Weighted maximum scatter difference based feature extraction and its application to face recognition

Abstract

An improved maximum scatter difference (MSD) algorithm based on weighted scheme is proposed in this paper. The existing MSD model and its improved method only highlight the role which within-class scatter matrix plays while they pay little attention to the action of between-class scatter matrix. Another weakness of the existing MSD model is that it is difficult to select an appropriate weight for within-class scatter matrix because the range of weight is usually too large. In order to make MSD more suitable for classification, different weights are assigned to both between-class and within-class scatter matrices, respectively. This scheme is more convenient for operation than original MSD because it confines the range of parameters to a small range. Finally, the results of experiments conducted on AR and FERET face database indicate the effectiveness of the proposed approach.