Recognition of Printed Kannada Numerals based on Zoning Method

Print
IJCA Proceedings on National Conferecne on Advanced Computing and Communications 2012
© 2012 by IJCA Journal
NCACC - Number 1
Year of Publication: 2012
Authors:
Ravindra S. Hegadi

Ravindra S Hegadi. Article: Recognition of Printed Kannada Numerals based on Zoning Method. IJCA Proceedings on National Conferecne on Advanced Computing and Communications 2012 NCACC(1):5-8, August 2012. Full text available. BibTeX

@article{key:article,
	author = {Ravindra S. Hegadi},
	title = {Article: Recognition of Printed Kannada Numerals based on Zoning Method},
	journal = {IJCA Proceedings on National Conferecne on Advanced Computing and Communications 2012},
	year = {2012},
	volume = {NCACC},
	number = {1},
	pages = {5-8},
	month = {August},
	note = {Full text available}
}

Abstract

Zoning is one of the popular methods used for the optical character recognition of documents. In this paper the zoning approach is used for recognition of printed Kannada numerals. The input scanned document image containing printed Kannada numerals is binarized. The noise present in the document in the form of tiny dots is eliminated. The row segmentation followed by the column segmentation is performed on this document to segment out every numeral. The number of regions is obtained from this segmented numeral, which will be used as one of the feature during recognition stage. A morphological thinning algorithm is applied to thin this numeral. In the next stage the number of end points and the coordinate values of each end point are obtained. The zones in which the end points lie, and the regions that each numeral generates, are used for the recognition of the numeral. The proposed algorithm is applied on the document containing the printed Kannada numerals of different fonts generated using Nudi 4. 0 software. The analysis of recognition using proposed method is also presented here.

References

  • Krishnamurti, 2003, 78.
  • Steever, 1998, 129-131.
  • "Awardees detail for the Jnanpith Award", Official website of Bharatiya Jnanpith. Bharatiya Jnanpith. Retrieved 2008-05-12.
  • "Declaration of Telugu and Kannada as classical languages". Press Information Bureau. Ministry of Tourism and Culture, Government of India. Retrieved 2008-10-31.
  • "Old Kannada". Retrieved 2009-05-07.
  • Gorman L. O' and Kasturi R. 1995. Document image analysis, IEEE Computer Society Press.
  • Ravindra S. Hegadi 2011. Template Matching Approach for Printed Kannada Numeral Recognition. In Proceedings of the International Conference on Computational Intelligence and Information Technology (CIIT), Pune, India, 480-483.
  • Sanjeev Kunte R. and Sudhakar Samuel R. D. 2007. An OCR system for printed Kannada text using two-stage Multi-network classification approach employing Wavelet features. In Proceedings of the IEEE Computer Society International Conference on Computational Intelligence and Multimedia Applications, India, 349–355.
  • Ashwin T. V. and Sastry P. S. 2002. A font and size independent OCR system for printed Kannada documents using support vector machines. Sadhana, 27(1), 35-58.
  • Karthik Sheshadri, Pavan Kumar T Ambekar, Deeksha Padma Prasad and Dr. Ramakanth P Kumar 2010. An OCR system for Printed Kannada using k-means clustering. In Proceedings of the IEEE International Conference on Industrial Technology (ICIT), Chile, 183-187.
  • Ravindra S. Hegadi 2012. Classification of Kannada Numerals using multi-layer Neural Network. In Proceedings of the International Conference on Advances in Computing (ICADC), Bangalore.