Visual word spatial arrangement for image retrieval and classification

Autor(es)

Penatti, Otavio A. B. ^[1] ; Silva, Fernanda B. ^[1] ; Valle, Eduardo ^{[1, 2]} ; Gouet-Brunet, Valerie ^{[3, 4]} ; Torres, Ricardo da S. ^[1]

Afiliação do(s) autor(es)

^[1] Univ Campinas UNICAMP, Inst Comp, RECOD Lab, BR-13083852 Campinas, SP - Brazil

^[2] Univ Campinas Unicamp, Sch Elect & Comp Engn FEEC, Dept Comp Engn & Ind Automat DCA, BR-13083852 Campinas, SP - Brazil

^[3] Paris Est Univ, IGN SR, MATIS Lab, F-94160 St Mande - France

^[4] CNAM, CEDRIC Lab, F-75141 Paris 03 - France

• Tipo de documento: Artigo Científico
• Fonte: PATTERN RECOGNITION; v. 47, n. 2, p. 705-720, FEB 2014.
• Citações Web of Science: 50

Resumo

We present word spatial arrangement (WSA), an approach to represent the spatial arrangement of visual words under the bag-of-visual-words model. It lies in a simple idea which encodes the relative position of visual words by splitting the image space into quadrants using each detected point as origin. WSA generates compact feature vectors and is flexible for being used for image retrieval and classification, for working with hard or soft assignment, requiring no pre/post processing for spatial verification. Experiments in the retrieval scenario show the superiority of WSA in relation to Spatial Pyramids. Experiments in the classification scenario show a reasonable compromise between those methods, with Spatial Pyramids generating larger feature vectors, while WSA provides adequate performance with much more compact features. As WSA encodes only the spatial information of visual words and not their frequency of occurrence, the results indicate the importance of such information for visual categorization. (C) 2013 Elsevier Ltd. All rights reserved. (AU)

• Processo FAPESP: 09/05951-8 - Indexação de dados multimídia em alta dimensionalidade: aplicação à busca em bases de imagens e vídeos
• Beneficiário: Eduardo Alves Do Valle Junior
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado
• Processo FAPESP: 09/10554-8 - Explorando Dicionários Visuais em Buscas de Imagens na Web
• Beneficiário: Otávio Augusto Bizetto Penatti
• Modalidade de apoio: Bolsas no Brasil - Doutorado
• Processo FAPESP: 12/16172-2 - Uso de grafos para Codificação da Distribuição Espacial de Palavras Visuais e seu uso na Busca e Classificação de Imagens em Grandes Coleções
• Beneficiário: Fernanda Brandão Silva
• Modalidade de apoio: Bolsas no Brasil - Mestrado