본문 바로가기
KERD
논문KCI 등재

Graphemes Segmentation for Arabic Online Handwriting Modeling

Adel M. Alimi|Houcine Boubaker|Najiba Tagougui|Haikal El Abed|Monji Kherallah
한국정보처리학회|2014.12|JIPS(Journal of Information Processing Systems) (Journal of Information Processing Systems)|제10권 제4호|pp. 503-522|DOI http://dx.doi.org/10.3745/JIPS.02.0006

2

조회

0

다운로드

0

인용

0

참고문헌

키워드

Baseline DetectionDiacritic FeaturesFourier DescriptorsGeometric ParametersGrapheme SegmentationOnline Arabic Handwriting Modeling

초록

In the cursive handwriting recognition process, script trajectory segmentationand modeling represent an important task for large or open lexicon context thatbecomes more complicated in multi-writer applications. In this paper, we will present adeveloped system of Arabic online handwriting modeling based on graphemessegmentation and the extraction of its geometric features. The main contributionconsists of adapting the Fourier descriptors to model the open trajectory of the segmentedgraphemes. To segment the trajectory of the handwriting, the system proceeds by firstdetecting its baseline by checking combined geometric and logic conditions. Then, thedetected baseline is used as a topologic reference for the extraction of particular pointsthat delimit the graphemes’ trajectories. Each segmented grapheme is then representedby a set of relevant geometric features that include the vector of the Fourier descriptorsfor trajectory shape modeling, normalized metric parameters that model the graphemedimensions, its position in respect to the baseline, and codes for the description of itsassociated diacritics.

Abstract

In the cursive handwriting recognition process, script trajectory segmentationand modeling represent an important task for large or open lexicon context thatbecomes more complicated in multi-writer applications. In this paper, we will present adeveloped system of Arabic online handwriting modeling based on graphemessegmentation and the extraction of its geometric features. The main contributionconsists of adapting the Fourier descriptors to model the open trajectory of the segmentedgraphemes. To segment the trajectory of the handwriting, the system proceeds by firstdetecting its baseline by checking combined geometric and logic conditions. Then, thedetected baseline is used as a topologic reference for the extraction of particular pointsthat delimit the graphemes’ trajectories. Each segmented grapheme is then representedby a set of relevant geometric features that include the vector of the Fourier descriptorsfor trajectory shape modeling, normalized metric parameters that model the graphemedimensions, its position in respect to the baseline, and codes for the description of itsassociated diacritics.

참고문헌 (44)

  1. R. Plamondon, "On-line and off-line handwriting recognition: a comprehensive Survey", IEEE Transaction on Pattern Analysis and Machine Intelligence, 22(1), pp.63~84 (2000)
  2. M. Pechwitz, "Baseline Estimation For Arabic Handwritten Words", Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition IWFHR, pp.479~484 (2002)
  3. S. Snoussi Maddouri, "Baseline extraction: comparison of six methods on IFN", ENIT database, 2008, 571~576
  4. C. Olivier, "Segmentation and Coding of Arabic Handwritten Words", Proceeding of the International Conference on Pattern Recognition 13th ICPR, pp.264~268 (1996)
  5. E. Persoon, "Shape Discrimination using Fourier descriptors", IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(3), pp.388~397 (1986)
  6. M. Kherallah, "Online Arabic Handwriting Recognition Competition", Proceedings of the 11th International Conference on Document Analysis and Recognition, pp.1454~1459 (2011)
  7. B. Al-Badr, "Survey and bibliography of Arabic optical text recognition", Signal Processing, pp.49~77 (1995)
  8. S. Garcia-Salicetti, "A hybrid Neural Predictive Model for On-Line Handwriting Recognition", World Multiconference on Systemics, Cybernetics and Informatics SCI'97, pp.316~323 (1997)
  9. H. Eraqi, "An on-line Arabic handwriting recognition system based on a new on-line graphemes segmentation technique", Proceedings of the 11th International Conference on Document Analysis and Recognition, pp.409~413 (2011)
  10. R. I. Elanwar, "Simultaneous segmentation and recognition of Arabic characters in an unconstrained on-line cursive handwritten document", Proceedings of World Academy of Science, Engineering and Technology (WASET), pp.288~291 (2007)
  11. A. Elbaati, "Arabic handwriting recognition using restored stroke chronology", Proceedings of the International Conference on Document Analysis and Recognition, pp.411~415 (2009)
  12. L. Likforman-Sulem, "A hough based algorithm for extraction text lines in handwritten documents", Proceedings of the third International Conference on Document Analysis and Recognition, pp.774~777 (1995)
  13. H. Boubaker, "Online Arabic handwriting modeling system based on the graphemes segmentation", Proceedings of the 20th International Conference on Pattern Recognition, pp.2061~2064 (2010)
  14. A. Hennig, "Zone-Estimation for Multiple Lines of Handwriting Using Approximate Spline Functions", Proceedings of the 5th International Workshop Frontiers in Handwriting Recognition, pp.325~328 (1996)
  15. Z. Razak, "Off-line handwriting text line segmentation : a review", International Journal of Computer Science and Network Security, 8(7), pp.12~20 (2008)
  16. M. A. Abuzaraida, "Segmentation techniques for online Arabic handwriting recognition: a survey", Proceeding of 3rd International Conference on ICT4M, pp.D37~D40 (2010)
  17. S. Izadi, "A new segmentation algorithm for online handwritten word recognition in persian script", Proceedings of the International Conference on Frontiers in Handwriting Recognition, pp.1140~1142 (2008)
  18. K. Daifallah, "Recognition-based segmentation algorithm for on-line Arabic handwriting", Proceedings of the International Conference on Document Analysis and Recognition, pp.877~880 (2009)
  19. J. Sternby, "On-line Arabic handwriting recognition with templates", Pattern Recognition Journal, 42(12), pp.3278~3286 (2009)
  20. M. Liwicki, "A novel approach to on-line handwriting recognition based on bidirectional long short-term memory networks", Proceedings of the 9th International Conference on Document Analysis and Recognition, pp.367~371 (2007)
  21. A. Graves, "A novel connectionist system for unconstrained handwriting recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(5), pp.855~868 (2009)
  22. M. Liwicki, "Combining diverse on-line and off-line systems for handwritten text line recognition", Pattern Recognition, 42(12), pp.3254~3263 (2009)
  23. J. Schenk, "Novel script line identification method for script normalization and feature extraction in on-line handwritten whiteboard note recognition", Pattern Recognition Journal, 42(12), pp.3383~3393 (2009)
  24. A. M. Alimi, "Evolutionary neuro-fuzzy approach to recognize on-line Arabic handwriting", Proceedings of the 4th International Conference on Document Analysis and Recognition, pp.382~386 (1997)
  25. N. Mezghani, "Bayes classification of online Arabic Characters by Gibbs modeling of class conditional densities", IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(7), pp.1121~1131 (2008)
  26. M. Kherallah, "On-line handwritten digit recognition based on trajectory and velocity modeling", Pattern Recognition Letters, 29(5), pp.580~594 (2008)
  27. M. Kherallah, "On-line Arabic handwriting recognition system based on visual encoding and genetic algorithm", Engineering Applications of Artificial Intelligence, 22(1), pp.153~170 (2009)
  28. Ming Ma, "Online Recognition of Handwritten Korean and English Characters", JIPS(Journal of Information Processing Systems), 8(4), pp.653~668 (2012), 한국정보처리학회
  29. T. Al-Sheikh, "Real-time Arabic handwritten character recognition", Pattern Recognition, 23(12), pp.1323~1332 (1990)
  30. N. Mezghani, "On-line recognition of handwritten Arabic characters using a Kohonen neural network", Proceeding of the International Workshop on Frontiers in Handwriting Recognition, pp.490~495 (2002)
  31. N. Mezghani, "Combination of pruned Kohonen maps for on-line Arabic characters recognition", Proceedings of the 7th International Conference on Document Analysis and Recognition, pp.900~905 (2003)
  32. A. M. Alimi, "Evolutionary computation for the recognition of on-line cursive handwriting", IETE Journal of Research, 48(5), pp.385~396 (2002)
  33. H. Boubaker, "New strategy for the on-line handwriting modelling", Proceedings of the 9th International Conference on Document Analysis and Recognition, pp.1233~1247 (2007)
  34. R. Plamondon, "Speed", accuracy trade-offs in target-directed movements, 1997, pp.20(2), 279~349
  35. H. Boubaker, "Handwriting and hand drawing velocity modeling by superposing beta impulses and continuous training component", International Journal of Computer Science Issues, 10(5), pp.57~63 (2013)
  36. Ch. C. Tappert, "The state of the art in on-line handwriting recognition", IEEE Transaction on Pattern Analysis and Machine Intelligence, 12(8), pp.787~808 (1990)
  37. H. Boubaker, "New algorithm of straight or curved baseline detection for short Arabic handwriting writing", Proceedings of the 10th International Conference on Document Analysis and Recognition, pp.778~782 (2009)
  38. G. Menier, "A new modeling method for on-line handwriting recognition", Proceedings of the 3rd International Conference on Document Analysis and Recognition, pp.499~503 (1995)
  39. M. Côté, "Automatic reading of cursive scripts using human knowledge", Proceedings of the 9th International Conference on Document Analysis and Recognition, pp.107~111 (2007)
  40. P. Nagabhushan, "Geometric model and projection based algorithms for tilt correction and extraction of acsenders", descenders for cursive word recognition, 2007, 488~491
  41. N. Tagougui, "Online Arabic handwriting recognition: a survey", International Journal on Document Analysis and Recognition, 16(3), pp.209~226 (2012)
  42. A. Chaabouni, "Static and dynamic features for writer identification based on multi-fractals", International Arabic Journal on Information Technologies, 11(4), pp.416~424 (2014)
  43. M. Hamdani, "Combining multiple HMMs using on-line and off-line features for off-line arabic handwriting recognition", Proceedings of the 10th International Conference on Document Analysis and Recognition, pp.201~205 (2009)
  44. Ph. Dreuw, "White-space models for offline Arabic handwriting recognition", Proceedings of the International Conference on Pattern Recognition, pp.1~4 (2008)

관련 논문AI추천

Online Recognition of Handwritten Korean and English Characters김수균, 박동원, 안성옥, Ming Ma한국정보처리학회 · JIPS(Journal of Information Processing Systems)2012 · 제8권 제4호Stroke Width-Based Contrast Feature for Document Image Binarization이귀상, Le Thi Khue Van한국정보처리학회 · JIPS(Journal of Information Processing Systems)2014 · 제10권 제1호Character Segmentation in Chinese Handwritten Text Based on Gap and Character Construction Estimation이귀상, ChengDong Zhang한국콘텐츠학회 · International Journal of Contents2012 · 제8권 제1호A Contour Descriptors-Based Generalized Scheme for Handwritten Odia Numerals RecognitionBanshidhar Majhi, Ratnakar Dash, Tusar Kanti Mishra한국정보처리학회 · JIPS(Journal of Information Processing Systems)2017 · 제13권 제1호Fuzzy-Membership Based Writer Identification from Handwritten Devnagari ScriptKiran Kumar Ravulakollu, Rajesh Bhat, Rajiv Kumar한국정보처리학회 · JIPS(Journal of Information Processing Systems)2017 · 제13권 제4호Text Line Segmentation using AHTC and Watershed Algorithm for Handwritten Document Images김광복, 김수형, 나인섭, 오강한한국콘텐츠학회 · International Journal of Contents2014 · 제10권 제3호

이 간행물의 다른 논문 (10건)

On the Performance of Oracle Grid Engine Queuing System for Computing Intensive ApplicationsVladi Kolici, Fatos Xhafa, Albert Herreropp. 491-502The Accuracy of the Non-continuous I Test for One- Dimensional Arrays with References Created by Induction VariablesQing Zhangpp. 523-542Design and Implementation of a Content Model for m-Learning손진곤, 김병욱pp. 543-554Multimodal Biometric Using a Hierarchical Fusion of a Person’s Face, Voice, and Online SignatureRéda Adjoudj, Youssef Elmir, Zakaria Elberrichipp. 555-567Performance Evaluation of the WiMAX Network under a Complete Partitioned User Group with a Traffic Shaping AlgorithmJesmin Akhter, M. R. Amin, Md. Imdadul Islampp. 568-580
원문 보기