基于BP神经网络的脱机手写混排字符集的识别方法

脱机手写字符自动识别是计算机光学字符识别(OCR)领域的一个活跃课题，有着十分广泛的应用前景.文中提出了基于BP神经网络的脱机手写中英文和数字混合字符集的识别方法，给出一种特征提取方法，通过实验说明如何选取网络隐含层神经元个数，以及如何选取网络连接权值的初值.对由不同人手写的中英文字符的混合字符集做识别实验，结果表明文中所设计的神经网络分类器，不仅能保证识别精度和识别速度，而且能有效的识别混合字符集.

AN OFF-LINE HANDWRITING CHINESE CHARACTER, ENGLISH CHARACTER AND DIGITAL CHARACTER SET RECOGNITION METHOD BASED ON THE BP NEURAL NETWORK

The automatic recognition of off-line handwriting character is an active subject inthe area of computer optical character recognition (OCR), which has a wide range ofpotential applications. An off-line handwriting Chinese character, English character anddigital recognition method is put forward based on the BP neural network. Also discussed arethe problem of feature extraction, the problem of determining the number of hidden layer＇sneural nodes, and the problem of initialization of connection weight, Experiments have beenconducted for an off-line handwriting character set. The recognition results show thatcompared with other recognition method. this designed can recognize Chinese character,English character and digital with same excellence recognition rate and speed.