Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/ICDAR.2005.124 | ICDAR-1 |
Keywords | Field | DocType |
decoding method,handwritten document segmentation,french novelist,theoretical framework,novelist draft,hidden markov random fields,dynamic programming image decoding,formal description,gustave flaubert,complex handwritten manuscript,hidden markov models,image segmentation,dynamic programming,decoding | Dynamic programming,Random field,Pattern recognition,Computer science,Document segmentation,Formal description,Image segmentation,Artificial intelligence,Decoding methods,Hidden Markov model,Viterbi algorithm | Conference |
ISSN | ISBN | Citations |
1520-5363 | 0-7695-2420-6 | 5 |
PageRank | References | Authors |
0.76 | 3 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Stéphane Nicolas | 1 | 77 | 9.64 |
Yousri Kessentini | 2 | 100 | 15.39 |
Thierry Paquet | 3 | 565 | 56.65 |
Laurent Heutte | 4 | 1231 | 100.21 |