• Articles • Previous Articles     Next Articles

Arabic Word Recognition by Classifiers and Context

Nadir Farah, Labiba Souici, and Mokhtar Sellami   

  1. Computer Science Department, Annaba University, BP 12 Annaba, 23000, Algeria
  • Received:2004-03-19 Revised:2004-12-27 Online:2005-05-10 Published:2005-05-10

Given the number and variety of methods used forhandwriting recognition, it has been shown that there is no singlemethod that can be called the ``best''. In recent years, the combinationof different classifiers and the use of contextual information havebecome major areas of interest in improving recognition results. Thispaper addresses a case study on the combination of multiple classifiersand the integration of syntactic level information for the recognitionof handwritten Arabic literal amounts. To the best of our knowledge,this is the first time either of these methods has been applied toArabic word recognition. Using three individual classifiers with highlevel global features, we performed word recognition experiments. Aparallel combination method was tested for all possible configurationcases of the three chosen classifiers. A syntactic analyzer makes afinal decision on the candidate words generated by the bestconfiguration scheme. The effectiveness of contextual knowledgeintegration in our application is confirmed by the obtained results.

Key words: Eiffel language; multiple inheritance; renaming; static analysis; semantic domains; semantic functions;

[1] Madhvanath S, Govindaraju V. The role of holistic paradigms inhandwritten word recognition. IEEE Trans. Pattern Analysis andMachine Intelligence, February 2001, 23(2): 149--164.

[2] Steinherz T, Rivlin E, Intrator N. Off-line cursive script wordrecognition: A survey. International Journal on Document Analysisand Recognition, IJDAR, 1999, 2(2): 1--33.

[3] Suen C Y. Rèflexions sur la reconnaissance de l’ècriturecursive. In Proc. CIFED'98, 1er Colloque International Francophonesur l'Ecrit et le Document, Mai 1998, Quèbec, Canada, pp.1--8.

[4] Impedevo S, Wang P S P, Bunke H (eds.). Automatic bankcheckprocessing. Series in Machine Perception and ArtificialIntelligence, World Scientific, 1997, Vol. 28.

[5] Amin A. Off-line Arabic character recognition: The state of theart. Pattern Recognition, 1998, 31(5): 517--530.

[6] Al Badr B, Mahmoud S A. Survey and bibliography of Arabic opticaltext recognition. Signal Processing, 1995, 41(1): 49--77.

[7] Essoukhri Ben Amara N. Sur la problèmatique et les orientations enreconnaissance de l'ècriture Arabe. In Proc. CIFED 2002, Hammamet 2002, Tunisia, pp.1--8.

[8] Pechwitz M, Maergner V. HMM based approach for handwritten Arabicword recognition using the IFN/ENITdatabase. In Proc. 7thInternational Conference on Document Analysis and Recognition,(ICDAR), Edinburgh, Scotland, August 2003.

[9] Snoussi-Maddouri S, Amiri H, Belaid A, Choisy C. Combination oflocal and global vision modeling for Arabic handwritten wordrecognition. In Proc. International Workshop Frontier in HandwritingIWFHR'02, Ontario, Canada, August 6--8, 2002, pp.128--138.

[10] Souici L, Aoun A, Sellami M. Global recognition system for Arabicliteral amounts. In Proc. International Conference on ComputerTechnologies and Applications, ICCTA'99, August 1999, Alexandria,Egypt.

[11] Farah N, Souici L, Sari T, Sellami M. Knowledge based artificialneural network for Arabic city name recognition. WSEASTransactions on Systems, April 2004, 3(2): 767--771.

[12] Souici-Meslati L, Sellami M. A hybrid approach for Arabic literalamounts recognition. AJSE, the Arabian Journal of Science andEngineering, October 2004, 29:2B.(2): 177--194.

[13] Xu L, Krzyzak A, Suen C Y. Methods of combining multipleclassifiers and their applications to handwriting recognition. IEEE Transactions on systems. Man, and cybernetics, May/June 1992,22(3): 418--435.

[14] Dengel A, Hoch R, Hones F, Jager T, Malburg M, Weigel A.Techniques for improving OCR results. Handbook of CharacterRecognition and Document Image Analysis, Bunke H, Wang P S P (eds.),World Scientific, 1997, pp.227--258.

[15] Ruta D, Gabrys B. An overview of classifier fusion methods. Computing and Information Systems, University of Paisley, February2000, 7(1): 1--10.

[16] Pavlidis T. Algorithms for graphic and image processing.Rockville, MD: -Computer Science Press , 1982.

[17] Belaid A, Belaid Y. Reconnaissance des formes: Mèthodes etapplications. -InterEditions , 1992.

[18] Otsu N. A threshold selection method from gray-level histogram. IEEE Transaction Systems, Man Cybernetics, 1979, 9(1): 62--66.

[19] Ameur A, Romeo-Pakker K, Miled H, Cheriet M. Approche globale pourla reconnaissance de mots manuscrits Arabes. In Proc. CNED'94, 3èmeColloque National sur l'Ecrit et le Document, Juillet 1994, pp.151--156.

[20] Jain A K, Mao J, Mohiuddin K. Artificial neural networks: Atutorial. IEEE Computers, Special Issue on Neural Computing, March1996, 9(3): 31--44.

[21] Bishop C M. Neural networks for pattern recognition.Clarendon Press, Oxford, 1995.

[22] Singh S, Amin A. Fuzzy Recognition of Chinese Characters. InProc. Irish Machine Vision and Image Processing Conference(IMVIP'99), Dublin, September 8--9, 1999, pp.219--227.

[23] Duin R P W. The combining classifier: To train or not to trainIn Proc. 16th International Conference on Pattern Recognition, QuebecCity, Canada, August 11--15, 2002, Vol. 2, pp.765--770.

[24] Jain A K, Duin R P W, Mao J. Statistical pattern recognition: Areview. IEEE Transactions on Pattern Analysis and MachineIntelligence, January 2000, 22(1): 4--38.

[25] Kittler J, Hatef M, Duin R P W, Matas J. On combining classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence,March 1998, 20(3): 226--239.

[26] Paquet T, Lecourtier Y. Recognition of handwritten sentences usinga restricted lexicon. Pattern Recognition, March 1993,26(3): 391--407.

[27] Guillevic D. Unconstrained handwriting recognition applied to theprocessing of bank cheques

[Dissertation]. Computer ScienceDepartment, Concordia University, Montreal, Canada, September 1995.

[28] Di Lecce V, Dimauro G, Guerriero A et al. A newhybrid approach for legal amount recognition. In Proc. 7thInternational Workshop on Frontiers in Handwriting Recognition,IWFHR'2000, Amsterdam, The Netherlands, September 2000, pp.199--208.

[29] Al-Ohali Y, Cheriet M, Suen C Y. Databases for recognition ofhandwritten Arabic cheques. Pattern Recognition, 2003,36(1): 111--121.
[1] Gen Zhang, Peng-Fei Wang, Tai Yue, Xu Zhou, Kai Lu. MEBS: Uncovering Memory Life-Cycle Bugs in Operating System Kernels [J]. Journal of Computer Science and Technology, 2021, 36(6): 1248-1268.
[2] Feng-Juan Gao, Yu Wang, Lin-Zhang Wang, Zijiang Yang, Xuan-Dong Li. Automatic Buffer Overflow Warning Validation [J]. Journal of Computer Science and Technology, 2020, 35(6): 1406-1427.
[3] Jung-Been Lee, Taek Lee, Hoh Peter In. Topic Modeling Based Warning Prioritization from Change Sets of Software Repository [J]. Journal of Computer Science and Technology, 2020, 35(6): 1461-1479.
[4] Gökçer Peynirci, Mete Eminaǧaoǧlu, Korhan Karabulut. Feature Selection for Malware Detection on the Android Platform Based on Differences of IDF Values [J]. Journal of Computer Science and Technology, 2020, 35(4): 946-962.
[5] Ling-Yun Situ, Student Member, CCF, Lin-Zhang Wang, Distinguished Member, CCF, Yang Liu, Member, ACM, IEEE, Bing Mao, Xuan-Dong Li, Fellow, CCF. Automatic Detection and Repair Recommendation for Missing Checks [J]. Journal of Computer Science and Technology, 2019, 34(5): 972-992.
[6] Ming-Zhe Zhang, Yun-Zhan Gong, Ya-Wen Wang, Da-Hai Jin. Unit Test Data Generation for C Using Rule-Directed Symbolic Execution [J]. Journal of Computer Science and Technology, 2019, 34(3): 670-689.
[7] Ji Wang, Senior Member, CCF, Xiao-Dong Ma, Wei Dong, Hou-Feng Xu, and Wan-Wei Liu, Member, CCF. Demand-Driven Memory Leak Detection Based on Flow- and Context-Sensitive Pointer Analysis [J]. , 2009, 24(2): 347-356.
[8] Wei-Wu Hu, Fu-Xin Zhang, and Zu-Song Li. Microarchitecture of the Godson-2 Processor [J]. , 2005, 20(2): 0-0.
[9] ZHANG WenHui . Combining Static Analysis and Case-Based Search Space Partitioning for Reducing Peak Memory in Model Checking [J]. , 2003, 18(6): 0-0.
[10] NIE Xumin; GUO Qing;. Renaming a Set of Non-Horn Clauses [J]. , 2000, 15(5): 409-415.
[11] NIE Xumin(聂旭民)and GUO Qing(郭青). Renaming a Set of Non-Horn Clauses [J]. , 2000, 15(5): 0-0.
[12] LIAO Husheng;. An Action Analysis for Combining Partial Evaluation [J]. , 2000, 15(2): 196-201.
[13] Qu Yuzhong; Wang Zhijian; Xu Jiafu;. Denotational Semantics of a Simple Model of Eiffel [J]. , 1995, 10(3): 214-226.
Full text



[1] Lian Lin; Zhang Yili; Tang Changjie;. A Non-Recursive Algorithm Computing Set Expressions[J]. , 1988, 3(4): 310 -316 .
[2] Ian Foster. Globus Toolkit Version 4: Software for Service-Oriented Systems[J]. , 2006, 21(4): 513 -520 .
[3] Min-Yi Guo, Zi-Li Shao, Edwin Hsing-Mean Sha. Preface[J]. , 2011, 26(3): 373 -374 .
[4] Peter Szolovits. Possibilities for Healthcare Computing[J]. , 2011, 26(4): 625 -631 .
[5] Feng Wang (王锋) Member, CCF, ACM, Can-Qun Yang (杨灿群), Yun-Fei Du (杜云飞), Juan Chen (陈娟), Hui-Zhan Yi (易会战), and Wei-Xia Xu (徐炜遐). Optimizing Linpack Benchmark on GPU-Accelerated Petascale Supercomputer[J]. , 2011, 26(5): 854 -865 .
[6] Jorge Martinez-Gil, Member, ACM, and Jos? F. Aldana-Montes. KnoE: A Web Mining Tool to Validate Previously Discovered Semantic Correspondences[J]. , 2012, 27(6): 1222 -1232 .
[7] Liang-Jun Zang, Cong Cao, Ya-Nan Cao, Yu-Ming Wu, and Cun-Gen Cao. A Survey of Commonsense Knowledge Acquisition[J]. , 2013, 28(4): 689 -719 .
[8] Shuo Shang, Lisi Chen, Zhe-Wei Wei, Dan-Huai Guo, Ji-Rong Wen. Dynamic Shortest Path Monitoring in Spatial Networks[J]. , 2016, 31(4): 637 -648 .
[9] An-Zhen Zhang, Jian-Zhong Li, Hong Gao, Yu-Biao Chen, Heng-Zhao Ma, Mohamed Jaward Bah. CrowdOLA: Online Aggregation on Duplicate Data Powered by Crowdsourcing[J]. , 2018, 33(2): 366 -379 .
[10] Su Zhang, Hua-Qian Cai, Yun Ma, Tian-Yue Fan, Ying Zhang, Gang Huang. SmartPipe: Towards Interoperability of Industrial Applications via Computational Reflection[J]. Journal of Computer Science and Technology, 2020, 35(1): 161 -178 .

ISSN 1000-9000(Print)

CN 11-2296/TP

Editorial Board
Author Guidelines
Journal of Computer Science and Technology
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
E-mail: jcst@ict.ac.cn
  Copyright ©2015 JCST, All Rights Reserved