基于多重卷积神经网络的大模式联机手写文字识别

联机手写识别在日常生产生活中有着广阔的应用,模式识别也一直把其作为研究的重点。传统的识别方法是利用普通卷积神经网络技术,该方法在对小规模字符集联机手写文字识别时有着较高识别率,总体性能高,但在对大规模字符集识别时,识别率则大大降低。提出一种基于多重卷积神经网络的识别方法,旨在克服以往方法对大规模字符集识别时识别效率不高的问题,提高大规模字符集联机手写文字的识别率。系统使用随机对角Levenberg-Marquardt方法来优化训练,通过使用UNIPEN训练集测试该方法识别准确率可达89%,是一个有良好前景的联机手写识别方法。

Large pattern online handwriting character recognition based on multi-convolution neural network

Online handwriting character recognition is an important field in the research of pattern recognition. The tradi-tional recognition method is based on the common convolutional neural networks（CNNs）technology. It has an efficient recogni-tion rate for the small pattern character set online handwriting characters,but has low recognition rate for the large pattern character set recognition. A recognition method based on multi-convolutional neural networks（MCNNs）is presented in this pa-per to overcome the situation that the previous methods have the low recognition rate for large pattern character set and improve the recognition rate for the large pattern handwriting character set recognition. The stochastic diagonal Levenbert-Marquardt meth-od is used in the system for training optimization. The experimental results show that the proposed method has the recognition rate of 89% and has a good prospect for online handwriting character recognition for large scale pattern.