Correlation matching recognition algorithm based on character normalized double projection

doi:10.3724/SP.J.1087.2013.00645

Journal of Computer Applications ›› 2013, Vol. 33 ›› Issue (03): 645-647.DOI: 10.3724/SP.J.1087.2013.00645

• Network and distributed techno • Previous Articles Next Articles

Correlation matching recognition algorithm based on character normalized double projection

WAN Jin'e^1,2*, YUAN Baoshe^1,2, GU Zhao³, Mirsali SABIT^1,2

1.School of Information Science and Engineering, Xinjiang University, Xinjiang Urumqi 830046, China;
2.Key Laboratory of Multilingual Information Technology, Xinjiang University, Xinjiang Urumqi 830046, China;
3.School of Mathematics and System Science, Xinjiang University, Xinjiang Urumqi 830046, China

Received:2012-09-28 Revised:2012-12-12 Online:2013-03-01 Published:2013-03-01

基于字符归一化双投影互相关性匹配识别算法

万金娥^1,2*,袁保社^1,2,谷朝³,米尔沙力江·沙吾提^1,2

1.新疆大学信息科学与工程学院,乌鲁木齐 830046;
2.新疆大学新疆多语种信息技术重点实验室,乌鲁木齐 830046;
3.新疆大学数学与系统科学学院,乌鲁木齐 830046

通讯作者: 万金娥
作者简介:万金娥(1987-),女,甘肃玉门人,硕士研究生,主要研究方向:图形图像识别处理; 袁保社(1955-),男,新疆乌鲁木齐人,教授,主要研究方向:图形图像处理、电路理论、信号处理; 谷朝(1987-),男,山东菏泽人,硕士研究生,主要研究方向:图论、组合数学; 米尔沙力江·沙吾提(1985-),男(维吾尔族),新疆喀什人,硕士研究生,主要研究方向:图形图像识别处理。
基金资助:
工业和信息化部电子信息产业发展基金资助项目(工信部财[2009]453)。

Abstract

Abstract: Since the correct character recognition rate of the printed Uighur character recognition system is low, in this study, a character image was scanned in both horizontal and vertical directions to create a row-projection vector and a column-projection map. In combination with three levels of classification, the target character with the corresponding classification characters' double projection maps was normalized individually, and the correlation mean calculation was carried out. The maximum mean character was taken as the best match recognition result, so as to implement the Uighur character recognition. The correlation matching recognition algorithm based on character normalized double projection method has been proved by experiment that it has the advantages of strong anti-interference, simple implementation, high matching accuracy, thus improving the correct rate of the printed Uighur character recognition.

Key words: printed Uyghur, double integral projection map, projection map normalization, mutual correlation, template matching recognition

摘要： 针对印刷体维吾尔文文字识别系统中的字符识别正确率较低这一难点问题,采用对字符图像进行横向扫描和纵向扫描生成行和列投影图, 结合三级分类,将目标字符与对应分类中的字符的双投影图逐一归一化并进行相关性均值计算的方法,取均值最大的字符作为最佳匹配识别结果,实现了对维文字符的识别。实验证明这种基于字符归一化双投影互相关性匹配识别算法方法抗干扰性强,简单易行,匹配精度高,使得印刷体维吾尔文字字符识别的正确率有了进一步提高。

关键词: 印刷体维吾尔文, 双积分投影图, 投影图归一化, 互相关性, 模板匹配识别

CLC Number:

TP317.4

万金娥袁保社谷朝米尔沙力江·沙吾提. 基于字符归一化双投影互相关性匹配识别算法[J]. 计算机应用, 2013, 33(03): 645-647.

References

[1]尹芳,王卫兵,陈德运.印刷体英文文档识别系统的设计与实现[J].哈尔滨理工大学学报,2008,13(6): 9-12.
[2]刘聚宁.印刷体汉字识别系统研究与实现[D].大连:大连理工大学,2011.
[3]哈力木拉提·买买提.多字体印刷维吾尔文识别系统的研究与实现[J].计算机学报,2004,27(11): 1480-1484.
[4]袁保社,吾守尔·斯拉木.一种手写维吾尔文字母识别算法[J].计算机工程,2010,36(2): 186-188.
[5]欧珠,普次仁,大罗桑朗杰,等.印刷体藏文文字识别技术研究[J].计算机工程与应用,2009,45(24): 165-172.
[6]张宏涛,龙翀,朱小燕,等.印刷体汉字识别后处理方法的研究[J].中文信息学报,2009,23(6):67-71.
[7]李晓,袁保社,陈卿,等.基于像素积分投影的印刷体维文字母切分方法[J].计算机技术与发展,2012,22(4): 41-44.
[8]哈力木拉提·买买提.基于轮廓的维吾尔文切分[C]// 第十一届全国民族语言文字信息学术研讨会论文集.北京:中国中文信息学会民族语言文字信息专业委员会,2007.
[9]陈卿.印刷体维吾尔文识别系统分类识别技术研究[D].乌鲁木齐:新疆大学,2012.
[10]周治紧,李玉鑑.基于投影归一化的字符特征提取方法[J].计算机工程,2006,32(2): 197-199.
[11]牛刚,梁伟.基于特征像素统计的图像相关匹配算法[J].微计算机信息,2005,21(33) : 103-107.
[12]王宇旸.基于可重构计算技术的图像识别与分类系统研究[D].合肥:中国科学技术大学,2009.
[13]BISDSY F, EI-SANA J, HABASH N. Online Arabic handwriting recognition using hidden Markov models[M]. New York: World Intellectual Property Organization, 2008.
[14]JIN J M, PENG L G, DING X Q. Printed Uyghur character recognition [C]// Proceedings of the 5th China Korea Joint Symposium on Oriental Language Processing and Pattern Recognition. Qingdao: [s.n.], 2004:59-62.

Correlation matching recognition algorithm based on character normalized double projection

基于字符归一化双投影互相关性匹配识别算法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 3

Recommended Articles

Metrics

[1]	ZHUANG Yanbin GUI Yuan XIAO Xianjian. Compressed Video Sensing Method Based on Motion Estimation and Backtracking based Adaptive Orthogonal Matching Pursuit [J]. Journal of Computer Applications, 2013, 33(09): 2577-2579.
[2]	CUI Xueying ZHANG Quan GUI Zhiguo. Non-local means denoising approach based on dictionary learning [J]. Journal of Computer Applications, 2013, 33(05): 1420-1422.
[3]	YANG Bing-qing TIAN Xiao-ping WU Cheng-mao. Enhancement algorithm for color images based on co-occurrence matrix [J]. Journal of Computer Applications, 2012, 32(09): 2573-2575.