手写维文字符分割中的多信息融合路径寻优方法

许亚美; 卢朝阳; 李静; 姚超

doi:10.7652/xjtuxb201308012

您当前的位置：

首页 >

文章列表页 >

手写维文字符分割中的多信息融合路径寻优方法

更新时间：2025-05-08

- 手写维文字符分割中的多信息融合路径寻优方法
- A Path Optimization Method Based on Multiple Information Fusion for Handwritten Uyghur Character Segmentation
- 西安交通大学学报 2013年47卷第8期页码：68-73+86
- 作者机构：
  
  西安电子科技大学综合业务网理论及关键技术国家重点实验室,西安,710071
- 作者简介：
- 基金信息：
  
  : 2012-11-03。作者简介: 许亚美(1978—),女,博士生;卢朝阳(通信作者),男,教授,博士生导师。基金项目: 国家自然科学基金资助项目(60872141);中央高校基本科研业务费专项资金资助项目(K50510010007);华为科技基金资助项目(HITC2011023)
- DOI：10.7652/xjtuxb201308012
  中图分类号： TP391.4
- 网络首发：2013-08-10，
  
  纸质出版：2013
- 稿件说明：
移动端阅览
许亚美, 卢朝阳, 李静, 等. 手写维文字符分割中的多信息融合路径寻优方法[J]. 西安交通大学学报, 2013,47(8):68-73+86.

A Path Optimization Method Based on Multiple Information Fusion for Handwritten Uyghur Character Segmentation[J]. 2013, 47(8): 68-73+86.
许亚美, 卢朝阳, 李静, 等. 手写维文字符分割中的多信息融合路径寻优方法[J]. 西安交通大学学报, 2013,47(8):68-73+86. DOI： 10.7652/xjtuxb201308012.

A Path Optimization Method Based on Multiple Information Fusion for Handwritten Uyghur Character Segmentation[J]. 2013, 47(8): 68-73+86. DOI： 10.7652/xjtuxb201308012.

摘要

针对维吾尔词书写粘连和手写笔画漂移等问题

提出一种基于多信息融合路径寻优的字符分割算法。利用笔画提取、切分和聚类

过分割单词图像得到主体和附加字段

通过字段模糊匹配获得鲁棒的字根序列描述

以抑制笔画漂移造成的干扰; 由建立的匹配位置高斯模型来估算字段匹配信息

经对单字分类器输出进行置信度转换

从而得到字符识别信息

再运用数据统计获取单词语义信息; 由构建的字符序列二阶Markov语言模型

基于Bayes准则

提出了单词后验概率的多信息加权融合计算方法

通过字段匹配及字根合并的路径寻优

可得到最佳字符分割结果。在手写维文样本库上的实验表明

所提算法能有效提升字符分割的准确率和稳定性。

Abstract

Character segmentation is a key technique for Uyghur handwriting recognition

but cursive characters and the phenomenon of stroke drift make the segmentation difficult. A new character segmentation algorithm based on multiple information fusion is proposed to solve the problem. Strokes of a word are extracted

segmented and clustered to get two types of sections: main and affix. The robust over-segmentation primitive sequences are obtained using fuzzy section matching to reduce the interference from stroke drift. Then

the matching information is estimated by constructing a matching position Gaussian model. The recognition confidence is converted from character classifier outputs by confidence transformation

and the semantic information is obtained by word data statistics. A character sequences Markov model is presented and the formula to calculate the posterior probability of a word is derived based on the Bayes criterion. The optimal path and the optimal segmentation result are achieved by weighted multiple information fusion. Experiments show that the proposed algorithm can effectively improve the accuracy and stability of character segmentation.

关键词

Keywords

references

宋喆. 现代维吾尔语词汇构成途径新探 [D]. 乌鲁木齐:新疆大学, 2006.

哈力木拉提,阿孜古丽. 多字体印刷维吾尔文字符识别系统的研究与开发 [J]. 计算机学报, 2004,27(11):1480-1484.

HALMURAT, AZIGULI. Research and development of a multifont printed Uyghur character recognition system [J]. Chinese Journal of Computers, 2004,27(11):1480-1484.

靳简明,丁晓青,彭良瑞,等. 印刷维吾尔文本切割 [J]. 中文信息学报, 2005,18(5):76-83.

JIN Jianming, DING Xiaoqing, PENG Liangrui, et al. Printed Uyghur texts segmentation [J]. Journal of Chinese Information Processing, 2005,18(5):76-83.

AZEEM S A, AHMED H. Recognition of segmented online Arabic handwritten characters of the ADAB database [C]∥Proceedings of the 10th IEEE International Conference on Machine Learning and Application. Piscataway, NJ, USA: IEEE, 2011:204-207.

SAEED K, ALBAKOOR M. Region growing based segmentation algorithm for typewritten and handwritten text recognition [J]. Applied Soft Computing, 2009,9(2):608-617.

ABANDAH G A, JAMOUR F T. Recognizing handwritten Arabic script through efficient skeleton-based grapheme segmentation algorithm [C]∥Proceedings of the 10th International Conference on Intelligent Systems Design and Applications. Piscataway, NJ, USA:IEEE, 2010:977-982.

PARVEZ M T, MAHMOUD S A. Arabic handwriting recognition using structural and syntactic pattern attributes [J]. Pattern Recognition, 2013,46(1):141-154.

DING Xiaoqing, LIU Hailong. Segmentation-driven offline handwritten Chinese and Arabic script recognition [M]∥Lecture Notes in Computer Science: Vol.4768. Berlin,Germany: Springer, 2008:196-217.

AL-HAMAD H A, ZITAR R A. Development of an efficient neural-based segmentation technique for Arabic handwriting recognition [J]. Pattern Recognition, 2010,43(8):2773-2798.

BOUKHAROUB A, BENNIA A. Recognition of handwritten Arabic literal amounts using a hybrid approach [J]. Cognitive Computation, 2011,3(2):382-393.

JUAN A, VIDAL E. Comparison of four initialization techniques for the K-medians clustering algorithm [M]∥Lecture Notes in Computer Science: Vol.1876. Berlin, Germany: Springer, 2000:842-852.

ABDELAZEEM S, ERAQI H M. On-line Arabic handwritten personal names recognition system based on HMM [C]∥Proceedings of the 11th IEEE International Conference on Document Analysis and Recognition. Piscataway, NJ, USA: IEEE, 2011:1304-1308.

AL-HAJJ M R, LIKFORMAN-SULEM L, MOKBEL C. Combining slanted-frame classifiers for improved HMM-based Arabic handwriting recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009,31(7):1165-1177.

JIN Lianwen, WEI Gang. Handwritten Chinese character recognition with directional decomposition cellular features [J]. Circuits, Systems and Computers, 1998,8(4):517-524.

KIMURA F, TAKASHINA K, TSURUOKA S, et al. Modified quadratic discriminant functions and its application to Chinese character recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1987,9(1):149-153.

WANG Qiufeng, YIN Fei, LIU Chenglin. Handwritten Chinese text recognition by integrating multiple contexts [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012,34(8):1469-1481.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

融合物理信息与深度算子网络的变压器绕组热-流场快速计算方法

冷库水平空气幕热湿阻隔性能数值模拟研究

电动车辆间接热系统快速除湿响应迟滞机理及优化控制策略

水蒸气掺混对氨裂解气旋流燃烧与排放特性的影响研究

混合电解槽阵列协同的风光耦合制氢系统双层多目标优化