A Highly-Efficient Face Recognition Method Based on Weighted LDA

In face recognition, the class mean of the training samples may deviate from the class center in small sample size. The method based on adaptively weighted fisherface is one of the approaches to deal with the problem. However, it didnpsilat consider the face recognition efficiency. To improve recognition efficiency, the paper proposes a highly-efficient face recognition method based on weighted LDA. Firstly, the wavelet transform is applied to the face image so that the lowest resolution sub-image of the face image is obtained. Secondly, the dimension of sub-image is reduced by 2DPCA. In the end, the class means are updated by using the weighted feature vector in the reduced order subspace. The traditional LDA is improved by using the new class means. The experiments on the ORL face database show that the proposed method can achieve higher recognition rate and efficiency as well as better implementation result.