A weighted infrared face recognition method based on block-DCT

A novel infrared face recognition method is proposed in this paper. In this method, to get the good performance of infrared face recognition from the biological feature, thermal images are converted into blood perfusion domain by blood perfusion model. Then, the blood perfusion images are partitioned into different sub-blocks. Each sub-block is represented by the coefficients extracted from block-DCT domain. Finally, according to the discriminative power, different sub-blocks can be assigned to different weights to get holistic features. Experiments demonstrate the method proposed outperforms other methods based on PCA.