Abstract
Along with the explosive growth of the Internet, comes the proliferation of pornography. Compared with the pornographic texts and images, blue movies can do much harm to children, due to the greater realism and voyeurism of blue movies. In this paper, a framework for recognizing blue movies by fusing the audio and video information is described. A one-class Gaussian mixture model (GMM) is used to recognize porno-sounds. A generalized contour-based pornographic image recognition algorithm is used to detect pornographic image frames of a video shot. Then a fusion algorithm based on the Bayes theory is employed to combine the recognition results from audio and video. Experimental results demonstrate that our framework which exploits both audio and video modalities is more robust and achieves better performance than one which uses either one alone.