|
|
Strokes order recovery based on calligraphic hybrid statisticalstructural model |
TUN Yang-Fei, PENG Huo-Ting, TUN Fei |
|
|
Abstract The assumption of minimum curvature between adjacent line segments which is used to recover strokes order from offline handwritings is not fully applicable for strokes order recovery from Chinese calligraphic handwriting. A new method based on calligraphic hybrid statisticalstructural model to recover strokes order was proposed. The stages are: (1) the features of input sample are extracted according to Chinese calligraphy model (CCM); (2) coarse selection is applied to find the candidate samples set; (3) CONDENSATION algorithm conditional density propagation over time is performed to select the best matching sample from candidate samples set with known strokes order. By recovering strokes order from 15 commonly used radicals of 100 Chinese calligraphic handwritings, the accuracy of Kalman filter based on minimum curvature and that of the new method were 42% and 91% respectively.
|
Published: 20 March 2012
|
|
基于书法文字统计结构混合模型的笔顺提取
离线手写体的笔顺提取中用到的相邻笔段间最小曲率的假设,对于中文书法文字的笔顺提取并不完全适用,为此提出基于书法统计结构混合模型,通过该模型获得笔顺的新方法,其步骤是:(1)按照书法文字模型提取样本的相关特征,(2)按照输入样本使用粗糙选择获得候选样本集,(3)使用条件密度传播算法从已知笔顺的候选样本集中搜索出和输入样本最佳匹配的样本.对100个书法文字中的15个常用部首进行笔顺提取,基于最小曲率的Kalman滤波和新方法的准确率分别为42%和91%.
|
|
[1] 吴佑寿,丁晓青.汉字识别原理方法与实现[M].北京:高等教育出版社,1992.
[2] 丁晓青.汉字识别研究的回顾[J].电子学报,2002, 30(9): 13641368.
DING Xiaoqing. Chinese character recognition: a review [J]. Chinese Journal of Electronics, 2002, 30(9): 13641368.
[3] YOSHIHARU K, MAKOTO Y. Recovery of drawing order from singlestrokes handwriting images [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(9): 938949.
[4] STEFAN J, DAIMLERBENZ A G. Recovering writing traces in offline handwriting recognition: using a global optimization technique [C]// Proceedings of 13th Int’l Conference Pattern Recognition. Vienna: IEEE, 1996: 152154.
[5] PIERRE M L, CHRISTIAN V G. A Kalman approach for stroke order recovering from offline handwriting [C]// Proceedings of the 4th International Conference on Document Analysis and Recognition. Ulm, Germany: IEEE, 1997: 519522.
[6] MICHAEL I, ANDREW B. Condensationconditional density propagation for visual tracking [J]. International Journal of Computer Vision, 1998, 29(1): 528.
[7] WU Yingfei, ZHUANG Yueting, PAN Yunhe, Web based chinese calligraphy learning with 3D visualization method[C]// Proceedings of ICME. Toronto: IEEE, 2006: 20732076. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|