Face image retrieval in video sequences using lifting wavelets transform feature extraction

Face image retrieval in video sequences is a challenging task for many multimedia applications. This paper introduces a scheme based on lifting wavelets transform feature extraction for face image retrieval in video sequences. In our scheme, we first extract the key-frames rapidly from video sequences by a color feature for its effectiveness. Based on the extracted key-frames, we propose to employ the AdaBoost based face detection method and the lifting wavelets transform (LFWT) technique which provides good alternative of intensity representation for feature extraction of the detected faces. By combining the two stages above, we can perform the face image retrieval in video sequences task efficiently and effectively.