A New Parallel Thinning Algorithm with Stroke Correction for Odia Characters

Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 27)

Abstract

There are several thinning algorithms reported in literature in last few decades. Odia has structurally different script than that of other Indian languages. In this paper, some major thinning algorithms are examined to study their suitability to skeletonize Odia character set. It is shown that these algorithms exhibit some deficiencies and vital features of the character are not retained in the process. A new parallel thinning technique is proposed that preserves important features of the script. Interestingly, the new algorithm exhibits stroke-preservation which is a higher level requirement of thinning algorithms. Present work also discusses a concept of stroke correction where a basic stroke is learnt from the original image and embedded on the skeleton.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bernard, T.M., Manzanera, A.: Improved low complexity fully parallel thinning algorithm. In: ICIAP (1999)Google Scholar
  2. 2.
    Chin, R.T., Wan, H.K., Stover, D.L., Iversion, R.D.: A one-pass thinning algorithm and its parallel implementation. CVGIP 40, 30–40 (1987)Google Scholar
  3. 3.
    Choy, S.S.O., Choy, C.S.T., Siu, W.C.: New single-pass algorithm for parallel thinning. CVIU 62, 69–77 (1995)Google Scholar
  4. 4.
    Couprie, M.: Note on fifteen 2-D parallel thinning algorithm. IGM’01, pp. 1–21 (2006)Google Scholar
  5. 5.
    Datta, A., Parui, S.K.: A robust parallel thinning algorithm for binary images. Pattern Recognition 27, 1181–1192 (1994)CrossRefGoogle Scholar
  6. 6.
    Guo, Z., Hall, R.W.: Fast fully parallel thinning algorithm. CVGIP 55, 317–328 (1992)CrossRefMATHGoogle Scholar
  7. 7.
    Hall, R.W.: Fast parallel thinning algorithm: parallel speed and connectivity preservation. CACM 32, 124–131 (1989)CrossRefGoogle Scholar
  8. 8.
    Kong, T.Y., Rosenfeld, A.: Digital topology: introduction and survey. CVGIP 48, 357–393 (1989)Google Scholar
  9. 9.
    Kwon, J.S., Gi, J.W., Kang, E.K.: An enhanced thinning algorithm using parallel processing. In: ICIP, vol. 3, pp. 752–755 (2001)Google Scholar
  10. 10.
    Lam, L., Suen, C.Y.: An evaluation of parallel thinning algorithm for character recognition. IEEE Tr. PAMI 17, 914–919 (1995)CrossRefGoogle Scholar
  11. 11.
    Negi, A., Bhagvati, C., Krishna, B.: An OCR system for Telugu. In: ICDAR 2001, pp. 1110–1114 (2001)Google Scholar
  12. 12.
    Pal, U., Chaudhuri, B.B.: Indian script character recognition-A survey. Pattern Recognition 37, 1887–1899 (2004)CrossRefGoogle Scholar
  13. 13.
    Pujari, A.K., Naidu, C.D., Jinga, B.C.: An adaptive and intelligent character recognizer for Telugu scripts using multiresolution analysis and associative measures. In: ICVGIP (2002)Google Scholar
  14. 14.
    Lu, H.E., Wang, P.S.P.: An improved fast parallel algorithm for thinning digital pattern. In: IEEE CVPR 1985, pp. 364–367 (1985)Google Scholar
  15. 15.
    Tarabek, P.: A robust parallel thinning algorithm for pattern recognition. In: SACI, pp. 75–79 (2012)Google Scholar
  16. 16.
    Wang, P.S.P., Hui, L.W., Fleming, T.: Further improved fast parallel thinning algorithm for digital patterns. In: Computer Vision, Image Processing and Communications Systems and Appln., pp. 37–40 (1986)Google Scholar
  17. 17.
    Zhang, T.Y., Suen, C.Y.: A fast parallel algorithm for thinning digital patterns. CACM 27, 236–239 (1984)CrossRefGoogle Scholar
  18. 18.
    Zhang, Y.Y., Wang, P.S.P.: A modified parallel thinning algorithm. In: CPR, pp. 1023–1025 (1988)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Arun K. Pujari
    • 1
  • Chandana Mitra
    • 2
  • Sagarika Mishra
    • 2
  1. 1.School of Computer & Info. SciencesUniversity of HyderabadHyderabadIndia
  2. 2.SUIITSambalpur UniversitySambalpurIndia

Personalised recommendations