基于反向传播神经网络的身份证号码识别研究

Research on IDNumber Recognition Based on BP Neural Network

基于反向传播算法的多层前馈网络(简称BP神经网络)在图像处理方面应用较为广泛。目前,身份证号码识别技术在图像识别领域迅猛发展,为提高识别身份证号码的速度及准确性,本文研究一种基于BP神经网络的身份证号码识别系统。首先,将身份证图像进行预处理,接着利用MATLAB对身份证号码进行定位以及分割,然后利用BP神经网络,通过调用MATLAB神经网络工具箱,设置相关参数对身份证号码进行训练、匹配数据库中的数字,最后识别并输出身份证号码。实验结果表明,基于BP神经网络的身份证号码识别正确率为95%,该系统具有较高的准确率以及鲁棒性。

The multi-layer feedforward network based on back propagation algorithm(referred to as BP neural network)is widely used in image processing.At present,ID card number identification technology is developing rapidly in the field of image recognition.In order to improve the speed and accuracy of identification of ID card numbers,this paper studies a ID number recognition system based on BP neural network.First,pre-process the ID card image,then use MATLAB to locate and segment the ID number,and then use the BP neural network to set the relevant parameters to train the ID number in the database by calling the MATLAB neural network toolbox.Number,finally identify and output the ID number.The experimental results show that the recognition rate of ID card number based on BP neural network is 95%,and the system has high accuracy and robustness.