A kernel maximum uncertainty discriminant analysis and its application to face recognition
Nenhuma Miniatura disponível
Citações na Scopus
2
Tipo de produção
Artigo de evento
Data
2009-02-05
Autores
Carlos E. Thomaz
GIRALDI, G. A.
GIRALDI, G. A.
Orientador
Periódico
VISAPP 2009 - Proceedings of the 4th International Conference on Computer Vision Theory and Applications
Título da Revista
ISSN da Revista
Título de Volume
Citação
THOMAZ, C. E.; GIRALDI, G. A. A kernel maximum uncertainty discriminant analysis and its application to face recognition. VISAPP 2009 - Proceedings of the 4th International Conference on Computer Vision Theory and Applications, v. 1, p. 341-346, feb. 2009.
Texto completo (DOI)
Palavras-chave
Resumo
In this paper, we extend the Maximum uncertainty Linear Discriminant Analysis (MLDA), proposed recently for limited sample size problems, to its kernel version. The new Kernel Maximum uncertainty Discriminant Analysis (KMDA) is a two-stage method composed of Kernel Principal Component Analysis (KPCA) followed by the standard MLDA. In order to evaluate its effectiveness, experiments on face recognition using the well-known ORL and FERET face databases were carried out and compared with other existing kernel discriminant methods, such as Generalized Discriminant Analysis (GDA) and Regularized Kernel Discriminant Analysis (RKDA). The classification results indicate that KMDA performs as well as GDA and RKDA, with the advantage of being a straightforward stabilization approach for the within-class scatter matrix that uses higher-order features for further classification improvements.