{"title":"Comparing Arabic and Latin Handwritten Digits Recognition Problems","authors":"Sherif Abdelazeem","volume":30,"journal":"International Journal of Computer and Information Engineering","pagesStart":1583,"pagesEnd":1588,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/5070","abstract":"A comparison between the performance of Latin and\r\nArabic handwritten digits recognition problems is presented. The\r\nperformance of ten different classifiers is tested on two similar\r\nArabic and Latin handwritten digits databases. The analysis shows\r\nthat Arabic handwritten digits recognition problem is easier than that\r\nof Latin digits. This is because the interclass difference in case of\r\nLatin digits is smaller than in Arabic digits and variances in writing\r\nLatin digits are larger. Consequently, weaker yet fast classifiers are\r\nexpected to play more prominent role in Arabic handwritten digits\r\nrecognition.","references":"[1] Cheng-Lin Liu, Kazuki Nakashima, Hiroshi Sako, and Hiromichi Fuji-\r\nsawa. Handwritten digit recognition: benchmarking of state-of-the-art\r\ntechniques. Pattern Recognition, 36(10):2271- 2285, Oct 2003.\r\n[2] D. Stork R. Duda, P. Hart. Pattern Classification. Wiley, New York,\r\n2nd edition edition, 2000.\r\n[3] Rich Caruana and Alexandru Niculescu-Mizil. An empirical comparison\r\nof supervised learning algorithms. In International Conference on\r\nMachine Learning (ICML), pages 161-168. Department of Computer\r\nScience, Cornell University, 2006.\r\n[4] Faruq A. Al-Omari and Omar M. Al-Jarrah. Handwritten indian numer-\r\nals recognition system using probabilistic neural networks. Advanced\r\nEngineering Informatics, 18(1):9-16, 2004.\r\n[5] Fady N. Said, Rita A. Yacoub, and Ching Y. Suen. Recognition of\r\nenglish and arabic numerals using a dynamic number of hidden neurons.\r\nIn ICDAR, pages 237-240, 1999.\r\n[6] Sherif Abdelazeem and Ezzat El-Sherif. Arabic handwritten digit recog-\r\nnition. International Journal of Document Analysis and Recognition\r\nIJDAR, 11(3):127-141, Dec 2008.\r\n[7] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning\r\napplied to document recognition. volume 86, pages 2278-2324. IEEE,\r\nnov 1998.\r\n[8] E. Kreyszig. Advanced Engineering Mathematics. Wiley, New York,\r\n9th edition edition, 2006.\r\n[9] Ezzat El-Sherif, Sherif Abdelazeem, and M. Yazeed. Automatic\r\ngeneration of optimum classification cascades. In 19th International\r\nConference on Pattern Recognition (ICPR 2008), Tampa, FL, Dec 2008.\r\n[10] Sherif Abdelazeem. A greedy approach for building classification\r\ncascades. In The Seventh International Conference on Machine Learning\r\nand Applications (ICMLA-08), pages 115-120, San Diego, CA, Dec\r\n2008.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 30, 2009"}