A novel fisher criterion based approach for face recognition
Chu Zhang, Wen-Sheng Chen · 2013
Traditional Fisher linear discriminant analysis (FLDA) method is a promising algorithm for face recognition. However, FLDA does not utilize the geometric distribution information of the training face data, which will degrade its performance. In order to enhance the discriminant power of FLDA, this paper proposes a novel Fisher criterion by using geometric distribution information of the training samples. The geometric distribution information based LDA (GLDA) algorithm is then developed for face recognition. The proposed GLDA approach has been evaluated with two publicly available face databases, namely ORL and FERET databases. Experimental results demonstrate the effectiveness of our GLDA approach.