基于支持向量机的手写数字串识别  

Handwritten Numerical String Recognition Based Support Vector Machine

作　　者：宋婉娟[1] 

机构地区：[1]湖北第二师范学院计算机学院,武汉430205

出　　处：《湖北第二师范学院学报》2010年第2期84-86,共3页Journal of Hubei University of Education

摘　　要：手写数字识别是手写字符识别的一个重要分支,单个数字识别技术已经比较成熟,而手写数字串的切分与识别则成为了该领域的一个难点。本文针对手写数字串的切分和识别设计了一种实验模型,该实验模型针对手写数字串的过度切分以及不足切分的特殊情况设置基于支持向量机的检测器进行再次识别确认,实验证明,使用基于支持向量机的检测器大大的减少了因为错误切分而带来的识别率的下降。Handwritten numerical recognition is an important branch of handwritten character recognition. The problem of isolated handwritten numerical recognition has been solved, and however, the segmentation and recognition of handwrit ten numerical string is a difficult problem in this area. An experiment model about handwritten numerical string recognition was applied in this paper, which could deal with the problems such as over segmentation and under segmentation by setting verifier based support vector machine. The experiment results show that this method with verifier based support vector machine reduce the decrease of recognition rate because of inaccurate segmentation greatly.

关 键 词：支持向量机 过度切分 检测器 

分 类 号：TP391.43[自动化与计算机技术—计算机应用技术]