Title: Text skew detection using log-polar transformation

Authors: Darko Brodić; Zoran N. Milivojević

Addresses: Technical Faculty in Bor, University of Belgrade, V.J. 12, Bor, Serbia ' Technical College Niš, A. Medevedeva 20, Niš, Serbia

Abstract: Several approaches have been taken for document text image skew detection. Their assignment was in the domain of efficiency, accuracy and robustness. This paper introduces the method for text skew detection based on the log-polar transformation. The original image is transformed in log-polar domain as well as the control ellipse. Their cross-correlation established the cost function. The extraction of the cost function maximum represents the text skew value in the region. The method is characterised by the accuracy and computational time inexpensiveness.

Keywords: digital image analysis; cross-correlation; log-polar transformation; OCR; optical character reconition; skew estimation; document images; text images.

DOI: 10.1504/IJRIS.2013.058191

International Journal of Reasoning-based Intelligent Systems, 2013 Vol.5 No.3, pp.195 - 201

Published online: 09 Dec 2013 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article