Skin Color detection Using Stepwise Neural Network and Color Mapping Co-occurrence Matrix

Abstract

Skin color has been proven to be a useful and robust cue for face detection, human tracking, image content filtering, pornographic filtering, etc. Most of skin classification researches are focused on using pixel-based method to classify skin and non-skin pixels. This paper proposed a new technique for region-based skin color detection using texture information. The texture information was extracted from the color mapping co-occurrence matrix (CMCM). This technique is extension of gray level co-occurrence matrix (GLCM) which is introduced by Haralicket. al to compute second order statistical texture features. The new color mapping matrix (CMM) between color bands have been developed for skin and non-skin area for each skin image and then, the CMCM were computed at four direction with distance, d = 1, and angle, θ = 0o, 45o, 90o, and 135o. The thirteen Haralick’s textures have been computed and used for formulating a skin color classifiers using stepwise neural network (SNN). The performance of each skin color classifier was measured based on true and false positive value. Besides that, the benchmark datasets from Universidad de Chile and TDSD were also be employed to test the skin color classifiers ability. The results shown that the skin color classifier formulated with [RGB] CMCM at direction (1, 0o) most superior as compared to other direction. Its average of true positive and false positive are 98.38 percent and 3.67 percent, respectively. Meanwhile, the classifier formulated with [RGB] CMCM at direction (1, 90o) is totally failed to classify skin and non-skin colors. Meaning that, the texture features which are computed from [RGB] CMCM at direction (1, 90o) cannot represent skin and non-skin color at all.