小波神经网络在手写数字识别中研究与应用  

The Research and Application of Wavelet Neural Network on Handwritten Numeral Recognition

作　　者：岳耀雪[1] 

机构地区：[1]山东理工职业学院,济宁272017

出　　处：《电脑编程技巧与维护》2010年第14期85-87,97,共4页Computer Programming Skills & Maintenance

摘　　要：针对手写数字识别的特点,讨论了数字识别预处理的方法,包括二值化、倾斜矫正、细化和归一化。利用小波函数代替传统神经网络中的激活函数,构建了用于数字识别,小波神经网络系统。仿真结果显示,新系统大大提高了网络训练速度,数字识别的正确率也明显提高。According to the characteristics of handwritten numeral recognition,introduced the pretreatment technologies of numeral recognition,it includes：binarization,slant correction,thinning and normalization.A wavelet function is used to replace the traditional neural network activation function,constitute a wavelet neural network system which is used for numeral recognition.The simulation result shows the new system raised the rate of network training greatly;the accuracy rate of numeral recognition has been improved obviously.

关 键 词：手写数字识别 小波神经网络 小波分析 

分 类 号：TP391.43[自动化与计算机技术—计算机应用技术]