Printed Arabic Sub-Word Recognition Using Moments

the cursive nature of the Arabic writing makes it difficult to accurately segment characters or even deal with the whole word efficiently. Therefore, in this paper, a printed Arabic sub-word recognition system is proposed. The suggested algorithm utilizes geometrical moments as descriptors for the separated sub-words. Three types of moments are investigated and applied to the printed sub-word images after dividing each image into multiple parts using windowing. Since moments are global descriptors, the windowing mechanism allows the moments to be applied to local regions of the sub-word. The local-global mixture of the proposed scheme increases the discrimination power of the moments while keeping the simplicity and ease of use of moments.

Authors:

• Ibrahim A. El rube
• Mohamed T. El Sonni
• Soha S. Saleh

Keywords:

• Arabic sub-word recognition
• windowing
• aspectratio
• moments.

References:

[1] Lorigo, L.M. Govindaraju, "Offline Arabic handwriting recognition: a
survey", IEEE Computer Society; pp. 712-724, vol. 28 no. 5, 2006.
[2] Jamshid Shanbehzadeh, Hamed Pezashki, Abdolhossein Sarrafzadeh,
"Feature Extraction from Farsi Handwritten letters", Proceedings of
Image and Vision Computing New Zealand 2007, pp. 35-40, Hamilton,
New Zealand, December 2007.
[3] Aburas, Abdurazzag Ali Gumah, Mohamed E., "Arabic Handwriting
Recognition: Challenges and Solutions", International Symposium on
Information Technology, ITSim, 26-28 Aug. 2008, vol 2, pages 1-6,
2008.
[4] Al-Hajj Mohamad, R.; Likforman-Sulem, L.; Mokbel,
C.; "Combining Slanted-Frame Classifiers for Improved HMM-based
Arabic Handwriting Recognition", IEEE Transactions on Pattern
Analysis and Machine Intelligence, Vol. 31, No. 7, pp. 1165-1177,
2009.
[5] Abdulaziz, E.Alsaif, K.I., "Radon Transformation for Arabic Character
Recognition", International conference on Computer and
Communication Engineering, Kuala Lumpur, Malaysia, 13-15 May
2008, pages 433-438, 2008.
[6] Aburas, A.A.; Rehiel, S.A., "Off Line Tool for Arabic Handwritten
Character Recognition Based On JPEG2000 Image Compression",
ICTTA, Kuala Lumpur, Malaysia, 7-11 April 2008, pp. 1 - 5, 2008.
[7] Mona Omidyeganeh, Reza Azmi, Kambiz Nayebi and Abbas Javadtalab,
"A New Method to improve Multi Font Farsi/Arabic Character
Segmentation Results: Using Extra Classes of Some Character
Combinations", Multimedia Modeling Conference, Nanyang
Technological University, Singapore MMM2007, pages 670-679, 2007.
[8] Zidouri, "A PCA-based Arabic Character feature extraction", 9th
International Symposium on Signal Processing and Its Applications,
Sharjah, UAE, 12-15 Feb. 2007, pp. 1 - 4, 2007.
[9] Mahmoud, S.A. Mahmoud, A.S., "Arabic Character Recognition using
Modified Fourier Spectrum (MFS)", Cybernetics and Systems, Vol. 40,
No. 3, April 2009, pp. 189 - 210.
[10] Gregory R Ball, Sargur N Srihari, Harish Srinivasan, "Segmentation-
Based And Segmentation-Free Methods for Spotting Handwritten
Arabic Words", Tenth International Workshop on Frontiers in
Handwriting Recognition, CEDAR 2006.
[11] Sargur N. Srihari, Gregory R. Ball and Harish Srinivasan. "Versatile
Search of scanned Arabic Handwriting", Arabic and Chinese
Handwriting Recognition, LNCS 4768, Springer 2008, pp. 57-69, 2008.
[12] Jawad H AlKhateeb, Jianmin Jiang, Jinchang Ren, and Stan S Ipson,
"Component-based Segmentation of Words from Handwritten Arabic
Text", World Academy of Science, Engineering and Technology, vol.
41, pp.344-348, 2008.
[13] Gheith Abandah, Nasser Anssari, "Novel moment features extraction for
recognizing handwritten Arabic letters", Journal of Computer Science,
vol. 5, No. 3, March, 2009, pp. 226-232.