Synthetic aperture radar image segmentation using fuzzy label field‐based triplet Markov fields model

• DOI: 10.1049/iet-ipr.2013.0686
• Publication Date: 2014-07-25T16:30:58Z
• Authors: Fan Wang; Yan Wu; Jianwei Fan; Xue Zhang; Qiang Zhang; Ming Li
• Keywords: Markov random field

The recently proposed triplet Markov random fields (TMF) model is very suitable for dealing with non‐stationary image segmentation. However, influenced by multiplicative speckle noise, synthetic aperture radar (SAR) dim and blurred in the boundaries of different areas, making it difficult to locate boundary accurately segmentation process. Thus, this study, authors propose a new algorithm using fuzzy label field‐based TMF SAR images. In algorithm, value each site field extended from finite discrete set classical continuous one, order describe memberships pixel classes. A energy function constructed joint prior distribution auxiliary field. construction also takes into account four direction information degree difference between neighbouring pixels. Iterative conditional estimation method maximum posterior mode criterion are applied implement parameter Experimental results on simulated data real images demonstrate effectiveness algorithm.