Color image segmentation and parameter estimation in a markovian framework

Citation
Z. Kato et al., Color image segmentation and parameter estimation in a markovian framework, PATT REC L, 22(3-4), 2001, pp. 309-321
Citations number
15
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
PATTERN RECOGNITION LETTERS
ISSN journal
01678655 → ACNP
Volume
22
Issue
3-4
Year of publication
2001
Pages
309 - 321
Database
ISI
SICI code
0167-8655(200103)22:3-4<309:CISAPE>2.0.ZU;2-F
Abstract
An unsupervised color image segmentation algorithm is presented, using a Ma rkov random field (MRF) pixel classification model. We propose a new method to estimate initial mean vectors effectively even if the histogram does no t have clearly distinguishable peaks. The only parameter supplied by the us er is the number of classes. (C) 2001 Elsevier Science B.V. All rights rese rved.