Name
Abstract | ||
|---|---|---|
We describe a method for learning statistical models of images using a second-order hidden Markov mesh model. First, an image cart be segmented in a way that best matches its statistical model by an approach related to the dynamic programming rued for segmenting Markov chains. Second, given an image segmentation, a statistical model (3D state transition matrix and observation distributions within states) call be estimated. These two steps are repeated until convergence to provide both a segmentation and a statistical model of the image. We propose a statistical distance measure between images based on the similarity of their statistical models, for classification and retrieval tasks. |
Year | DOI | Venue |
|---|---|---|
2000 | 10.1109/ICPR.2000.903505 | 15TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 3, PROCEEDINGS: IMAGE, SPEECH AND SIGNAL PROCESSING |
Keywords | Field | DocType |
hidden markov model,image retrieval,convergence,markov chains,statistical model,state transition,hidden markov models,image segmentation,markov processes,markov chain,image classification,second order,probability,pixel,labeling,statistical analysis,mesh generation,dynamic programming | Computer vision,Markov process,Pattern recognition,Markov model,Computer science,Markov chain,Image segmentation,Variable-order Markov model,Statistical model,Artificial intelligence,Statistical distance,Hidden Markov model | Conference |
ISSN | Citations | PageRank |
1051-4651 | 9 | 0.78 |
References | Authors | |
1 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Daniel Dementhon | 1 | 1327 | 139.94 |
| David Doermann | 2 | 4313 | 312.70 |
| Marc Vuilleumier Stückelberg | 3 | 30 | 3.32 |