Skin Detection Using Color Component Subtraction and Texture Information

This paper presents skin detection algorithm for detecting human skin regions in color images. The input color image in RGB format is converted into HSV format for color components subtraction. The value component minus hue component is applied for first stage of skin detection. The result of the subtraction is considered as skin region candidates. From the skin region candidates, rectangular box enclosing the regions are estimated. The texture features are also calculatedfor these skin candidates regions, where contrast and entropy are used. The features give acceptable separation between skin and non skin regions. These texture features are used to verifiy that the segmented blobs are skin regions. The algorithm is tested on color images focusing on palm and face skin regions. The results had shown that the algorithm is able to achieve more than 90% of detection rate.