Abstract: Focusing on multi-face detection problems of color image with complicated background and so on, this paper proposes an improved multi-face detection method based on skin-color model and Gaussian distribution. Skin regions are acquired using skin-color model in the first stage. In the second stage, facial features are utilized to obtain face candidates. Finally, two Gaussian curves are acquired by projecting the edge-detection-image to X-axes and Y-axes respectively, and an accurate face region is found through the solution of Gaussian equation. Simulation shows that the robust method proposed in the paper can improve the multi-face detection accuracy and the detection speed.

Key words: face detection, facial feature extraction, Gaussian distribution model, projection