بازشناسی کلمات دست‌نویس فارسی به کمک تبدیل قطبی- لگاریتمی و مدل مخفی مارکوف
محورهای موضوعی : مهندسی برق و کامپیوتر
غلامرضا نادعلی‌نیا چاری
1
(دانشگاه سمنان)
خشایار یغمایی
2
(دانشگاه سمنان)
حامد فضل‌اللهی آقاملک
3
(دانشگاه بیرجند)
سيدمحمد رضوي
4
(دانشگاه بیرجند)
کلید واژه: تبدیل قطبی- لگاریتمی مدل مخفی مارکوف بازشناسی کلمات دست‌نویس فارسی,
چکیده مقاله :
در این مقاله یک سیستم بازشناسی کلمات فارسی معرفی می‌شود که از خودهمبستگی محلی مرتبه بالای تصویر قطبی- لگاریتمی برای استخراج ویژگی از زیرکلمات فارسی استفاده می‌کند. این شیوه استخراج ویژگی باعث می‌شود سیستم در مقابل تغییرات نگارشی مانند تغییر مقیاس‌های خطی و چرخش مقاوم شود. همچنین به کمک تبدیل قطبی- لگاریتمی، نمونه‌برداری از تصویر زیرکلمه به صورتی انجام شده که بیشترین نمونه‌ها در یک ناحیه خاص متمرکز باشد. در روش ارائه‌شده از مدل مخفی مارکوف گسسته به عنوان طبقه‌بند و همچنین برای افزایش امنیت و دقت خروجی سیستم بازشناسی از یک شبکه واژه‌نامه استفاده شده و برای ارزیابی سیستم از پایگاه داده ایران‌شهر استفاده شده بود. مقایسه نتایج حاصل از روش پیشنهادی با نتایج سایر روش‌های استخراج ویژگی مؤید این است که سیستم بازشناسی پیشنهاد‌شده در این مقاله از حساسیت کمتری نسبت به تغییرات نگارشی برخوردار است.
In this paper a recognition system for Persian words is introduced which utilizes the local higher order of the log-polar image autocorrelation for feature extraction of Persian sub-words. This feature extraction technique brings up leads to a system robustness in cases of writing variations alteration like scaled or rotated handwritings. Also using the log-polar transform, the sub-word image sampling will be performed so that most of acquired samples will be centered in a certain area. The proposed method uses the discrete Hidden Markov’s Model (HMM) as a classifier. Furthermore a net of dictionaries were employed to increase the reliability and precision of the system output. Finally, the Iran-Shahr database is utilized to evaluate the system performance. Comparing the results of the proposed method and other previous methods, proves that a less sensitivity has been achieved by the proposed method about handwriting variations.
[1] S. Almaadeed, C. Higgens, and D. Elliman, "Recognition of off - line handwritten arabic words using hidden markov model approach," in Proc. 16th Int. Conf. Pattern Recognition, vol. 3, pp. 481-484, Feb. 2002.
[2] S. Almaadeed, C. Higgens, and D. Elliman, "Off-line recognition of handwritten arabic words using multiple hidden markov models," Knowledge-Based Systems, vol. 17, no. 4, pp. 75-79, May 2004.
[3] M. Pechwitz and V. Margner, "HMM based approach for handwritten arabic word recognition using the IFN/ENIT-database," in ICDAR03 Proc. of the 7th Int. Conf. on Document Analysis and Recognition, IEEE Computer Society, vol. 2, pp. 890-894, Edinburgh, Scotland, Aug. 2003.
[4] R. Safabakhsh and P. Adibi, "Nastaaligh handwritten word recognition using a continuous - density variable-duration HMM," The Arabian J. Science and Eng., vol. 30, no. 1B, pp. 95-118, Apr. 2005.
[5] M. Mohamed and P. Gader, "Handwritten word recognition using segmentation - free hidden markov modeling and segmentation - based dynamic programming techniques," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 5, pp. 548-554, May 1996.
[6] M. M. Haji, Farsi Handwritten Word Recognition Using Continuous Hidden Markov Models and Structural Features, M.Sc. Thesis, Shiraz University, Shiraz, Iran, Jan. 2005.
[7] A. Broumandnia, J. Shanbehzadeh, and M. Nourani, "Handwritten Farsi/Arabic word recognition," in Proc. Int. Conf. on Computer Systems and Applications, pp. 767-771, 13-16 May 2007.
[8] S. Al-Qahtani and M. Khorsheed, "An omni-font HTK-based Arabic recognition system," in Proc. 8th IASTED Int"l Conf. Artificial Intelligence and Soft Computing, vol. 3, pp. 317-321, Sep. 2004.
[9] S. Al-Qahtani and M. Khorsheed, "A HTK-based system to recognise arabic script," in Proc. 4th IASTED Int. Conf. Visualization, Imaging, and Image Processing, vol. 4, pp. 133-140, Sep. 2004.
[10] H. Bunke, S. Bengio, and A. Vinciarelli, "Off - line recognition of unconstrained handwritten texts using HMMS and statistical language models," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no.6, pp. 709-720, Jun. 2.
[11] M. Khorsheed, "Recognising handwritten arabic manuscripts using a single hidden markov model," Pattern Recognition Letters, vol. 24, no. 14, pp. 2235-2242, Oct. 2003.
[12] C. G. Rafael and R. E. Woods, Digital Image Processing, Addison-Wesley, 1993.
[13] I. A. Jannoud, "Automatic arabic handwritten text recognition system," American J. of Applied Sciences, vol. 4, no. 11, pp. 857-864, Mar. 2007.
[14] L. Lam, S. W. Lee, and C. Y. Suan, "Thinning methodologies - a comprehensive survey," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 14, no. 9, pp. 869-885, Sep. 1992.
[15] V. J. Traver and F. Pla, "Log - polar mapping template design: from task - level requirements to geometry parameters," Image Vision Computing, vol. 26, no. 10, pp. 1354-1370, Nov. 2008.
[16] W. K. Wong, C. W. Choo, C. K. Loo, and J. P. The, "FPGA implementation of log - polar mapping," in Proc. Intl. Conf. on Mechatronics and Machine Vision in Practice, vol. 4, pp. 45-50, Dec. 2008.
[17] F. Yuan, H. Zhang, and R. Jia, "Digital image stabilization based on log-polar transform," in Proc. Int. Conf. Image and Graphics, pp. 769-773, Aug. 2007.
[18] S. Zokai and G. Wolberg, "Image registration using log-polar mappings for recovery of large-scale similarity and projective transformations," IEEE Trans. Image Processing, vol. 14, no. 10, pp. 1422-1434, Oct. 2005.
[19] T. Kurita, K. Hotta, and T. Mishima, "Scale and rotation invariant recognition method using higher - order local autocorrelation features of Log - Polar image," in Proc. 3rd Asian Conf. on Computer Vision, vol. 2, pp. 89-96, Apr. 1998.
[20] N. Otsu and T. Kurita, "A new scheme for practical, flexible, and intelligent vision systems," in Proc. IAPR Workshop Comput. Vis., pp. 431-435, Oct. 1988.
[21] S. M. Lajevardi, Z. M. Hussain, "Facial expression recognition: gabor filters versus higher - order correlators," in Proc. Int. Conf. on Communication, Computer and Power, ICCCP'09, pp. 354-358, Muscat, Oman, Feb. 2009.
[22] R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, John Wiley & Sons, 2nd Edition, 2001.
[23] L. Rabiner, "A tutorial on hidden markov models and selected applications in speech recognition," IEE Proc. on Readings in Speech Recognition, vol. 77, no. 2, pp. 257-286, Feb. 1989.
[24] F. Biadsy, J. El - Sana, and N. Habash, "Online arabic handwriting recognition using hidden markov models," in Proc. the 10th Int. Workshop on Frontiers of Handwriting Recognition, vol. 1, pp. 85-90, Oct. 2006.
[25] R. Ebrahimpour, R. D. Vahid, and B. M. Nezhad, "Decision templates with gradient based features for farsi handwritten word recognition," International J. of Hybrid Information Technology, vol. 4, no. 1, pp. 1-12, Jan. 2011.
[26] R. Ebrahimpour, M. Amini, and A. Vahidi Shams, "A new combination method based on different representation of data," Int. J. of Hybrid Information Technology, vol. 4, no. 3, pp. 51-60, Jul. 2011.
[27] R. Ebrahinpour, M. Amini, and F. Sharifizadehi, "Farsi handwritten recognition using combining neural networks based on stacked generalization," Int. J. on Electrical Engineering and Informatics, vol. 3, no. 2, pp. 146-164, Jun. 2011.