A robust Markovian segmentation based on highest confidence first (HCF)
Thomas Meier, King Ngi Ngan, Gregory A. Crebbin · 2002
A new robust method to segment images based on Markov random fields (MRF) is presented. The algorithm does not require the number of classes or regions K as input, which is normally difficult to determine in advance. There is also no need for an initial estimate obtained by an algorithm such as K-means. Further, each region is connected during the whole segmentation process leading to more reliable estimates of the regions' mean gray levels and to fewer wrong detected boundaries. In addition, a novel way to incorporate edge information into the segmentation process is proposed resulting in a better detection of small objects. Experimental results demonstrate the performance of our technique.