CFP last date
20 December 2024
Reseach Article

Estimation of Tilt in Characters and Correction for better Readability by OCR Systems

by C. S. Vijayashree, Vishwanath C. Kagawade, T. Vasudev
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 90 - Number 13
Year of Publication: 2014
Authors: C. S. Vijayashree, Vishwanath C. Kagawade, T. Vasudev
10.5120/15777-4471

C. S. Vijayashree, Vishwanath C. Kagawade, T. Vasudev . Estimation of Tilt in Characters and Correction for better Readability by OCR Systems. International Journal of Computer Applications. 90, 13 ( March 2014), 1-7. DOI=10.5120/15777-4471

@article{ 10.5120/15777-4471,
author = { C. S. Vijayashree, Vishwanath C. Kagawade, T. Vasudev },
title = { Estimation of Tilt in Characters and Correction for better Readability by OCR Systems },
journal = { International Journal of Computer Applications },
issue_date = { March 2014 },
volume = { 90 },
number = { 13 },
month = { March },
year = { 2014 },
issn = { 0975-8887 },
pages = { 1-7 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume90/number13/15777-4471/ },
doi = { 10.5120/15777-4471 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T22:10:55.119859+05:30
%A C. S. Vijayashree
%A Vishwanath C. Kagawade
%A T. Vasudev
%T Estimation of Tilt in Characters and Correction for better Readability by OCR Systems
%J International Journal of Computer Applications
%@ 0975-8887
%V 90
%N 13
%P 1-7
%D 2014
%I Foundation of Computer Science (FCS), NY, USA
Abstract

The existing Optical Character Readers (OCRs) are capable of reading linear form text and have limitations to read artistic and non-linear form text. The tilt in characters contributes a major share in affecting the efficiency of the recognition algorithms. This paper presents a technique to estimate and correct the vertical tilt in printed characters of English in order to make an OCR to read the text more efficiently. The input characters are assumed to be segmented from the document image and free from noise. Initially, the direction of tilt of the characters is detected using a heuristically constructed knowledgebase. Next, the inclination of the character to its base is estimated using line drawing algorithm. Finally, the estimated tilt is corrected through rotation in counter direction of the tilt. The method has been tested with sufficient samples and readability analysis is performed with an OCR. Experimental results show an average improvement in readability by OCR from 20% before tilt correction to 82% after the tilt correction.

References
  1. Nagabhushan P, 2001, Document Image Processing, Proc. National Pre-Conf. Workshop on Document Processing, India, pp. 114.
  2. O'Gorman, Lawrence, Rangachar, Kasturi, 1998, Executive briefing: Document image analysis, IEEE Computer Society Press.
  3. Vasudev T, Hemanthakumar G H, Nagabhushan P. , 2005, Segmentation of characters in an arc-form, 7th Int. Conf. on Cognitive Systems (ICCS 2005), India.
  4. Thomas Bayer, UlrichB, Ingrid Renz, 1997, Information Extraction from paper documents, Handbook of Character Recognition and Image Analysis, pp. 653-677
  5. Suen, Xu, Lam, 1999, Automatic recognition of handwritten data on cheques – Fact or fiction, Pattern Recognition Letters, Vol. 20, No. 11-13, pp. 1287-1295
  6. Chatterji B N, 2001, Feature Extraction Methods for Character Recognition, Proc. National Pre-Conference Workshop on Document Processing,, India, pp. 7-20
  7. Pal,U. Mitra, M. ,Choudari B. B, 2001, Multi-Skew Detection of Indian Script Documents, Int. Conf. on Document Analysis and Recognition (ICDAR 2001).
  8. Gatos B et al. , 1997, Skew detection and text line position determination in digitized documents, Journal of Pattern Recognition, Vol. 30, No. 9, pp. 1505-1519.
  9. Amin A, Fischer S, 2000, A Document Skew Detection Method Using the Hough Transform, Journal of Pattern Analysis and Applications, Vol 3, pp. 243-253
  10. Kavallieratou, Fakotakis, Kokkinakis, 2002, Skew Angle Estimation For Printed and Handwritten Documents Using the Wigner-Ville Distribution, Image and Vision Computing, Vol 20, pp. 813-824
  11. Liolios, Fakotakis, Kokkinakis, 2003, Generalization of the Form Identification and Skew Detection Problem, Pattern Recognition, No. 35, pp. 243-264
  12. Shivakumar P, 2005, Generation of Complete Large Document Images from Split Components, Ph. D thesis under the supervision of Hemanthakumar G, University of Mysore, India
  13. Yue Lu and Chew Lim Tan, 2003, A nearest-neighbor chain based approach to skew estimation in document images, Journal of Pattern Recognition Letters, Vol 24, pp. 2315-2323.
  14. Vasudev T, Hemanthakumar G H, Nagabhushan P. , 2007, "Transformation of arc-form-text linear-form-text- suitable for OCR", ScienceDirect, Pattern recognition letters 28 (2007) 2343-2351.
  15. Vishwanath C Kagawade, Vijayashree C S and Vasudev T, July 2012, Transformation of artistic form text to linear form text for OCR systems, ICAdC-2012.
  16. Vishwanath C Kagawade, Vijayashree C S and Vasudev T, Dec 2012, Transformation of artistic form text to linear form text for OCR systems using Radon Transform, ICERECT-12.
  17. Rich, Knight, 1991, Artificial Intelligence, TMH pubns.
  18. Donald Hearn, Baker M P, 2003, Computer Graphics, Pearson Education, 2nd Edition.
  19. R. E. Twogood, F. Graham Sommer, 1982, Digital Image Processing, IEEE Transactions on Nuclear Science, Vol. 29, No. 3.
  20. P. Saragiotis and N. Papamarkos, 2008, Local Skew Correction in Documents, International Journal of Pattern Recognition and Artificial Intelligence, Vol. 22, No. 4 , 691–710, World Scientific Publishing Company.
  21. P. Nagabhushan, S. A. Anagadi et. al. , Feb 2007, Geometric Model and Projection Based Algorithms for Tilt Correction and Extraction of Ascenders / Descenders for Cursive Word Recognition, IEE-ICSCN pp. 488-491.
  22. H. K. Chethan and G. Hemantha Kumar, 2010, Graphics Separation and Skew Correction of Mobile Captured Documents and Comparative analysis with Existing Methods, International Journal of Computer Science and Applications, Vol. 7 No. 3.
  23. Takuma Yamaguchi, Yasuaki Nakano, et. al. 2003, Digit Classification on Signboards for Telephone Number Recognition, Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003), 0-7695-1960-1/03, IEEE.
  24. Tian Jipeng, G. Hemantha Kumar, H. K. Chethan,May 2011, Skew Correction for Chinese Character using Hough Transform, International Journal of Computer Applications (0975– 8887) ,Volume 22– No. 2.
  25. Nandini N. , Srikanta Murthy K. , and G. Hemantha Kumar, 2008, Estimation of Skew Angle in Binary Document Images Using Hough Transform, World Academy of Science, Engineering and Technology 42.
  26. Rajiv Kapoor, Deepak Bagai, Kamal, 2004, A new algorithm for skew detection and correction, Science Direct, Pattern recognition letters(25), pp. 1215-1229.
  27. C. M. Velu and P. Vivekandan, June 2010, Automated letter sorting for Indian Postal Address Recognition System based on PIN codes, Journal of Internet and information system Vol. 1(1), pp. 6-15
  28. Rafael C Gonzales & Richard E Woods, 2002, Digital Image Processing, 2nd Ed. , Pearson Education Publicatn.
Index Terms

Computer Science
Information Sciences

Keywords

Linear text Artistic text Tilt in characters Tilt correction OCR.