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.
Chapter PDF
Similar content being viewed by others
Keywords
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
Nagy, G., Seth, S., Vishwanathan, M.: A Prototype Document Image Analysis System for Technical Journals. Computer 25, 10–12 (1992)
Mao, S., Kanungo, T.: Emperical performance evaluation methodology and its application to page segmentation algorithms. IEEE Transactions on PAMI 23, 242–256 (2001)
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)
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)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kumar, K.S.S., Namboodiri, A., Jawahar, C.V. (2005). Learning to Segment Document Images. In: Pal, S.K., Bandyopadhyay, S., Biswas, S. (eds) Pattern Recognition and Machine Intelligence. PReMI 2005. Lecture Notes in Computer Science, vol 3776. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11590316_73
Download citation
DOI: https://doi.org/10.1007/11590316_73
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-30506-4
Online ISBN: 978-3-540-32420-1
eBook Packages: Computer ScienceComputer Science (R0)