基于BP特征筛选的模糊聚类手写体数字识别  

Handwritten Numeral Recognition by Fuzzy Clustering Based on BP Feature Extraction

作　　者：叶佩[1] 江涛[2] 

机构地区：[1]武汉工业学院数理系,武汉430023 [2]武汉理工大学管理学院,武汉430070

出　　处：《武汉理工大学学报》2007年第6期128-130,共3页Journal of Wuhan University of Technology

基　　金：国家自然科学基金(79970025);湖北省教育厅科研计划项目(D200618009);武汉工业学院校立科研项目(05Y24)

摘　　要：运用BP神经网络对无约束手写体数字的识别过程中的数字样本进行筛选,将筛选的结果纳入聚类源,再通过构造模糊关系矩阵,进行模糊聚类。实验证明,该方法具有很高的抗干扰性能,克服了传统算法单因子识别的局限性,识别率和准确率都有很大提高。The figure specimens were filtered through the process of unconstrained Handwritten Numeral Recognition by BP neural network in the paper. And the result of screening was fit into the clustering source. At last fuzzy clustering was carried out by constituting the fuzzy relation matrix. The result of experiment demonstrates that the method have very high noise immunity capacity and overcame the limitation of traditional algorithm with single factor recognition. The recognition rate and precision ratio were greatly improved at the same time.

关 键 词：模糊聚类 BP神经网络 数字识别 

分 类 号：TP182[自动化与计算机技术—控制理论与控制工程]