Notification: Our email services are now fully restored after a brief, temporary outage caused by a denial-of-service (DoS) attack. If you sent an email on Dec 6 and haven't received a response, please resend your email.
CFP last date
20 December 2024
Reseach Article

Segmentation of Connected Components and Overlapping Lines in Gurumukhi Handwritten Documents

by Snehdeep, Manoj Kumar
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 102 - Number 13
Year of Publication: 2014
Authors: Snehdeep, Manoj Kumar
10.5120/17874-8850

Snehdeep, Manoj Kumar . Segmentation of Connected Components and Overlapping Lines in Gurumukhi Handwritten Documents. International Journal of Computer Applications. 102, 13 ( September 2014), 10-14. DOI=10.5120/17874-8850

@article{ 10.5120/17874-8850,
author = { Snehdeep, Manoj Kumar },
title = { Segmentation of Connected Components and Overlapping Lines in Gurumukhi Handwritten Documents },
journal = { International Journal of Computer Applications },
issue_date = { September 2014 },
volume = { 102 },
number = { 13 },
month = { September },
year = { 2014 },
issn = { 0975-8887 },
pages = { 10-14 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume102/number13/17874-8850/ },
doi = { 10.5120/17874-8850 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T22:33:00.476245+05:30
%A Snehdeep
%A Manoj Kumar
%T Segmentation of Connected Components and Overlapping Lines in Gurumukhi Handwritten Documents
%J International Journal of Computer Applications
%@ 0975-8887
%V 102
%N 13
%P 10-14
%D 2014
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Text line segmentation is extremely important phase of OCR. Overlapped lines, skewed lines and connected components make the problem of line segmentation more complicated in Gurumukhi handwritten documents. The existence of these problems in handwritten text documents declines the performance of OCR system. In this paper, we present a technique to solve these problems. The proposed algorithm is based on mid-point detection. The algorithm deals with these problems and gives effective results 90% in case of overlapped lines and 94% accurate results for segmentation of connected components between neighboring lines. This paper also provides a review on major problems in line segmentation that decreases the accuracy of recognition system. The proposed method has achieved 93. 05% accuracy in text line segmentation.

References
  1. Simpel Jindal, Gurpreet Singh Lehal, "Line Segmentation of Gurumukhi Manuscripts", December 2012.
  2. Namisha Modi, Khushneet Jindal, "Text line detection and segmentation in Handwritten Gurumukhi Scripts", International Journal of Advanced Research in Computer Science and Software Engineering, vol. 3, Issue 5, PP:1075-1080, May, 2013.
  3. Naresh Kumar Garg, Lakhwinder Kaur, M. K. Jindal, "A New Method for Line Segmentation of Handwritten Hindi Text", IEEE, 2010.
  4. M. K. Jindal, R. K. Sharma, G. S. Lehal, "Segmentation of Horizontally Overlapping lines in Printed Gurmukhi Script", IEEE, 2006.
  5. Naresh Kumar Garg, Lakhwinder Kaur, M. K. Jindal, "Segmentation of Handwritten Hindi Text", International Journal of Computer Applications, Vol. 1, No. 4, 2010.
  6. Ashu Kumar, Simpel Rani Jindal, "Segmentation of Handwritten Gurumukhi text into Lines", International Conference on recent advances and Future Trends in Information Technology (iRAFIT2012), pp. 13-17,2012.
  7. Saiprakash Palakollu, Renu Dhir, Rajneesh Rani, "Handwritten Hindi Text Segmentation Techniques for Lines and Characters", World congress on Engineering and Computer Science, Vol. 1, 2012.
  8. Nallapareddy Priyanka, Srikanta Pal, Ranju Mandal, "Segmentation of handwritten Gurumukhi Text into Lines", IJCA, 2010.
  9. U. Pal, Sagarika Datta, "Segmentation of Bangla Unconstrained Handwritten Text",IEEE, 2003.
  10. G. Louloudis, B. Gatos, I. Pratikakis,C. Halatsis, "A Block-Based Hough Transform Mapping for Text Line Detection in Handwritten Documents", Proceedings of the tenth International Workshop on Frontiers in Handwriting Recognition, La Baule,Oct. 2006.
  11. Rajiv Kumar, Amardeep Singh, "Detection and Segmentation of Lines and Words in Gurumukhi Handwritten Text", IEEE,2010.
  12. M. K. Jindal, R. K. Sharma, G. S. Lehal, "Segmentation of Horizontally Overlapping lines in Printed Indian Script", International Journal of Computational Intelligence Research, Vol. 3, No. 4, pp. 277-286, 2007.
  13. Munish Kumar, M. K. Jindal, R. K. Sharma, "Classification of Characters and Grading Writers in Offline Handwritten Gurmukhi Script", IEEE, 2011.
  14. G. S. Lehal, Chandan Singh, Ritu Lehal, "A Shape Based Post Processor for Gurumukhi OCR", IEEE, 2001.
  15. G S Lehal, Chandan Singh, "A Gurumukhi Script Recognition System", IEEE, 2000.
Index Terms

Computer Science
Information Sciences

Keywords

Line Segmentation Gurumukhi Skew Lines Overlapped Lines Connected components.