Please wait a minute...
浙江大学学报(工学版)
J4  2010, Vol. 44 Issue (3): 468-472    DOI: 10.3785/j.issn.1008973X.2010.03.010
    
Strokes order recovery based on calligraphic hybrid  statisticalstructural model
 TUN Yang-Fei, PENG Huo-Ting, TUN Fei
Download:   PDF(0KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

The assumption of minimum curvature between adjacent line segments which is used to recover strokes order from offline handwritings is not fully applicable for strokes order recovery from Chinese calligraphic handwriting. A new method based on calligraphic hybrid statisticalstructural 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
CLC:     
  TP 391  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Cite this article:

TUN Yang-Fei, PENG Huo-Ting, TUN Fei. Strokes order recovery based on calligraphic hybrid  statisticalstructural model. J4, 2010, 44(3): 468-472.

URL:

http://www.zjujournals.com/eng/10.3785/j.issn.1008973X.2010.03.010     OR     http://www.zjujournals.com/eng/Y2010/V44/I3/468


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 Xiaoqing. Chinese character recognition: a review ［J］. Chinese Journal of Electronics, 2002, 30(9): 13641368.
［3］ YOSHIHARU K, MAKOTO Y. Recovery of drawing order from singlestrokes handwriting images ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(9): 938949.
［4］ STEFAN J, DAIMLERBENZ A G. Recovering writing traces in offline 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 offline handwriting ［C］// Proceedings of the 4th International Conference on Document Analysis and Recognition. Ulm, Germany: IEEE, 1997: 519522.
［6］ MICHAEL I, ANDREW B. Condensationconditional density propagation for visual tracking ［J］. International Journal of Computer Vision, 1998, 29(1): 528.
［7］ WU Yingfei, ZHUANG Yueting, PAN Yunhe, Web based chinese calligraphy learning with 3D visualization method［C］// Proceedings of ICME. Toronto: IEEE, 2006: 20732076.
[1] NING Zhi-hua, HE Le-nian, HU Zhi-cheng. A high voltage high stability switching-mode controller chip[J]. J4, 2014, 48(3): 377-383.
[2] LI Lin, CHEN Jia-wang,GU Lin-yi, WANG Feng. Variable displacement distributor with valve control for axial piston pump/motor[J]. J4, 2014, 48(1): 29-34.
[3] CHEN Zhao, YU Feng, CHEN Ting-ting. Log-structured even recycle strategy for flash storage[J]. J4, 2014, 48(1): 92-99.
[4] JIANG Zhan, YAO Xiao-ming, LIN Lan-fen. Feature-based adaptive method of ontology mapping[J]. J4, 2014, 48(1): 76-84.
[5] CHEN Di-shi,ZHANG Yu , LI Ping. Ground effect modeling for small-scale unmanned helicopter[J]. J4, 2014, 48(1): 154-160.
[6] HUO Xin-xin, CHU Jin-kui,HAN Bing-feng, YAO Fei. Research on interface circuits of multiple piezoelectric generators[J]. J4, 2013, 47(11): 2038-2045.
[7] YANG Xin, XU Duan-qing, YANG Bing. A parallel computing method for irregular work[J]. J4, 2013, 47(11): 2057-2064.
[8] WANG Yu-qiang,ZHANG Kuan-di,CHEN Xiao-dong. Numerical analysis on interface behavior of
adhesive bonded steel-concrete composite beams[J]. J4, 2013, 47(9): 1593-1598.
[9] CUI He-liang, ZHANG Dan, SHI Bin. Spatial resolution and its calibration method for Brillouin scattering based distributed sensors[J]. J4, 2013, 47(7): 1232-1237.
[10] PENG Yong, XU Xiao-jian. Numerical analysis of effect of aggregate distribution on splitting strength of asphalt mixtures[J]. J4, 2013, 47(7): 1186-1191.
[11] WU Xiao-rong, QIU Le-miao, ZHANG Shu-you, SUN Liang-feng, GUO Chuan-long. Correlated FMEA method of complex system with linguistic vagueness[J]. J4, 2013, 47(5): 782-789.
[12] JIN Bo, CHEN Cheng, LI Wei. Gait correction algorithm of hexapod walking robot
with semi-round rigid feet[J]. J4, 2013, 47(5): 768-774.
[13] ZHONG Shi-ying, WU Xiao-jun, CAI Wu-jun, LING Dao-sheng. Development of horizontal sliding model test facility
 for footpad’s lunar soft landing[J]. J4, 2013, 47(3): 465-471.
[14] YUAN Xing, ZHANG You-yun, ZHU Yong-sheng, HONG Jun，QI Wen-chang. Fault degree evaluation for rolling bearing combining
backward inference with forward inference[J]. J4, 2012, 46(11): 1960-1967.
[15] YANG Fei, ZHU Zhu, GONG Xiao-jin, LIU Ji-lin. Real-time dynamic obstacle detection and tracking using 3D Lidar[J]. J4, 2012, 46(9): 1565-1571.