HVS Inspired System for Script Identification in Indian Multi-script Documents

  • Peeta Basa Pati
  • A. G. Ramakrishnan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3872)

Abstract

Identification of the script of the text, present in multi-script documents, is one of the important first steps in the design of an OCR system. Much work has been reported relating to Roman, Arabic, Chinese, Korean and Japanese scripts. Though some work has already been reported involving Indian scripts, the work is still in its nascent stage. For example, most of the work assumes that the script changes only at the level of the line, which is rarely an acceptable assumption in the Indian scenario. In this work, we report a script identification algorithm, which takes into account the fact that the script changes at the word level in most Indian bilingual or multilingual documents. Initially, we deal with the identification of the script of words, using Gabor filters, in a bi-script scenario. Later, we extend this to tri-script and then, five-script scenarios. The combination of Gabor features with nearest neighbor classifier shows promising results. Words of different font styles and sizes are used. We have shown that our identification scheme, inspired from the Human Visual System (HVS), utilizing the same feature and classifier combination, works consistently well for any of the combination of scripts experimented.

Keywords

Gabor filter script identification prototype selection 

References

  1. 1.
    Spitz, A.L.: Determination of Script and Language Content of Document Images. IEEE transaction on Pattern Analysis and Machine Intelligence 19, 235–245 (1997)CrossRefGoogle Scholar
  2. 2.
    Hochberg, J., Kelly, P., Thomas, T., Kerns, L.: Automatic script identification from document images using cluster based templates. IEEE transaction on Pattern Analysis and Machine Intelligence 19, 176–181 (1997)CrossRefGoogle Scholar
  3. 3.
    Wood, S.L., Yao, X., Krishnamurthi, K., Dang, L.: Language identification for printed text independent of segmentation. In: Proc. of Intl. Conf. on Image Processing, pp. 428–431 (1995)Google Scholar
  4. 4.
    Tan, T.N.: Rotation invariant texture features and their use in automatic script identification. IEEE transaction on Pattern Analysis and Machine Intelligence 20, 751–756 (1998)CrossRefGoogle Scholar
  5. 5.
    Chaudhuri, A.R., Mandal, A.K., Chaudhuri, B.B.: Page layout analyser for multilingual indian documents. In: Proceedings of the Language Engineering Conference, pp. 24–32 (2002)Google Scholar
  6. 6.
    Pal, U., Chaudhuri, B.B.: Script line separation from Indian muli-script document. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 406–409 (1999)Google Scholar
  7. 7.
    Chaudhuri, S., Seth, R.: Trainable Script Identification Strategies for Indian languages. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 657–660 (1999)Google Scholar
  8. 8.
    Dhanya, D., Ramakrishnan, A.G., Pati, P.B.: Script identification in printed bilingual docuements. Sadhana 27, 73–82 (2002)CrossRefGoogle Scholar
  9. 9.
    Pati, P.B., Raju, S.S., Pati, N.K., Ramakrishnan, A.G.: Gabor filters for document analysis in indian bilingual documents. In: Proc. of the Int. Conf. on Intelligent Sensing and Information Processing, pp. 123–126 (2004)Google Scholar
  10. 10.
    Pal, U., Sinha, S., Chaudhury, B.B.: Word-wise script identification from a document containing english, devanagari and telugu text. In: Proc. of National Conf. on Document Analysis and Recognition, pp. 213–220 (2003)Google Scholar
  11. 11.
    Padma, M.C., Nagabhushana, P.: Identification and separation of text words of kannada, hindi and english languages through discriminating features. In: Proc. of National Conf. on Document Analysis and Recognition, pp. 252–260 (2003)Google Scholar
  12. 12.
    Pati, P.B.: Indian Script Word Image Dataset, http://www.ee.iisc.ernet.in/new/people/students/phd/pati/
  13. 13.
    Gabor, D.: Theory of communication. J. IEE 93, 429–457 (1946)Google Scholar
  14. 14.
    Daugman, J.: Uncertainty relation for resolution in space, spatial frequency and orientation optimized by two-dimensional visual cortical filters. J. Opt. Soc. Am. A 2, 1160–1169 (1985)CrossRefGoogle Scholar
  15. 15.
    Marcelja, S.: Mathematical description of the response of simple cortical cells. J. Opt. Soc. Am. 70, 1297–1300 (1980)CrossRefMathSciNetGoogle Scholar
  16. 16.
    Campbell, F.W., Robson, J.G.: Application of Fourier analysis to the visibility of gratings. J. Physiol. 197, 551–566 (1968)Google Scholar
  17. 17.
    Morrone, M.C., Burr, D.C.: Feature detection in human vision: a phase dependent energy model. Proc. Roy. Soc. Lon(B) 235, 221–245 (1988)CrossRefGoogle Scholar
  18. 18.
    Porat, M., Zeevi, Y.Y.: The generalized gabor scheme of image representation in biological and machine vision. IEEE transaction on Pattern Analysis and Machine Intelligence 10, 452–467 (1988)MATHCrossRefGoogle Scholar
  19. 19.
    Jain, A.K., Farrokhnia, F.: Unsupervised texture segmentation using Gabor filters. Pattern Recognition 24, 1167–1186 (1991)CrossRefGoogle Scholar
  20. 20.
    Chan, W., Coghill, G.: Text analysis using local energy. Pattern Recognition 34, 2523–2532 (2001)MATHCrossRefGoogle Scholar
  21. 21.
    Raju, S.S., Pati, P.B., Ramakrishnan, A.G.: Gabor filter based block energy analysis for text extraction from digital document images. In: Proc. of the First Int. Workshop on Document Image Analysis for Libraries, DIAL 2004 (2004)Google Scholar
  22. 22.
    Devi, V.S., Murthy, M.N.: An incremental prototype set building technique. Pattern Recognition 35, 505–513 (2002)MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Peeta Basa Pati
    • 1
  • A. G. Ramakrishnan
    • 1
  1. 1.Department of Electrical EngineeringIndian Institute of ScienceBangaloreIndia

Personalised recommendations