earticle

영어

In order to improve the robustness of face identification with the changes of illumina-tion, expression and facial alteration, a new facial feature extraction algorithm based on weighted adaptive lifting wavelet(ALW) scheme and pulse-coupled neural network (PCNN) is involved in this paper. The face images are decomposed into several subbands by weighted adaptive lifting scheme. Then the PCNN is utilized to decompose each weighted subbands into a series of binary images, the entropies of which are calculated and regarded as facial features. Experimental results show that the method yields a good robustness against the illumination, expression and facial variability and reduces the computer burden.