光学与光电技术, 2016, 14 (5): 43, 网络出版: 2016-12-23
基于图像特征提取的脱机手写数字识别方法
An Off-Line Handwritten Numeral Recognition Method Combined With the Statistical Characteristics and Structural Features
脱机手写数字识别 主分量分析 结构特征 统计特征 offline handwritten numeral recognition principal component analysis structural features statistical characteristics
摘要
脱机手写数字识别其本质是数字的图像特征匹配问题,所以需要进行手写数字的特征提取,为了准确识别,往往使用较高的特征维数,这就导致识别效率较低。为了提高识别效率,同时为了保持较高的识别率,提出了一种基于图像特征提取的脱机手写数字识别方法。首先利用主分量分析法抽取数字字符图像的统计特征,来降低数字的特征维数,通过对主分量重建模型的误差分析进行数字识别;然后,结合手写数字的笔画结构不稳定的特点,设计并提取数字的宽高比结构特征,进一步比对识别;最后,利用自制训练样本及测试样本库进行仿真实验,数字识别率为96%,识别准确率较高。
Abstract
Off-line handwritten numeral recognition is a pattern recognition problem of the images of ten numbers. In order to improve the recognition efficiency, the character dimension of numbers image should be decreased. As well, in order to improve the recognition veracity, the character mode instability which resulted from different writing styles and habits should be considered. A numbers recognition method which combined with the statistical characteristics and structural features of numbers is proposed in this paper. Firstly, the principal component analysis (PCA) method was adopted to extract statistical characteristics of numeral image. The numeral recognition will be realized through analysis of the reconstruction error of model which reconstructed by the principal components. In order to further determine the type of numeral, the structural features of width to height rate are designed and added to the recognition process. Finally, through experiments on the identification of numeral image, the reliability and accuracy of this method of digital recognition is verified and the recognition rate is 96%.
周胜明, 张玉叶, 王春歆. 基于图像特征提取的脱机手写数字识别方法[J]. 光学与光电技术, 2016, 14(5): 43. ZHOU Sheng-ming, ZHANG Yu-ye, WANG Chun-xin. An Off-Line Handwritten Numeral Recognition Method Combined With the Statistical Characteristics and Structural Features[J]. OPTICS & OPTOELECTRONIC TECHNOLOGY, 2016, 14(5): 43.