Pattern Recognition, International Conference on (2010)
Aug. 23, 2010 to Aug. 26, 2010
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICPR.2010.178
In this paper, a kernel uncorrelated adjacent-class discriminant analysis (KUADA) approach is proposed for image recognition. The optimal nonlinear discriminant vector obtained by this approach can differentiate one class and its adjacent classes, i.e., its nearest neighbor classes, by constructing the specific between-class and within-class scatter matrices in kernel space using the Fisher criterion. In this manner, KUADA acquires all discriminant vectors class by class. Furthermore, KUADA makes every discriminant vector satisfy locally statistical uncorrelated constraints by using the corresponding class and part of its most adjacent classes. Experimental results on the public AR and CAS-PEAL face databases demonstrate that the proposed approach outperforms several representative nonlinear discriminant methods.
adjacent classes, locally statistical uncorrelated constraints, kernel uncorrelated adjacent-class discriminant analysis (KUADA)
Y. Yao, J. Yang, S. Li, X. Jing and L. Bian, "Kernel Uncorrelated Adjacent-class Discriminant Analysis," 2010 20th International Conference on Pattern Recognition (ICPR 2010)(ICPR), Istanbul, 2010, pp. 706-709.