摘要
基于笔画平面抽取和动态网格划分,提出一种笔画平面与模糊隶属度相结合的手写体汉字特征提取方法,该方法克服了汉字特征抽取过程中因笔画粗细不均、笔画长短变形等引起的特征抽取不稳定问题.其基本思想是:用动态网格将汉字图像分别划分为横、竖、撇、捺4个笔画平面,并赋予每个网格中的点模糊隶属度,针对每个网格求加权累积直方图,最终获得汉字特征.基于南京理工大学NUST603HW手写汉字库的实验结果表明,该汉字特征抽取方法是有效的.
Based on stroke plane extraction and dynamic meshing partition, a new method for Chinese character feature extraction is proposed. This method combines stroke plane with fuzzy membership to improve the unstable problem, which is caused by the distortion of stroke. The basic idea is to divide the Chinese character image into four different stroke planes by dynamic meshing, allocate the fuzzy membership for each meshing, then compute the weighted accumulation histogram aimed for obtaining the feature for each meshing. The experiment results on NUST603HW handwritten Chinese character database of Nanjing university of science and technology verify the effectiveness of the proposed method.
出处
《扬州大学学报（自然科学版）》
CAS
CSCD
2008年第4期69-73,共5页
Journal of Yangzhou University：Natural Science Edition
基金
国家自然科学基金资助项目(60774017)
江苏省高校自然科学基金资助项目(07KJB520133
05KJB520152)
关键词
笔画平面
模糊隶属度
特征抽取
stroke plane
fuzzy membership
feature extraction
