联机手写英文识别  

On-Line Handwriting Cursive Recognition

作　　者：邹明福[1] 钮兴昱[1] 刘昌平[1] 白洪亮[1] 

机构地区：[1]中国科学院自动化研究所文字识别工程中心,北京100080

出　　处：《计算机研究与发展》2006年第1期138-144,共7页Journal of Computer Research and Development

摘　　要：英文手写识别既是模式识别问题又是一个搜索问题,其计算复杂度非常高·针对这个问题,提出了一些新的方法来解决联机英文手写识别问题·首先,运用一些先验知识对所获得的基线进行调整;其次,针对英文识别过程的复杂度太高,提出了快速有效的解码算法———主笔划分层构筑Viterbi算法;最后,将多阶段的分类信息融合到决策过程中,较大幅度地提高了系统的性能·在Unipen训练集和实验室数据集上测试取得了良好的效果·On-line cursive handwriting recognition is both a pattern recognition and search problem. Its computing complexity is very high. Some new methods are proposed to overcome these problems. First, some prior knowledge, such as middle of primitive and delayed stroke, is used to adjust the reference line. Then, based on the special primitive attribute of handwriting cursive, a fast valid decoding algorithm, that is, the primitive level building beam viterbi （PLBBV）, is presented. Finally, a combining classifiers algorithm that uses all the classifiers＇ measurement to make decision is represented. The tests on the Unipen training set and the laboratory set reveal the feasibility of the proposed method.

关 键 词：自由手写识别 分层构筑 多阶段识别 解码算法 大词汇 粗分类 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]