A New Nonparametric Linear Discriminant Analysis Method Based on Marginal Information
Zhenghong Gu, Jian Jun Yang · 2009
Marginal information is of great importance for classification. This paper presents a new nonparametric linear discriminant analysis method named Push-Pull marginal discriminant analysis (PPMDA) which takes full advantage of marginal information. For two-class cases, the idea of this method is to determine projection directions such that the marginal samples of one class are pushed away from the between-class marginal samples as far as possible and simultaneously pulled to the within-class samples as close as possible. This idea can be extended for multi-class cases and gives rise to the PPMDA algorithm for feature extraction of multi-class problems. The proposed method is evaluated using the Extended Yale face database B and the ORL database. Experimental results show the effectiveness of the proposed method and its performance advantage over the state-of-art feature extraction methods.