Estimation of the Text Skew in the Old Printed Documents

Authors

  • Darko Brodic University of Belgrade
  • Čedomir A. Maluckov Technical Faculty in Bor, University of Belgrade
  • Liangrui Peng Department of Electronic Engineering, Tsinghua University

Keywords:

convex hull, document image analysis, moment methods, optical character recognition, skew adjustment, vertical projection profiles.

Abstract

Old printed documents represent the significant part of our heritage. In order to preserve them, the digitalization is indispensable. The paper proposed a robust skew estimation method for old printed document. It is based on the connected components made by filled convex hulls around text element. The connected components are enlarged by oriented morphological operation. Then, the longest connected component is extracted. The global orientation of the document is detected by its orientation. Accordingly, document image was globally de-skewed. The algorithm is tested on synthetic and real datasets. Obtained results proved the algorithms
correctness.

Author Biography

Darko Brodic, University of Belgrade

Technical Faculty in Bor

References

Amin, A.; Wu, S. (2005); Robust Skew Detection in Mixed Text/Graphics Documents, Proc.of 8th ICDAR, Seoul, Korea, 247-251.

Manmatha, R.; Srimal, N. (1999); Scale Space Technique for Word Segmentation in Handwritten Manuscripts, Proc. of 2nd ICSSTCV, LNCS 1682, London, Great Britain, 22-33.

O'Gorman, L. (1993); The Document Spectrum for Page Layout Analysis, IEEE Trans Pattern Anal Mach Intell, ISSN 0162-8828, 15(11): 1162-1173.

Louloudis, G.; Gatos, B.; Pratikakis, I.; Halatsis, C. (2008); Text Line Detection in Handwritten Documents, Pattern Recognition, ISSN 0031-3203, 41(12): 3758-3772.

Postl,W. (1986); Detection of Linear Oblique Structures and Skew Scan in Digitized Documents, Proc. of 8th ICPR, Paris, France, 687-689.

Yan, H. (1993); Skew Correction of Document Images Using Interline Cross-Correlation, CVGIP: Graphical Models and Image Processing, ISSN 1049-9652, 55(6): 538-543.

Brodić, D.; Milivojević, Z.N. (2013); Log-polar Transformation as a Tool for Text Skew Estimation, Elektronika Ir Elektrotechnika ISSN 1392-1215, 19(2): 61-64.

Saragiotis, P.; Papamarkos, N. (2008); Local Skew Correction in Documents, Int J Pattern Recognit Artif Intell ISSN 0218-0014, 22(4): 691-710.

Makridis, M.; Nikolau, N.; Papamarkos, N. (2010); An Adaptive Technique for Global and Local Skew Correction in Color Documents, Expert Syst Appl, ISSN 0957-4174, 37(10): 6832-6843.

Otsu, N. (1979); A Threshold Selection Method from Gray-level Histograms, IEEE Trans Sys, Man, Cyber, ISSN 0018-9472, 9(1): 62-66.

Chen, Kuo-Nan; Chen, Chin-Hao; Chang, Chin-Chen (2012); Efficient Illumination Compensation Techniques for Text Images, Digit Signal Prog ISSN 0165-1684, 22(5): 726-733.

Brodić, D.; Milivojević, D.R. (2012); An Algorithm for the Estimation of the Initial Text Skew, Inf Technol Control, ISSN 1392-124X, 41(3): 211-219.

Brodić, D. (2011); The Evaluation of the Initial Skew Rate for Printed Text, J Electr Eng, ISSN 1335-3632, 62(3): 142-148.

Kapogiannopoulos, G.; Kalouptsidis, N. (2002); A Fast High Precision Algorithm for the Estimation of Skew Angle Using Moments, Proc. of SPPRA, Crete, Greece, 275-279.

Zramdini, A.; Ingold, R. (1993); Optical Font Recognition from Projection Profiles, Electronic Publishing, ISSN 0194-4851, 6(3): 249-260.

Brodić, D.; Milivojević, D.; Tasić, V.; Milivojević, Z. (2013); Identification of the Global Text Skew Based on the Convex Hulls, Proc. of MIPRO, Opatija, Croatia, 1282-1286.

Identification of the Global Text Skew Based on the Convex Hulls, Proc. of MIPRO, Opatija, Croatia, 1282-1286.

Published

2013-09-17

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.