Lip signatures for automatic person recognition

This paper evaluates lip features for person recognition, and compares performance with that of the acoustic signal. Recognition accuracy is found to be equivalent in the 2 domains, agreeing with the findings of Chibelushi. The optimum dynamic window length for both acoustic and visual modalities is found to be about 100ms. Recognition performance of the upper lip is considerably better than the lower lip, achieving 15% and 35% identification error rates respectively, using a single digit test and training token.