摘要
提出了一种基于笔划的手写体汉字方向分解特征提取的新方法 .根据每个笔划像素点及其邻域像素点的方向分布特征 ,汉字图像被分解为“横”、“竖”、“撇”和“捺”4种子模式 ,而无需提取轮廓和骨架 .文中构造了 5种不同的弹性网格 ,并将其应用于方向分解特征的提取 ,最后 ,应用 86 3手写样本库HCL2 0 0
A new directional feature extraction approach based on st roke directional decomposition of a Chinese character is proposed. Without extra cting the skeleton or contour of the character, the four directional sub_patt erns, namely, horizontal, vertical, left up diagonal and right up d iagonal sub_patterns are obtained directly by analyzing the stroke directional characteristics of the character. Then five kinds of elastic me shing methods are presented to extract cellular directional featu res. Finally, experiments on handwritten samples from HCL2000 are carried on whi ch prove the effectiveness of the proposed approach.
出处
《华南理工大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2003年第3期11-14,共4页
Journal of South China University of Technology(Natural Science Edition)
基金
国家自然科学基金资助项目 (6 0 2 75 0 0 5 )
广东省自然科学基金资助项目 (0 116 110 2 0 82 8)
Motorola研究基金资助项目
