基于候选特征笔画和多类阈值的手写汉字切分①-计算机系统应用.PDFVIP

2013 年 第 22 卷 第 5 期 计 算 机 系 统 应 用 基于候选特征笔画和多类阈值的手写汉字切分① 1 1 2 3 马建平 , 汪庆锋 , 陈 渤 , 陈 强 1(浙江工业大学 计算机科学与技术学院, 杭州 310023) 2(浙江商业职业技术学院 应用工程学院, 杭州 310053) 3(广东第二师范学院 计算机科学系, 广州 510310) 摘 要: 通过分析汉字的常见结构, 鉴于汉字与汉字之间的距离和构成汉字的部件之间的距离的显著差异性, 提 出一种基于候选特征笔画和多类阈值的手写汉字切分方法. 首先从构成手写汉字的笔画集合中提取候选特征笔 画, 根据候选特征笔画将手写汉字预切分, 然后利用基于间距阈值的部件组合规则对过切分的汉字部件进行组 合, 最后采用基于单字宽度阈值的粘连汉字判断规则搜索粘连汉字, 对粘连汉字进行递归切分. 实验表明, 该方 法对连续手写汉字的切分准确率较高, 具有一定的实用性. 关键词: 汉字结构; 手写; 特征笔画; 阈值; 切分 Segmentation of Handwritten Chinese Characters Based on the Candidate Characteristics Strokes and Multi-Class Threshold 1 1 2 3 MA Jian-Ping , WANG Qing-Feng , CHEN Bo , CHEN Qiang 1(School of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, China) 2(School of Application Engineering, Zhehuabg Vocational College of Commerce, Hangzhou 310053, China) 3(Department of Computer Science, Guangdong University of Education, Guangzhou 510310, China) Abstract: With the analysis of the common structures of Chinese characters, a handwritten Chinese characters segmentation method which based on the candidate characteristics strokes and multi-class threshold is proposed in view of the significant difference between the distance between Chinese characters and the distance between the components that constitute a Chinese character. Firstly, the candidate characteristics strokes are extracted from the collection of strokes that constitute handwritten Chinese characters, the handwritten Chinese characters are pre-segmented according to the candidate characte