An algorithm of skin detection based on texture

Skin detection is widely used in many domains such as face detection and tracking as well as sensitive image detection. In this paper, RGB, YCbCr and HSV color spaces are used to conduct experimental comparison of skin color detection. The skin color detection based on HSV color space characteristic is very capable of making a distinction between the skin point and non-skin points in the picture. Moreover, this paper proposes a texture-based skin detection technique. It takes advantage of gray statistics to extract texture features and implements skin color detection combining with HSV color space. Experimental data shows that this texture detection algorithm based on gray statistics is effective for skin detection, which improves results of the skin detection to some degree.