1. © Recognition Of Writer-Independent Off-Line Handwritten Arabic (Indian) Numerals Using Hidden Markov Models Mahmoud, S ELSEVIER SCIENCE BV, SIGNAL PROCESSING; pp: 844-857; Vol: 88 King Fahd University of Petroleum & Minerals http://www.kfupm.edu.sa Summary This paper describes a technique for the recognition of optical off-line handwritten Arabic (Indian) numerals using hidden Markov models (HMM). The success of HMM in speech recognition encouraged researchers to apply it to text recognition. In this work we did not follow the general trend of using sliding windows in the direction of the writing line to generate features. Instead we generated features based on the digit as a unit. Angle-, distance-, horizontal-, and verticalspan features are extracted from Arabic (Indian) numerals and used in training and testing the HMM. These features proved to be simple and effective. In addition to the HMM the nearest neighbor classifier is used. The results of both classifiers are then compared. Several experiments were conducted for estimating the suitable number of states for the HMM. The best results were achieved with an HMM model with 10 states. In addition, we experimented with different number of features. The best results were achieved with 120 feature vector representing a digit. A database of 44 writers, each writer wrote 48 samples of each digit resulting in a database of 21,120 samples. The data were size normalized to enable the technique to be size invariant. In extracting the features the center of gravity of the digit is used to make the technique translation invariant. The randomization technique was used to generate Arabic (Indian) numbers for training and testing the HMM classifier. The randomization was done on the number of digits per number and on the digit sequence. About 2171 Arabic (Indian) numbers were generated, totaling 21,120 digits. 1700 numbers (totaling 16,657 digits) were used in training the HMM and 471 numbers (totaling 4463 digits) are used in Copyright: King Fahd University of Petroleum & Minerals; http://www.kfupm.edu.sa

2. 1. 2. 3. 4. 5. 6. 7. © testing the HMM. The samples of the first 24 writers were used in training the nearest neighbor classifier and the remaining 20 writers' samples were used in testing. The achieved average recognition rates are 97.99% and 94.35% using the HMM and the nearest neighbor classifiers, respectively. The classification errors were analyzed and it was clear that some errors may be attributed to bad data, some to deformation and unbalanced proportion of digit segments, different writing styles of some digits, errors between digit pairs were specified and analyzed, and genuine errors. It was clear that the real misclassification of genuine data, in the case of HMM was nearly 1%. This proves the effectiveness of the presented technique to writer-independent off-line Arabic (Indian) handwritten digit recognition. The technique is writer independent as separate writers' data were used in training of the classifiers and other writers' data were used in the testing phase. (c) 2007 Elsevier B.V. All rights reserved. References: HTK SPEECH RECOGNITI ALBADR B, 1995, SIGNAL PROCESS, V41, P49 ALMAADEED S, 2002, INT C PATT RECOG, P481 ALMAADEED S, 2004, KNOWL-BASED SYST, V17, P75, DOI 10.1016/j.knosys.2004.03.002 ALOMARI F, 2001, P ACS IEEE INT C COM, P83 ALOMARI FA, 2004, ADV ENG INFORM, V18, P9, DOI 10.1016/j.aei.2004.02.001 8. BAZZI I, 1997, P INT C DOC AN REC U, V2, P842 9. BAZZI I, 1999, IEEE T PATTERN ANAL, V21, P495 10. BOUSLAMA F, 1999, INT J PATTERN RECOGN, V13, P1027 11. CHEUNG K, 1998, IEEE T PATTERN ANAL, V29, P1382 12. GOVINDAN VK, 1990, PATTERN RECOGN, V23, P671 13. HAMID A, 2001, P ACS IEEE INT C COM, V110 14. HASSIN AH, 2004, J COMPUT SCI TECHNOL, V19, P538 15. HOSSEINI HMM, 1996, P AUSTR NZ C INT INF, P80 16. HU JY, 2000, PATTERN RECOGN, V33, P133 17. KHORSHEED MS, 2002, PATTERN ANAL APPL, V5, P31 18. LIU CL, 2003, PATTERN RECOGN, V36, P2271, DOI 19. 10.1016/S0031-3206(03)00085-2 20. LORIGO LM, 2006, EEE T PATTERN ANAL M, V28, P712 21. MANTAS J, 1986, PATTERN RECOGN, V19, P425 22. MOHAMED M, 1996, IEEE T PATTERN ANAL, V18, P548 23. SADRI J, 2003, P 2 IR C MACH VIS IM, V1, P300 24. SAID FN, 1999, P 5 INT C DOC AN REC, P237 25. SALAH AA, 2002, IEEE T PATTERN ANAL, V24, P420 Copyright: King Fahd University of Petroleum & Minerals; http://www.kfupm.edu.sa

3. 26. 27. 28. 29. 30. 31. 32. 33. © SALOUM S, 2001, P ACS IEEE INT C COM, P106 SHAHREZEA MHS, 1995, P INT C IM PROC, V3, P436 SHI M, 2002, PATTERN RECOGN, V35, P2051 SOLTANZADEH H, 2004, PATTERN RECOGN LETT, V25, P1569, DOI 10.1016/j.patrec.2004.05.014 TEOW LN, 2002, PATTERN RECOGN, V35, P2355 TOUJ S, 2005, INT ARAB J INF TECHN, V2, P318 TSANG IJ, 1998, INT C IM PROC, V2, P939 For pre-prints please write to: smasaad@kfupm.edu.sa Copyright: King Fahd University of Petroleum & Minerals; http://www.kfupm.edu.sa