 - Visão artificial e reconhecimento de padrões aplicados em plasticidade vegetal
• Beneficiário: Odemir Martinez Bruno
• Modalidade de apoio: Auxílio à Pesquisa - Regular