Handwritten document segmentation using hidden Markov random fields

  title={Handwritten document segmentation using hidden Markov random fields},
  author={St{\'e}phane D Nicolas and Yousri Kessentini and Thierry Paquet and Laurent Heutte},
  journal={Eighth International Conference on Document Analysis and Recognition (ICDAR'05)},
  pages={212-216 Vol. 1}
In this paper we present a method based on hidden Markov random fields and 2D dynamic programming image decoding, for segmenting pages of complex handwritten manuscripts such as novelist drafts. After a formal description of the theoretical framework and the principles of the decoding method, we describe the implementation of the model and the decoding method. Then we discuss the results obtained with this approach on the drafts of the French novelist Gustave Flaubert. 
10 Citations
6 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 10 extracted citations


Publications referenced by this paper.
Showing 1-6 of 6 references

Multi-dimensional Dynamic Programming for statistical image segmentation and recognition

  • E. Geoffrois
  • International Conference on Image and Signal…
  • 2003
Highly Influential
4 Excerpts

Geman , Stochastic relaxation , Gibbs distributions and the Bayesian restoration of images

  • D. S. Geman
  • Markov Random FieldsTheory and application
  • 1993

Similar Papers

Loading similar papers…