BDPCA plus LDA: a novel fast feature extraction technique for face recognition

Appearance-based methods, especially linear discriminant analysis (LDA), have been very successful in facial feature extraction, but the recognition performance of LDA is often degraded by the so-called "small sample size" (SSS) problem. One popular solution to the SSS problem is principal component analysis(PCA)+LDA (Fisherfaces), but the LDA in other low-dimensional subspaces may be more effective. In this correspondence, we proposed a novel fast feature extraction technique, bidirectional PCA (BDPCA) plus LDA (BDPCA+LDA), which performs an LDA in the BDPCA subspace. Two face databases, the ORL and the Facial Recognition Technology (FERET) databases, are used to evaluate BDPCA+LDA. Experimental results show that BDPCA+LDA needs less computational and memory requirements and has a higher recognition accuracy than PCA+LDA.