Segmentation of Ancient and Historical Gilgit Manuscripts

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 379)

Abstract

The Gilgit manuscripts belong to fifth century A.D. and are oeuvre of texts which deal with Buddhist work. It is one of the oldest manuscripts in the world and is considered to be a milestone in the history of Buddhist works in India. It is a collection of both official and unofficial Buddhist works which are believed to have helped in the evolution of many literatures including Chinese, Japanese, and Sanskrit. Since this manuscript is almost seventeen centuries old it has not been able to fully decipher the text yet. It has been laminated by the National Archives of India which proves it is one of the most important literatures concerning India. In this paper, we perform character-based image segmentation on Gilgit manuscript in order to simplify and to better identify character in the image of the manuscript. The employed method gives an accuracy of nearly 87 %.

Keywords

Gilgit manuscripts Segmentation Character-based Buddhist works 

References

  1. 1.
  2. 2.
    Gilgit manuscript—piecing together fragments of history: Copyright © 2000–2004 (the-south-asian.com) Aug 2004Google Scholar
  3. 3.
    Choudhary, A.: A review of various character segmentation techniques for cursive handwritten words recognition. Int. J. Inf. Comput. Technol. 4(6), 559–564 (2014)Google Scholar
  4. 4.
    Cavalin, P.R., Britto, A.S., Bortolozzi, F., Sabourin, R., Oliveira, L.: An implicit segmentation based method for recognition of handwritten strings of characters. In: Proceedings of the ACM Symposium on Applied Computing, 836–840 (2006)Google Scholar
  5. 5.
    Gillies, M.: Cursive word recognition using hidden Morkov models. In: Proceedings of the Fifth U.S. Postal Service Advanced Technology Conference, pp. 557–562 (1992)Google Scholar
  6. 6.
    Cho, W., Lee, S.W., Kim, J.H.: Modelling and recognition of cursive words with hidden Markov models. Pattern Recognit. 28(12), 1941–1953 (1995)CrossRefGoogle Scholar
  7. 7.
    Saba, T., Sulong, G., Rehman, A.: Document image analysis: issues, comparison of methods and remaining problems. Artif. Intell. Rev. 35, 101–118 (2011)CrossRefGoogle Scholar
  8. 8.
    Dawoud, A.: Iterative cross section sequence graph for handwritten character segmentation. IEEE Trans. Image Process 16(8), 2150–2154 (2007)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Roy, P.P., Pal, U., Lladós, J., Delalandre, M.: Multioriented touching text character segmentation in graphical documents using dynamic programming. Pattern Recognit. 45(5), 1972–1983 (2012)CrossRefGoogle Scholar
  10. 10.
    David, X.Z.: Extraction of embedded and/or line touching character line objects. JPRS 35 (2002)Google Scholar
  11. 11.
    Roberto, R.J., Thomé, A.C.G.: Cursive character recognition—a character segmentation method using projection profile based technique (2002)Google Scholar

Copyright information

© Springer India 2016

Authors and Affiliations

  • Pinjari Hameed
    • 1
  • Rosemary Koikara
    • 1
  • Chethan Sharma
    • 2
  1. 1.Department of CSEChrist UniversityBangaloreIndia
  2. 2.IEEE MemberBangaloreIndia

Personalised recommendations