A New Segmentation Method for Persian/Arabic OCR Based on Baseline Processing

Majlesi Journal of Electrical Engineering

مقاله 6، دوره 3، شماره 3، خرداد 2009، صفحه 53-61   

نوع مقاله: Review Article

شناسه دیجیتال (DOI): 10.1234/mjee.v3i3.155

نویسندگان

Mahboubeh Shamsi¹؛ Reza Rasouli^{* 2}؛ Soudeh Shadravan²

¹Islamic Azad University Bardsir

²Azad Islamic University Bardsir

چکیده

One of the most important stages in Character Recognition Systems is “Segmentation”, because any mistake will affect to all other tasks, especially to character recognition. This operation is more complex in Persian/Arabic writing than other Latin writing like English, and there has been an ongoing research on it. Other algorithms, that has been used as base as proposed algorithm, show 85% accuracy. In this paper, a new improved method has been presented by analyzing the visual features of the Persian/Arabic language. The proposed algorithm is able to segment existing fonts up to 98.5% accuracy or even 100% on some cases. The remaining error could be refined by applying a good character recognition technique and a precise vocabulary.

کلیدواژه‌ها

image processing؛ Persian OCR؛ Azad Islamic University Bardsir؛ fa؛ Segmentation؛ recognition؛ smoothing؛ Arabic OCR؛ Baseline Method

مراجع

[1]

Aburas, A, A. & Rehiel, M, A. 2007. Off-line Omni-style Handwriting Arabic Character Recognition System Based on Wavelet Compression. Arab Research Institute in Sciences & Engineering. ISSN 1994-3253. 3(4): 123-135.

[2]

AlKhateeb, J, H. Ren, J. Ipson, S & Jiang, J. 2008. knowledge-based baseline detection and optimal thresholding for words segmentation in efficient preprocessing of handwritten Arabic text. Fifth international conference on information technology: new generations. IEEE computer society. pp. 1158-1159.

[3]

Al-Rashaideh, H. 2006. Preprocessing phase for Arabic Word Handwritten Recognition. Russian Academy of Sciences. 6(1): 11-19. Russian Federation.

[4]

A. Hassin, Tang, Xiang-Long, Liu, Jia-Feng, Zhao-Wei, “Printed Arabic character recognition using HMM”, Journal of Computer Science & Technology, vol. 19, no. 4, Science Press, pp. 538-543, China, 2004.

[5]

Argner, V & El Abed, H. 2008. Databases and Competitions: Strategies to Improve Arabic Recognition Systems. pp. 82-103.

[6]

Pechwitz, M & Maegner, V. 2003. HMM Based approach for handwritten Arabic Word Recognition Using the IFN/ENIT– DataBase, ICDAR’03, Edinburgh. pp. 890-894.

[7]

Nawaz, S.N., Sarfraz, M., Zidouri, A. & Al-Khatib, W.G. 2003. An approach to offline Arabic character recognition using neural networks. 10th IEEE International Conference on Electronics, Circuits and Systems (ICECS'03). 3:1328-

1331. 14-17 December.

[8]

Liana, M & Venu, G. 2006. Offline Arabic Handwriting Recognition: A Survey. IEEE, Transactions on Pattern Analysis and Machine Intelligence. 28: 712-724.

[9]

Latfi, F. Nader, F & Mouldi, B. 2006. Arabic Word Recognition by Using Fuzzy Classifier). Journal of Applied Scinces. ISSN 1812-56546. (3): 617-650.

[10]

Khorsheed, M.S. 2002. Off-line Arabic character recognition - a review. Pattern Analysis & Applications. 5(1): 31-45.

[11]

Farooq, F. Govindaraju, V & Perrone, M. 2005. Preprocessing Methods for Handwritten Arabic Documents. (ICDAR’05) Proceedings of the 2005 Eight International Conference on Document Analysis and Recognition, IEEE. 1. pp. 267-271.

Biography

Mahboubeh Shamsi is a Lecturer of Computer Science at Islamic Azad University, Bardsir, Iran. She is also a Ph.D. candidate at University of Technology, Malaysia. She has Master’s degrees in Computer Science from Islamic Azad University, Najafabad, Iran and a Bachelor’s degree in Applied Mathematics from Isfahan University, Iran. Her research interests include Security, Image Processing, Biometrics, Handwriting recognition, and Mathematic.

Abdolreza rasouli Kenari is a Lecturer of Computer Science at Islamic Azad University, Bardsir, Iran. He is also a Ph.D. candidate at University of Technology, Malaysia. He has Master’s degrees in Computer Science from Islamic Azad University, Najafabad, Iran and a Bachelor’s degree in Mathematics from Isfahan University, Iran. His research interests include Cryptography, Security, Data Mining, Distributed Database, Web App, Image Processing, Algorithms, and Mathematic.

Soudeh Shadravan is an Associate Lecturer of Computer Science at Islamic Azad University, Bardsir, Iran. She is also a Ms.C. student at University of Technology, Malaysia. She has Bachelor’s degrees from Islamic Azad University, Meybod, Iran and an Adv Diploma’s degree from Islamic Azad University, Bardsir, Iran in Computer Science. Her research interests include Network, Logical Phase, and Graphic.