A HIGHLY EFFICIENT AUDIO-VISUAL RECOGNITION SYSTEM BASED ON MULTIBAND FEATURE

This paper present a extremely high-octane audio-visual detection system in compression domain. For face recognition systems, the multiband feature fusion method selects the wavelet sub bands that are equable to illumination and facial expression variations. These sub bands will be distilled directly from the inverse quantization in the compression system. By taking the inverse quantized wavelet coefficient of the video as the input, the inverse wavelet transform which equivalents to image reconstruction is omitted. As a result, the computational complexity of the conventional video-based face recognition system is attenuated. To present a set of new face localization methods to localize the facial wavelet coefficients from the wavelet sub band image. The additional feature (Audio) will be added into the facial feature to enhance the recognition performance of the system. The dual optimal multiband feature fusion method is then used to fuse the two set of wavelet coefficients and generate the scores. The proposed system achieves high recognition accuracy in audio-visual database and also provides low computational complexity.