Lip Recognition for Authentication and Security

Abstract

Lip is used as an identifier from person to person as the size of the upper and lower lips, furrows, grooves, the distances between the lines and the edges vary individualistically. These unique parameters are experimented to distinguish individuals and their uniqueness is also verified. The highlighting advantage in devising the biometric system based on lip recognition is that the data acquisition and handling are simple and hence storing and processing the data becomes an unconstrained task leading to drastic increase in the efficacy of the system. The main focus of this work is to track the lips in the given face image and then extract suitable features from the lips to perform the differentiation task. Accurately and robustly tracking lip motion in image sequences is especially difficult because lips are highly deformable, and they vary in shape, colour, and relation to surrounding features across individuals; in addition, they are subject to both non-rigid (expression, utterance of speech) and rigid motion (head movement). The use of colour space transformation has shown very well for lip image segmentation.