The Filtering of Internet Images Based on Detecting Erotogenic-part

The research of pornographic images has recently emerged as an active topic. Compared with several deficiencies of the previous approaches which detected by the features of skin-color only, the paper presents a novel algorithm based on the face and trunk detection. And through the recognizing the erotogenic-part in the image, we implemented the algorithm and construct a simple and fast pornographic images classifier system based on a decision tree. The extensive experiments validated that the erotic images detecting system provides a higher detection rate and much lower false positive rate than many ones before. And results of experiments on 193 pornographic and 1259 benign images show a excellent performance, i.e. the detection rate has reached 80.31%, and the false positive rate has reached 18.30%.