Sensitive body image detection technology based on skin color and texture cues

This paper researches the features of pornographic videos sensitive body videos, and presents a method to recognize and shield the sensitive content automatically. Skin color is one of important cues for pornographic video´s detection. Firstly, transform the color space, calculate Gaussian probability distribution, definite threshold value, analyze texture and noise to extract skin message from a frame image, and then build a skin color mask. Secondly, study the differences between sensitive body image and normal image in skin color distribution to extract some effective factors for judging and determine threshold values of the judgment factors. Finally, judge whether there is sensitive content in a frame image using the values of the factors and make the appropriate process for current frame according to the judgment result. Our algorithm achieves the satisfactory experimental results of shielding the sensitive content automatically when people watch video.