FACE LOCATION IN WAVELET-BASED VIDEO COMPRESSION FOR HIGH PERCEPTUAL QUALITY VIDEOCONFERENCING

We present a human face location technique based on contour extraction within the framework of a wavelet-based video compression scheme for videoconferencing applications. In addition to an adaptive quantizatio n in which spatial constraints are enforced to preserve perceptually i mportant information at low bit rates, semantic information of the hum an face is incorporated to design a hybrid compression scheme for vide oconferencing since the human face is often the most important portion within a frame and should be coded with high fidelity. The human face is detected based on contour extraction and feature point analysis. A n approximated face mask is then used in the quantization of the decom posed subbands. At the same total bit rate, coarser quantization of th e background enables the face region to be quantized finer and coded w ith higher quality. Simulation results have shown that the perceptual image quality can be greatly improved using the proposed scheme.