The week's pick
Reseach Article
Isolated Handwritten Words Segmentation Techniques in Gurmukhi Script
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 1 - Number 24 |
| Year of Publication: 2010 |
| Authors: Galaxy Bansal, Dharamveer Sharma |
10.5120/547-713
|
Galaxy Bansal, Dharamveer Sharma . Isolated Handwritten Words Segmentation Techniques in Gurmukhi Script. International Journal of Computer Applications. 1, 24 ( February 2010), 104-111. DOI=10.5120/547-713
Abstract
Segmentation of handwritten words is a challenging task primarily because of structural features of the script and varied writing styles. Handwritten words are also prone to the problem of overlapped, connected, merged and broken characters. Based on certain properties of Gurmukhi script, different zones across the height of word are detected. Segmentation accuracy of 72.6% has been achieved with the use of the algorithms for segmenting all types of words. Segmentation accuracy of 88.1% has been achieved for segmenting all types of handwritten words in Gurmukhi script. Further, different categories of overlapping and touching characters in all the three zones (upper, middle and lower zone) of handwritten words in Gurmukhi script have been identified on the basis of structural properties of Gurmukhi script. A method for segmenting overlapping characters in middle zone has been proposed.
References
- Sargur N. Srihari, "Machine Printed Character Segmentation Method using Side Profiles", Proc. SMC' 99, Vol. 6, pp. 863-867, 1999.
- U. Pal and S. Datta, "Segmentation of Bangla Unconstrained Handwritten Text", Proc. 7th ICDAR, pp 1128-1132, 2003.
- N. Shanthi and K. Duraiswamy, "Preprocessing Algorithms for the Recognition of Tamil Handwritten Characters", Proc. 3rd International CALIBER, Cochin, pp. 77-82, 2005.
- N. Tripathy and U. Pal, "Handwriting segmentation of unconstrained Oriya text", Proc. Sadhana Academy of Engineering Sciences, Vol. 31, Part 6, pp.755-769, 2006.
- M. Hanmandlu and P. Agrawal, "A structural approach for segmentation of handwritten Hindi text", Proc. The International Conference on Cognition and Recognition, pp. 589-597.
- M. K. Jindal, R. K. Sharma and G. S. Lehal, "Segmentation of Horizontally Overlapping Lines in Printed Indian Scripts", Proc. International Journal of Computational Intelligence Research, Vol. 3, No. 4, pp. 277-286, 2007.
- M. K. Jindal, R. K. Sharma and G. S. Lehal, "A study of touching characters in a degraded Gurmukhi text", Proc. World Academy of Science, Engineering and Technology, Vol. 4, pp.121-124, 2005.
- LI Yi, Yefeng Zheng, David Doermann, Stefen Jaeger, "Script independent text line segmentation in freestyle handwritten documents", pp. 1-28, 2006.
- Dharam Veer Sharma and G. S. Lehal, "An Iterative Algorithm for Segmentation of Isolated Handwritten Words in Gurmukhi script", Proc. 18th ICPR, pp. 1022-1025, 2006.
- M. K. Jindal, R. K. Sharma and G. S. Lehal, "Segmentation of Horizontally Overlapping Lines in Printed Gurmukhi Script", Proc. International Journal of Computational Intelligence and Research (IJCIR), pp. 226-229, 2006.
- A. Bishnu and B. Chaudhuri, "Segmentation of Bangla Handwritten Text into Characters by recursive Contour Following", 5th ICDAR, pp.402-405, 1999.
- G. S. Lehal and Chandan Singh, "A Gurmukhi Script Recognition System", Proc. 15th ICPR, Vol. 2, pp. 557-560, 2000.
- Manish Kumar, Dr. R. K. Sharma (TIET, Patiala) and Dr. G. S. Lehal (Punjabi University, Patiala), Ph.D. Thesis on "Degraded Text recognition of Gurmukhi Script", March 2008.
Index Terms
Keywords