The demarcating method of infrared image measuring temperature based on GA-BP network

According to temperature demarcation of infrared image measuring temperature, one demarcating method based on GA-BP network is proposed in this paper. This method is that the structural parameters of BP neural network is optimized by using genetic algorithm, then the temperature demarcation is carried on through obtained the best structural BP neural network. According to using the global search ability of genetic algorithm and local search ability accurately of BP neural network, so as to improved the accuracy of temperature calibration. It can be seen that through MATLAB simulation tests, using this method carry out temperature demarcation is superior to BP neural network from convergence precision and convergence speed.