Mean-shift based Mixture Model for Face Detection in Color Image (MP-L1)

Author(s) : Tze-Yin Chow (The Hong Kong Polytechnic University, Hong Kong) Kin-Man Lam (The Hong Kong Polytechnic University, Hong Kong)

Abstract : Human face detection is a challenging task under different lighting conditions. In this paper, we propose an efficient and reliable algorithm to detect human faces in an image. In our algorithm, skin-colored pixels under various lighting conditions are identified by using a region-based approach. Within the detected skin-color regions, a ratio method is proposed to determine possible eye candidates. Two eye candidates form a possible face region, which is then verified by means of a two-stage procedure with an eigenmask. Experiment results show that this face detection algorithm is efficient and reliable under different lighting conditions.

Menu