Skin Detection Using Contourlet-Based Texture Analysis

Detection of skin pixels in arbitrary images is addressed in this paper. We have combined texture and color information to segment skin regions. First, a pixel-based boosted skin detection method is used to locate skin pixels. To further improve the detect performance, skin region texture features are employed using the non-subsampled contourlet coefficients. For the candidate skin pixels, the set of 8 times 8 patches around that pixel in all subimages are selected and the feature vector of each patch is extracted. Multilayer perceptron is then utilized to learn features and classify any given input sample. The proposed algorithm has achieved true positive rate of about 82.8% and false positive rate of about 7.6% on the test set that contains 300 images. Experimental results show the effectiveness of the proposed method when compared to the other state-of-the-art texture-based skin segmentation approaches.