Self Adaptable Recognizer for Document Image Collections

  • Million Meshesha
  • C. V. Jawahar
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4815)


This paper presents an architecture that enables the recognizer to learn incrementally and, thereby adapt to document image collections for performance improvement. We argue that the recognition scheme for a book could be considerably different from that designed for isolated pages. We employ learning procedures to capture the relevant information available online, and feed it back to update the knowledge of the system. Experimental results show the effectiveness of our design for improving the performance on-the-fly.


  1. 1.
    Feng, S., Manmatha, R.: A hierarchical, HMM-based automatic evaluation of OCR accuracy for a digital library of books. In: Joint Conference on Digital Libraries (JCDL), pp. 109–118 (2006)Google Scholar
  2. 2.
    Sankar, P., et al.: Digitizing a million books: Challenges for document analysis. In: Proc. of the Seventh IAPR Workshop on Document Analysis Systems, pp. 425–436 (2006)Google Scholar
  3. 3.
    Lin, X.: DRR research beyond COTS OCR software: A survey. In: SPIE Conference on Document Recognition and Retrieval XII, San Jose, CA, pp. 16–20 (2005)Google Scholar
  4. 4.
    Xu, Y., Nagy, G.: Prototype extraction and adaptive OCR. IEEE Transactions on Pattern Analysis and Machine Intelligence 21, 1280–1296 (1999)CrossRefGoogle Scholar
  5. 5.
    Hastie, T., Tibshirani, R., Friedman, J.: The elements of statistical learning. Springer, Heidelberg (2001)Google Scholar
  6. 6.
    Nagy, G.: Twenty years of document image analysis in PAMI. IEEE Transactions on Pattern Analysis and Machine Intelligence 22, 38–62 (2000)CrossRefMathSciNetGoogle Scholar
  7. 7.
    Kahan, S., Pavlidis, T., Baird, H.S.: On the recognition of printed characters of any font and size. IEEE Transactions on Pattern Analysis and Machine Intelligence 9, 274–288 (1987)CrossRefGoogle Scholar
  8. 8.
    Rawat, S., et al.: A semi-automatic adaptive OCR for digital libraries. In: Proc. of the Seventh IAPR Workshop on Document Analysis Systems, pp. 13–24 (2006)Google Scholar
  9. 9.
    Ivanov, Y., Blumberg, B., Pentland, A.: Expectation maximization for weakly labeled data. In: Proc. of the Int. Conf. on Machine Learning, pp. 218–225 (2001)Google Scholar
  10. 10.
    Iyengar, V.S., Apte, C., Zhang, T.: Active learning using adaptive resampling. In: Sixth Int. Conference on Knowledge Discovery and Data Mining, pp. 92–98 (2000)Google Scholar
  11. 11.
    Diehl, C., Cauwenberghs, G.: SVM incremental learning, adaptation and optimization. In: Proc. IEEE Int. Joint Conf. Neural Networks, pp. 2685–2690 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Million Meshesha
    • 1
  • C. V. Jawahar
    • 1
  1. 1.Center for Visual Information Technology, International Institute of Information Technology, Hyderabad - 500 032India

Personalised recommendations