汉字串的模糊匹配算法  

An Fuzzy Match Algorithm of Chinese Character Strings

作　　者：娄正良[1] 刘昌平[1] 白洪亮[1] 邹明福[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：《微电子学与计算机》2004年第4期13-15,24,共4页Microelectronics & Computer

摘　　要：目前手写文稿的处理由于存在分割和识别的困难,很难达到实用的阶段。文章提出的算法是针对手写文稿的处理在信封检索系统中的具体应用而提出的,在假定信封地址行分割、识别有错误的前提下,从信封地址中识别出感兴趣的字符串。试验表明:运用该算法的系统,其检出率达到95%,误检率只有15%,取得了良好的效果。There are many difficulties existed in segmentation and recognition of off-line handwritten document processing. It is difficult that off-line handwritten document processing is brought into application. The proposed algorithm could make the immature technology of off-line handwritten document processing applied into practice of envelope retrieval system. In the case of some errors occurred in segmentation and recognition, sensitive address string was extracted from envelopment image. In experiments, the detection rate is 95%, false reject rate only is 15%. Good results are demonstrated by application.

关 键 词：信封检索 模糊匹配 后处理 检出率 误检率 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]