Weighted infrared face recognition in multiwavelet domain

To extract the discriminative information from the sparse representation of infrared face image, a weighted infrared face recognition method based on a regularization discriminant criterion in multiwavelet domain is proposed in this paper. Firstly, the useful information in infrared face is represented by multi-wavelet transformation. Then, a regularization discriminant criterion is applied to determine the weights of subbands in multiwavelet domain. Finally, based on the weighted fusion distance, the 1-NN classifier is applied to get final recognition result. The experiment results show that the recognition performance of sparse representation based on multiwavelet representation outperforms that of method based on traditional wavelet representation; and the proposed infrared face recognition method considering the contributions of different sub-bands in multiwavelet domain has better recognition performance, compared with the method without weighted fusion algorithm.