Abstract

Arabic character recognition is a challenging problem in several artificial intelligence applications, especially when recognizing connected cursive letters. Another dimension of complexity is that Arabic characters may form various shapes depending on their positions in the word. As a result, unconstrained handwritten Arabic character recognition has not been well explored. In this study, we propose an efficient algorithm for Arabic character recognition. The new algorithm combines features extracted from curvelet and spatial domains. The curvelet domain is multiscale and multidirectional. Therefore, curvelet domain is efficient in representing edges and curves. Meanwhile, the spatial domain preserves original aspects of the characters. This feature vector is then trained using the back propagation neural network for the recognition task. The proposed algorithm is evaluated using a database containing 5,600 handwritten characters from 50 different writers. A promising average success rate of 90.3% has been achieved. Therefore, the proposed algorithm is suitable for the unconstrained handwritten Arabic character recognition applications.

Keywords:

Character database, curvelet transform, neural network, optical character recognition,

References

1. Abandah, G. and N. Anssari, 2009. Novel moment features extraction for recognizing handwritten Arabic letters. J. Comput. Sci., 5(3): 226.
   CrossRef    
2. Abandah, G.A. and F.T. Jamour, 2010. Recognizing handwritten Arabic script through efficient skeleton-based grapheme segmentation algorithm. Proceeding of the Conference on Intelligent Systems Design and Applications (ISDA), pp: 977-982.
   CrossRef    
3. Aburas, A.A. and S. Ali Rehiel, 2007. Handwriting Arabic character recognition using haar wavelet compression. Proceeding of the International Conference on Intelligent and Advanced Systems (ICIAS’2007), pp: 793-797.
   CrossRef    
4. Alginahi, Y.M., 2013. A survey on Arabic character segmentation. Int. J. Doc. Anal. Recog., 16(2): 1-22.
   CrossRef    
5. Ali, M.A. and K. Jumari, 2004. Skeletonization algorithm for Arabic handwriting. Arab Gulf J. Sci. Res., 22(1): 28-33.
   
6. Al-Jawfi, R., 2009. Handwriting Arabic character recognition LeNet using neural network. Int. Arab J. Inf. Techn., 6(3).
   
7. Arica, N. and F.T. Yarman-Vural, 2002. Optical character recognition for cursive handwriting. IEEE T. Pattern Anal., 24(6): 801-813.
   CrossRef    
8. Aulama, M.M., A.M. Natsheh, G.A. Abandah and M.M. Olama, 2011. Optical character recognition of handwritten Arabic using hidden Markov models. Proceeding of the SPIE Defense, Security and Sensing, International Society for Optics and Photonics, pp: 80550L-80550L-12.
   CrossRef    
9. Bahashwan, M.A. and S.A. Abu Bakar, 2014. A database of Arabic handwritten characters. Proceeding of the International Conference on Control System, Computing and Engineering (ICCSCE, 2014), pp: 632-635.
   CrossRef    
10. Bland, J.M. and D.G. Altman, 1997. Statistics notes: Cronbach's alpha. BMJ, 314(7080): 572.
    CrossRef    PMid:9055718 PMCid:PMC2126061    
11. Candes, E., L. Demanet, D. Donoho and L. Ying, 2006. Fast discrete curvelet transforms. Multiscale Model. Sim., 5(3): 861-899.
    CrossRef    
12. Chandra, P., 2003. Sigmoidal function classes for feedforward artificial neural networks. Neural Process. Lett., 18(3): 205-215.
    CrossRef    
13. El-Glaly, Y. and F. Quek, 2012. Isolated Handwritten Arabic Characters Recognition Using Multilayer Perceptrons and K nearest Neighbor Classifiers. Retrieved from: http://arabic-icr.googlecode.com/git/Thesis/Classification%20Paper/Papers/MLSP%20Arabic%20Character%20Recognition.pdf.
    Direct Link
14. Elzobi, M., A. Al-Hamadi, Z. Al Aghbari, L. Dings and A. Saeed, 2014. Gabor wavelet recognition approach for off-line handwritten Arabic using explicit segmentation. Adv. Intell. Sys. Comput., 233: 245-254.
    CrossRef    
15. Hafeez Allah, A. A., S. A. Abu Bakar and W. A. Orfali, 2014. Curvelet transform sub-difference image for crowd estimation. Proceeding of the IEEE International Conference on Control System, Computing and Engineering (ICCSCE, 2014), pp: 502-506.
    CrossRef    
16. Harris, C. and M. Stephens, 1988. A combined corner and edge detector. Proceeding of the Alvey Vision Conference, Manchester, UK, pp: 50.
    CrossRef    
17. Jia, H. and Z. Xiangfeng, 2009. Facial feature extraction and recognition based on Curvelet transform and SVD. Proceeding of the International Conference on Apperceiving Computing and Intelligence Analysis (ICACIA’2009), pp: 104-107.
    CrossRef    
18. Kabbani, R., 2012. Selecting most efficient Arabic OCR features extraction methods using Key Performance Indicators. Proceeding of the 2nd International Conference on Communications Computing and Control Applications (CCCA, 2012), pp: 1-6.
    CrossRef    
19. Kausalya, K. and S. Chitrakala, 2012. Idle object detection in video for banking ATM applications. Res. J. Appl. Sci. Eng. Technol., 4(24): 5350-5356.
    
20. Keys, R., 1981. Cubic convolution interpolation for digital image processing. IEEE T. Acoust. Speech, 29(6): 1153-1160.
    CrossRef    
21. Kokare, M., B. Chatterji and P. Biswas, 2003. Wavelet transform based texture features for content based image retrieval. Proceeding of the 9th National Conference on Communications (NCC’2003). Chennai, India, pp: 443-447.
    
22. Prasad, S., G.K. Verma, B.K. Singh and P. Kumar, 2012. Basic handwritten character recognition from multi-lingual image dataset using multi-resolution and multi-directional transform. Int. J. Wavelets Multi., 10(5).
    
23. Rashad, M., K. Amin, M. Hadhoud and W. Elkilani, 2012. Arabic character recognition using statistical and geometric moment features. Proceeding of the Japan-Egypt Conference on Electronics, Communications and Computers (JEC-ECC), pp: 68-72.
    CrossRef    
24. Sahlol, A. and C. Suen, 2014. A novel method for the recognition of isolated handwritten Arabic characters. 1: 13. Retrieved from: arXiv preprint arXiv:1402.6650.
    Direct Link
25. Starck, J., 2002. Image processing by the curvelet transform. Proceeding of the Tyrrhenian International Workshop on Digital Communications (IWDC’02).
    PMCid:PMC1370306    
26. Zhang, T. and C.Y. Suen, 1984. A fast parallel algorithm for thinning digital patterns. Commun. ACM, 27(3): 236-239.
    CrossRef    
27. Zidouri, A., 2010. On multiple typeface Arabic script recognition. Res. J. Appl. Sci. Eng. Technol., 2(5): 428-435.
    

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.