Gabor wavelet neural network algorithm based on parallel structure

A Gabor wavelet neural network algorithm was presented based on parallel structure. According to the characteristics of multi-CPU parallel structure and neural network parallel, the algorithm for recognizing image target was designed based on the Gabor wavelet neural network. The algorithm input layer involved operation on scale, translation and frequency modulated parameter of Gabor wavelet, the hide layer realized and optimized the neural network algorithm on parallel CPU and the algorithm output layer gave the classification result of Gabor wavelet network algorithm. The simulation experiment was processed by four types plane image targets, and the results indicate that the recognition rate is 98%, recognition time is 40 ms.