An image recognition model that combines some neural-network-based imageprocessing models is proposed. The recognition procedure consists of coarse regionsegmentation/extraction performed by a resistive-fuse network, Gabor wavelet transformation anddynamic-link matching. We have also developed a PC-based face/object recognition systemincluding FPGA implementation of the resistive-fuse network. The system has successfullyachieved real-time face recognition from a natural scene image.
展开▼