Abstract Many linear discriminant analysis (LDA) and kernel Fisher discriminant analysis (KFD) methods are based on the restrictive assumption that the data are homoscedastic. In this paper, we propose a new KFD method called heteroscedastic kernel weighted discriminant analysis (HKWDA) which has several appealing characteristics. First, like all kernel methods, it can handle nonlinearity efficiently in a disciplined manner. Second, by incorporating a weighting function that can capture heteroscedastic data distributions into the discriminant criterion, it can work under more realistic situations and hence can further enhance the classification accuracy in many real-world applications. Moreover, it can effectively deal with the small sample size problem. We have performed some face recognition experiments to compare HKWDA with several linear and nonlinear dimensionality reduction methods, showing that HKWDA consistently gives the best results.


    Access

    Download


    Export, share and cite



    Title :

    Extending Kernel Fisher Discriminant Analysis with the Weighted Pairwise Chernoff Criterion


    Contributors:
    Dai, Guang (author) / Yeung, Dit-Yan (author) / Chang, Hong (author)


    Publication date :

    2006-01-01


    Size :

    13 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Extending Kernel Fisher Discriminant Analysis with the Weighted Pairwise Chernoff Criterion

    Dai, G. / Yeung, D.-Y. / Chang, H. | British Library Conference Proceedings | 2006


    Fisher+Kernel criterion for discriminant analysis

    Shu Yang, / Shuicheng Yan, / Dong Xu, et al. | IEEE | 2005


    Ship target recognition using kernel Fisher discriminant [4554-26]

    Li, Y. / Bai, B. / Jiao, L. et al. | British Library Conference Proceedings | 2001



    Image Interpolation using Texture Orientation Map and Kernel Fisher Discriminant

    Wu, X. / Zhang, X. | British Library Conference Proceedings | 2005