Robust lip feature detection in facial images

This paper present an algorithm to locate four lip features in face images. Specifically, it extracts the left and right corners, the upper and lower lips, upon the condition that the positions of the two eye centers are provided in advance. Four lip features are located by taking the characteristic of lip color and edge information into account. Analysis conducted on more than 2000 facial images proved that the eye positions and eye distance can be utilized to roughly specify mouth area. We tested the proposed algorithm on 530 images collected from FERET database. The experimental results show that the proposed algorithm can accurately detect lip features.