A Bayesian approach for object classification based on clusters of SIFT local features

Several methods have been presented in the literature that successfully used SIFT features for object identification, as they are reasonably invariant to translation, rotation, scale, illumination and partial occlusion. However, they have poor performance for classification tasks. In this work, SIFT f...

ver descrição completa

Detalhes bibliográficos
Autores: Leonardo Chang Fernández, Luis Enrique Sucar Succar, Eduardo Francisco Morales Manzanares
Formato: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2012
País:México
Recursos:Instituto Nacional de Astrofísica, Óptica y Electrónica
Repositorio:Repositorio Institucional del INAOE
Idioma:inglés
OAI Identifier:oai:inaoe.repositorioinstitucional.mx:1009/2079
Acesso em linha:http://inaoe.repositorioinstitucional.mx/jspui/handle/1009/2079
Access Level:acceso abierto
Palavra-chave:info:eu-repo/classification/Object class recognition/Object class recognition
info:eu-repo/classification/Local features/Local features
info:eu-repo/classification/SIFT/SIFT
info:eu-repo/classification/Clustering/Clustering
info:eu-repo/classification/Bayesian networks/Bayesian networks
info:eu-repo/classification/cti/1
info:eu-repo/classification/cti/12
info:eu-repo/classification/cti/1203
Descrição
Resumo:Several methods have been presented in the literature that successfully used SIFT features for object identification, as they are reasonably invariant to translation, rotation, scale, illumination and partial occlusion. However, they have poor performance for classification tasks. In this work, SIFT features are used to solve object class recognition problems in images using a two-step process. In its first step, the proposed method performs clustering on the extracted features in order to characterize the appearance of the different classes. Then, in the classification step, it uses a three layer Bayesian network for object class recognition. Experiments show quantitatively that clusters of SIFT features are suitable to represent classes of objects. The main contributions of this paper are the introduction of a Bayesian network approach in the classification step to improve performance in an object class recognition task, and a detailed experimentation that shows robustness to changes in illumination, scale, rotation and partial occlusion.