基于主分量分析法的脱机手写数字识别  

Offline Handwritten Numeral Recognition Based on Principal Component Analysis

作　　者：张国华[1] 万钧力[1] 

机构地区：[1]三峡大学电气信息学院,宜昌443002

出　　处：《计算机工程》2007年第18期219-221,共3页Computer Engineering

基　　金：湖北省教育厅科学技术基金资助项目(2003A002)

摘　　要：针对手写数字识别研究中统计特征和结构特征融合困难的问题,利用主分量分析法提取数字字符结构特征的统计信息,重建数字模型,并估计重构偏差,同时提取数字的高宽比特征和欧拉特征,通过组合与3种特征相对应的贝叶斯分类器的分类结果实现数字识别。使用该方法对样本库中的样本进行测试,正确识别率为90.73%。To overcome the difficulty of fusing statistical feature and structural feature in the research on handwritten numeral recognition, principal component analysis is used to reconstruct numeral model and estimate the numeral reconstructive error based on the statistical information of digit structural feature. At the same time, the height-width ratio and Euler value of numeral is extracted. Recognition of digital character is completed through the combination of Bayes classifier corresponding to the three type features. The recognition rate of the method is 90.73% in handwritten numeral database.

关 键 词：数字识别 主分量 特征提取 组合分类器 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]