Contextual Reclassification of Multispectral Images: A Markov Random Field Approach

This work presents methods for multispectral image classification using the contextual classifiers based on Markov Random Field (MRF) models. Performance of some conventional classification methods is evaluated, through a Monte Carlo study, with or without using the contextual reclassification. Spatial autocorrelation is present in the computer-generated data on a true scene. The total misclassification rates for varying strengths of autocorrelation and for different methods are compared. The results indicate that the combination of the spectral-contextual classifiers can improve to a great extent the accuracy of conventional non-contextual classification methods. It is also shown how the most complicated cases can be handled by the Gibbs sampler.