摘要
本文提出了一种用于字符预分类的模糊逻辑分析法，对文本字符作印刷结构分析，给出了一个带有客差分析的文本行字符基线精确测定算法，其它有效参考线则通过聚类分析获得．模糊逻辑用于确定各字符类的隶属值以保证字符的正确预分类．实验结果表明，我们的模糊印刷字符预分类法在SUN4／490工作站上每秒可有效处理104以上字符，并对不同大小的字符有满意的结果．
This paper presents a fuzzy-logic approach to analyzing tmeraphical structures of textual blocks in order to be used for character preclassification. An efficient baseline detection algorithm embedded with tolerance analysis is developed for locating precisely the baseline. The other virtual reference lines are extracted by a clustering technique. To ensure character preclassification correctly, a fuzzy-logic approach is used to assign a membership to each typographical category for arnbiguous classes. The results show that our fuzzy typographical analysis for character preclassification is efficient to moe than 10, 000 characters per second on a SUN 4/490 workstation and has been tested for different font sizes with satisfactory pefformance.
出处
《常熟高专学报》
1999年第2期71-79,共9页
Journal of Changshu College
关键词
字符预分类
模糊逻辑
模糊印刷分析
字符识别
character preclassification, typographical categoization, baseline detection, fuzzy logic, fuzzy classfication
