混沌优化BP网络在指纹分类中的应用

The Application of BP Neural-network Based on Chaotic Optimization in Fingerprint Classification

利用混沌运动的遍历性、随机性和规律性等特点,将加速混沌优化方法与BP算法相结合,并用混沌激励函数代替部分S型激励函数的混合优化方法对BP网络进行了改进.仿真实验结果表明,改进后的BP网络能够对指纹进行准确分类,其精确度高于传统BP网络.

Because of the important characteristics which are ergodicity, randomness and regularity, the accelerated chaotic algorithm is combined with the BP algorithm; a certain chaotic motivating function is used to replace the S style motivating function of the neural unit in the hidden-layer of the BP neural-network in this paper. The experimental results reveal that the styles of fingerprints could be classified more accurately by the BP neural - network based on chaotic optimization than the traditional one.