Abstract | ||
---|---|---|
In this paper, we are interested in massively parallel multiscale relaxation algorithms applied to image classification. First, we present a classical multiscale model applied to supervised image classification. The model consists of a label pyramid and a whole observation field. The potential functions of the coarse grid are derived by simple computations. Then, we propose another scheme introducing a local interaction between two neighbor grids in the label pyramid. This is a way to incorporate cliques with far apart sites for a reasonable price. Finally we present the results on noisy synthetic data and on a SPOT image obtained by different relaxation methods using these models. |
Year | DOI | Venue |
---|---|---|
1993 | 10.1109/ICASSP.1993.319766 | ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: image and multidimensional signal processing - Volume V |
Keywords | Field | DocType |
Markov processes,hierarchical systems,image recognition,parallel algorithms,relaxation theory,SPOT image,cliques,image classification,label pyramid,massively parallel multiscale relaxation algorithms,multiscale Markov random fields | Random field,Pattern recognition,Parallel algorithm,Massively parallel,Computer science,Markov chain,Synthetic data,Artificial intelligence,Pyramid,Contextual image classification,Grid | Conference |
Volume | ISBN | Citations |
5 | 0-7803-0946-4 | 11 |
PageRank | References | Authors |
3.92 | 2 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zoltan Kato | 1 | 265 | 28.28 |
Marc Berthod | 2 | 429 | 163.29 |
Josiane Zerubia | 3 | 2032 | 232.91 |