期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于统计的动态规划算法在联机汉字切分中的应用 被引量：3

Statistics based dynamic programming method for online handwritten character segmentation
下载PDF
导出
摘要 针对中文联机手写文本识别中需要对不同长度的切分路径进行快速合理评价的问题,提出了一种基于后验概率的动态规划代价函数计算方法,结合切分块与切分点的几何信息,利用原始切分块的个数对代价值进行加权。实验证明,该方法有效克服了不同路径长度的负面影响,提高了最优切分路径搜索的准确率。 To solve the problem that rapid and effective evaluation of the segmentation path is needed for online handwritten Chinese text recognition,this paper proposed a statistics based cost function for dynamic programming.It utilized geometrical information of segmentation blocks and points and weighted by the number of segmentation blocks in the original segmentation path.Experiment proves that this method can overcome the shortcoming caused by the variance of length of segmentation paths and increase the accuracy of optimal path search.
作者 姚正斌 丁晓青 刘长松
机构地区 清华大学电子工程系智能系统与技术国家重点实验室
出处 《计算机应用研究》 CSCD 北大核心 2011年第7期2592-2594,共3页 Application Research of Computers
基金 国家"973"计划资助项目(2007CB311004)
关键词 字符切分 动态规划 切分路径 代价函数 后验概率 character segmentation dynamic programming segmentation path cost function posterior probability
分类号 TP391.4 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献9

  • 1张习文 高秀娟 戴国忠.基于多层次信息的连续手写中文的自适应分割方法.计算技术与自动化,2003,22(3):73-77.
  • 2韩勇,须德,戴国忠.MST在手写汉字切分中的应用[J].软件学报,2006,17(3):403-409. 被引量：7
  • 3CORMEN T H, LESERSON C E, RIVEST R L, et al. Introduction to algorithms[ M ]. 2nd ed. Boston : Massachusetts Institute of Technology, 2001.
  • 4TSENG L Y, CHEN R C. Segmenting handwritten Chinese characters based on heuristic merging of stroke bounding boxes and dynamic programming[ J]. Pattern Recognition Letters, 1998,19 ( 10 ) : 963-973.
  • 5GAO Xue, LALLICAN P M, GIARD-GAUDIN C V. A two-stage online handwritten Chinese character segmentation algorithm based on dynamic programming[ C ]//Proc of the 8th ICDAR. Washington DC : IEEE Computer Society,2005:735-739.
  • 6HAN Zhi, LIU Chang-ping. A two-stage handwritten character segmentation approach in mail address recognition [ C ]//Proc of the 8th ICDAR. Washington DC : IEEE Computer Society, 2005 : 111-115.
  • 7ZHOU Xiang-dong, YU Jun-lun, LIU Cheng-lin. Online handwritten japanese character string recognition incorporating geometric context [ C ]//Proc of the 9th ICDAR. 2007:48-52.
  • 8于金伦,周祥东,刘成林.手写字符串识别搜索算法[J].模式识别与人工智能,2009,22(2):182-187. 被引量：2
  • 9ZHU Bi-lan, ZttOU Xiang-dong, LIU Cheng-lin, et al. Effect of improved path evaluation for on-line handwritten Japanese text recognition[ C]//Proc of the 10th ICDAR. Washington DC:IEEE Computer Society,2009:516-520.

二级参考文献13

  • 1韩布新.部件组合──潜在的汉字结构层次[J].中文信息学报,1995,9(3):27-32. 被引量：9
  • 2Fujisawa H, Nakano Y, Kurino K. Segmentation Methods for Character Recognition : From Segmentation to Document Structure Analysis. Proc of the IEEE, 1992, 80(7) : 1079 -1092
  • 3Liu Chenglin, Sako H, Fujisawa H. Effects of Classifier Structures and Training Regimes on Integrated Segmentation and Recognition of Handwritten Numeral Strings. IEEE Trans on Pattern Analysis and Machine Intelligence, 2004, 26 ( 11 ) : 1395 - 1407
  • 4Zhou Xiangdong, Yu Jinlun, Liu Chenglin, et al. Online Handwritten Japanese Character String Recognition Incorporating Geometric Context// Proc of the 9th International Conference on Document A- nalysis and Recognition. Curitiba, Brazil, 2007 : 48 - 52
  • 5Cheriet M, Kharma N, Liu Chengli, et al. Character Recognition Systems: A Guide for Students and Practitioners. New York, USA: John Wiley & Sons, 2007
  • 6Liu Chenglin, Koga M, Fujisawa H. Lexicon-Driven Segmentation and Recognition of Handwritten Character Strings for Japanese Address Reading. IEEE Trans on Pattern Analysis and Machine Intelligence, 2002, 24(11) : 1425 -1437
  • 7Nakagawa M, Zhu Bilan, Onuma M. A Model of Online Handwritten Japanese Text Recognition Free from Line Direction and Writing Format Constraints. IEICE Trans on Information and Systems, 2005, 88(8) : 1815 -1822
  • 8Lee C H, Rabiner L R. A Frame-Synchronous Network Search Algorithm for Connected Word Recognition. IEEE Trans on Acoustics Speech and Signal Processing, 1989, 37( 11 ) : 1649 -1658
  • 9Chen M Y, Kundu A, Srihari S N. Variable Duration Hidden Markov Model and Morphological Segmentation for Handwritten Word Recognition. IEEE Trans on Image Processing, 1995, 4 ( 12 ) : 1675 - 1688
  • 10Kimura F, Takashina K, Tsuruoka S, et al. Modified Quadratic Discriminant Functions and the Application to Chinese Character Recognition. IEEE Trans on Pattern Analysis and Machine Intelligence, 1987, 9(1) : 149 -153

共引文献7

同被引文献33

  • 1林雪松,周婧,林德新.MATLAB7.0应用集锦编程[M].北京:机械工业出版社,2005:115.
  • 2Revuelta-Martínez A, Rodríguez L, García-Varea I.A computer assisted speech transcription system[C]// Proceedings of the Demonstrations at the 13th Conference of theEuropean Chapter of the Association for Computational Linguistics. Berlin. 2012:41-45.
  • 3Sanchis A, Juan A, Vidal E. A word-based Nave Bayes classifier for confidence estimation in speech recognition[J].IEEE Transactions on Audio, Speech, and LanguageProcessing, 2012,20(2):565-574.
  • 4Wang Qiufeng, Yin Fei, Liu Chenglin. Unsupervised language model adaptation for handwritten Chinese text recognition[J].Pattern Recognition, 2014,47(3):1202-1216.
  • 5Sánchez-Sáez R, Leiva L A, Sánchez J A, et al. Interactive predictive parsing using a web-based architecture[C]// Proceedings of the NAACL HLT 2010 DemonstrationSession. Association for Computational Linguistics Stroudsburg. 2010:37-40.
  • 6Serrano N, Sanchis A, Juan A. Balancing error and supervision effort in interactive-predictive handwriting recognition[C]// Proceedings of the 15th InternationalConference on Intelligent User Interfaces. 2010:373-376.
  • 7Farhad M M, Hossain S M, Khan A S, et al. An efficientoptical character recognition algorithm using artificial neural network by curvature properties of characters[C]// 2014 International Conference on Informatics, Electronics & Vision(ICIEV). 2014:1-5.
  • 8Sanchez-Cortina I, Serrano N, Sanchis A, et al. A prototype for interactive speech transcription balancing error and supervision effort[C]// Proceedings of the 2012ACM international conference on Intelligent User Interfaces. 2012:325-326.
  • 9Haiyang L I, Zheng T, Zheng G, et al. Confidence measure based on context consistency using word occurrence probability and topic adaptation for spoken term detection[J].IEICE Transactions on Information and Systems, 2014,97(3):554-561.
  • 10Feenstra R C, Li Z, Yu M. Exports and credit constraints under incomplete information: Theory and evidence fromChina[J].Review of Economics and Statistics, 2014,96(4):729-744.

引证文献3

计算机应用研究
2011年 第7期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部