Abstract—The performance of an OCR system will not be satisfactory for most of the scanned images without accurate skew correction. This paper presents the skew angle estimation and correction for Urdu document images script using moments method. The basic idea is to draw a random polygon over the text in document. This leads to thinning free preprocessing. The skew angle is calculated using Central moments and centroid of the document image. Experimental results are found to be satisfactory and compared with other skew detection techniques.
Index Terms—Skew Estimation, Moments, Optical Character Recognition, Urdu Document.
R. J. Ramteke is with the Department of Computer Science, North Maharashtra University, Jalgaon-425001, (M.S.) India. phone:+91-9890688672; e-mail: rakeshramteke@yahoo.co.in.
Imran Khan Pathan, is with Miliya College of Arts and Science, Beed,(M.S.), India. He is now pursuing his Ph.D. at North Maharashtra University,Jalgaon-425001, (M.S.) India. (e-mail: mca_imran2003@yahoo.co.in).
S. C. Mehrotra is with the Department of Computer Science and Information Technology, Dr. Babasaheb Ambedkar Marathwada University,Aurangabad-431001, (M.S.), India (e-mail: mehrotrasc@rediffmail.com).
Cite: R. J. Ramteke, Imran Khan Pathan, S. C. Mehrotra, "Skew Angle Estimation of Urdu DocumentImages: A Moments Based Approach," International Journal of Machine Learning and Computing vol. 1, no. 1, pp. 7-12, 2011.