| Paper: | IMDSP-P13.4 | ||
| Session: | Image Modeling | ||
| Time: | Thursday, May 18, 16:30 - 18:30 | ||
| Presentation: | Poster | ||
| Topic: | Image and Multidimensional Signal Processing: Modeling | ||
| Title: | MULTI-DIMENSIONAL DEPENDENCY-TREE HIDDEN MARKOV MODELS | ||
| Authors: | Bernard Merialdo, Joakim Jiten, Benoit Huet, Institut Eurecom, France | ||
| Abstract: | In this paper, we propose a new type of multi-dimensional Hidden Markov Model based on the idea of Dependency Tree between positions. This simplification leads to an efficient implementation of the re-estimation algorithms, while keeping a mix of horizontal and vertical dependencies between positions. We explain the DT-HMM and we present the formulas for the Maximum Likelihood re-estimation. We illustrate the algorithm by training a 2-dimensional model on a set of coherent images. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012