Skin Detection Model Research Based on Image Enhancement
Histogram element gradation distribution of the original image concentrates in the low gradation level, and after histogram equalization processed the image is bright and unconspicuous in details. In order to improve the situation, this paper presents an improved image enhancement algorithm .In the algorithm the original image is transformed by the conventional histogram equalization and mapped the histogram equalization processing image as far as possible within the scope of mapping. Then linear transform is used to enhance contrast and apply to mix skin complexion model to extract. Experiments prove that this method is better than double skin model detection at testing results, especially in the eyes and mouth.
Zhenyu Du and Bin Liu
G. L. Yang et al., "Skin Detection Model Research Based on Image Enhancement", Applied Mechanics and Materials, Vol. 65, pp. 260-263, 2011