Performance based algorithm for the detection and extraction of human skin

This paper presents the comparative analysis of various color space models like RGB, HSV and YC_bC_r color models for detection and extraction of human skin from it. Skin detection is broadly used in applications like face detection, tracking of the body parts and hand gesture analysis, for retrieval of skin and blocking of unpleasant contents. The proposed method is performed in four phases; the effect of color space transformation on skin detection performance and finding the appropriate color space for skin detection; the role of the illuminance part of a color space; the appropriate pixel based skin color modeling technique; and finally, the effect of color fidelity algorithms on color based skin classification. The heterogeneity of RGB color space is detached by using HSV and YC_bC_r color space models. In this paper the input image captured from a camera is converted into three different color space models i.e. RGB, HSV and YC_bC_r and then performance analysis of algorithms is to be evaluated on the basis of skin detection and extraction.