Weighted BDPCA Based on Local Feature for Face Recognition with a Single Training Sample

One of the main challenges faced by the current face recognition techniques lies in the difficulties of collecting samples. In the situation of law actualizing, passport or status validating, only one sample per person is available. Unfortunately, many reported face recognition techniques rely heavily on the size and representative of training set, and most of them will suffer serious performance drop or even fail to work if only one training sample per person is available to the systems. Such a task is very challenging for most current algorithms due to the extremely limited representative of training sample. In this paper, the two-directional 2DPCA (BDPCA) is developed to attack this problem. The block weighted two-directional 2DPCA (MWBDPCA) is proposed for efficient face representation and recognition. Beside this, the fuzzy theory is applied to classification. Experimental results on ORL and a subset of CAS-PEAL face database show that the method presented achieves even higher recognition accuracy.