Learning to Segment Document Images

  • K. S. Sesh Kumar
  • Anoop Namboodiri
  • C. V. Jawahar
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3776)

Abstract

A hierarchical framework for document segmentation is proposed as an optimization problem. The model incorporates the dependencies between various levels of the hierarchy unlike traditional document segmentation algorithms. This framework is applied to learn the parameters of the document segmentation algorithm using optimization methods like gradient descent and Q-learning. The novelty of our approach lies in learning the segmentation parameters in the absence of groundtruth.

Keywords

Segmentation Algorithm Document Image Text Line Foreground Pixel Text Block 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Nagy, G., Seth, S., Vishwanathan, M.: A Prototype Document Image Analysis System for Technical Journals. Computer 25, 10–12 (1992)CrossRefGoogle Scholar
  2. 2.
    Mao, S., Kanungo, T.: Emperical performance evaluation methodology and its application to page segmentation algorithms. IEEE Transactions on PAMI 23, 242–256 (2001)Google Scholar
  3. 3.
    Sylwester, D., Seth, S.: Adaptive segmentation of document images. In: Proceedings of the Sixth International Conference on Document Analysis and Recognition, Seattle, WA, pp. 827–831 (2001)Google Scholar
  4. 4.
    Peng, J., Bhanu, B.: Delayed reinforcement learning for adaptive image segmentation and feature extraction. IEEE Transactions on Systems, Man and Cybernetics 28, 482–488 (1998)CrossRefGoogle Scholar
  5. 5.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • K. S. Sesh Kumar
    • 1
  • Anoop Namboodiri
    • 1
  • C. V. Jawahar
    • 1
  1. 1.Centre for Visual Information TechnologyInternational Institute of Information TechnologyHyderabadIndia

Personalised recommendations