Initialization of Markov Random Field Clustering of Large Remote Sensing Images

T.N. Tran, H.R.M.J. Wehrens, D.H. Hoekman, L.M.C. Buydens

Research output: Contribution to journalArticleAcademicpeer-review

53 Citations (Scopus)


Markov random field (MRF) clustering, utilizing both spectral and spatial interpixel dependency information, often improves classification accuracy for remote sensing images, such as multichannel polarimetric synthetic aperture radar (SAR) images. However, it is heavily sensitive to initial conditions such as the choice of the number of clusters and their parameters. In this paper, an initialization scheme for MRF clustering approaches is suggested for remote sensing images. The proposed method derives suitable initial cluster parameters from a set of homogeneous regions, and estimates the number of clusters using the pseudolikelihood information criterion (PLIC). The method works best for an image consisting of many large homogeneous regions, such as agricultural crops areas. It is illustrated using a well-known polarimetric SAR image of Flevoland in the Netherlands. The experiment shows a superior performance compared to several other methods, such as fuzzy C-means and iterated conditional modes (ICM) clustering
Original languageEnglish
Pages (from-to)1912-1919
JournalIEEE Transactions on Geoscience and Remote Sensing
Issue number8
Publication statusPublished - 2005


  • polarimetric sar
  • unsupervised classification
  • multispectral images
  • bayes factors
  • radar images
  • model
  • segmentation
  • algorithm

Fingerprint Dive into the research topics of 'Initialization of Markov Random Field Clustering of Large Remote Sensing Images'. Together they form a unique fingerprint.

Cite this