Comparing Arabic and Latin Handwritten Digits Recognition Problems

Authors: Sherif Abdelazeem

Abstract:

A comparison between the performance of Latin and Arabic handwritten digits recognition problems is presented. The performance of ten different classifiers is tested on two similar Arabic and Latin handwritten digits databases. The analysis shows that Arabic handwritten digits recognition problem is easier than that of Latin digits. This is because the interclass difference in case of Latin digits is smaller than in Arabic digits and variances in writing Latin digits are larger. Consequently, weaker yet fast classifiers are expected to play more prominent role in Arabic handwritten digits recognition.

Keywords: Handwritten recognition, Arabic recognition, Digits recognition, Document recognition

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1060383

References:

[1] Cheng-Lin Liu, Kazuki Nakashima, Hiroshi Sako, and Hiromichi Fuji- sawa. Handwritten digit recognition: benchmarking of state-of-the-art techniques. Pattern Recognition, 36(10):2271- 2285, Oct 2003.
[2] D. Stork R. Duda, P. Hart. Pattern Classification. Wiley, New York, 2nd edition edition, 2000.
[3] Rich Caruana and Alexandru Niculescu-Mizil. An empirical comparison of supervised learning algorithms. In International Conference on Machine Learning (ICML), pages 161-168. Department of Computer Science, Cornell University, 2006.
[4] Faruq A. Al-Omari and Omar M. Al-Jarrah. Handwritten indian numer- als recognition system using probabilistic neural networks. Advanced Engineering Informatics, 18(1):9-16, 2004.
[5] Fady N. Said, Rita A. Yacoub, and Ching Y. Suen. Recognition of english and arabic numerals using a dynamic number of hidden neurons. In ICDAR, pages 237-240, 1999.
[6] Sherif Abdelazeem and Ezzat El-Sherif. Arabic handwritten digit recog- nition. International Journal of Document Analysis and Recognition IJDAR, 11(3):127-141, Dec 2008.
[7] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. volume 86, pages 2278-2324. IEEE, nov 1998.
[8] E. Kreyszig. Advanced Engineering Mathematics. Wiley, New York, 9th edition edition, 2006.
[9] Ezzat El-Sherif, Sherif Abdelazeem, and M. Yazeed. Automatic generation of optimum classification cascades. In 19th International Conference on Pattern Recognition (ICPR 2008), Tampa, FL, Dec 2008.
[10] Sherif Abdelazeem. A greedy approach for building classification cascades. In The Seventh International Conference on Machine Learning and Applications (ICMLA-08), pages 115-120, San Diego, CA, Dec 2008.