Dangerous persons can be monitored accurately and quickly using the high-precision recognition of the rel-ative facial images via the image sensors. To increase the recognition rate of face recognition by improving the immune algorithm, the immune computation was redesigned for bet-ter face recognition to decrease the facial disturbances of the pose, illumination and expression (PIE), in this paper. The clonal selection algorithm was improved with the modifica-tion of the affinity and the algorithm workflow. The improved clonal selection algorithm searches the most similar anti-body sample against the antigen of an unknown facial image, according to the affinity between the antigen and the anti-body. The unknown facial images were recognized with this
improved affinity and the uncertainty-based reasoning, so the affinity matching of the antibody with the unknown anti-gen was also improved. Experimental results show that this immune algorithm outperforms some state-of-the-art algo- rithms in the face recognition accuracy tests with such facial
image databases as AR, Yale and CMU-PIE. So the pro-posed immune algorithm is useful and effective to improve the performance of face recognition in the image sensor network.

EB00000002855K

Available