IMAGE GUARDER: AN INTELLIGENT DETECTOR FOR ADULT IMAGES

摘要

In this paper, we proposed an intelligent adult image detector, called Image Guarder, which can automatically analyze the image content, efficiently recognize adult images. In order to speed up recognition, a two layers recognition framework is adopted. An adaptive statistical color model is developed to detect the skin pixel in variant illumination environment. Smooth character is used to test the skin texture feature after skin color detection. Only the images that have enough skin color pixels and smooth texture are sent to a support vector machine (SVM) classifier to refine the recognition. Color, texture and shape features are extracted from the skin regions and fed into the trained SVM. The experimental results are carried out on a large image set about 110,657 nature images and 11,351 adult images downloaded from the Internet. The Image Guarder shows excellent performance that the precision for adult image recognition is 76.5%, while the precision for benign image is 95% respectively. The average process speed is less than one seconds per frame on a Pentium IV1.5GHz PC.