Skin color and feature-based face detection in complicated backgrounds

An efficient face detection scheme that can detect multiple faces in a color image with a complex environment and different illumination levels is proposed in this paper. The first stage adopts skin color-based segmentation to search potential face regions. The second stage detects the lip in potential face regions using a lip color model and searches the eyes using geometry textures. The last stage clips the face region using an optimization ellipse. Results of the study demonstrate that the proposed approach performs well in detecting various poses in different illumination conditions and complicated backgrounds.