SAR image segmentation based on mixture context and wavelet hidden-class-label Markov random field
Computers & Mathematics with Applications
Multiscale segmentation and anomaly enhancement of SAR imagery
IEEE Transactions on Image Processing
Minimum description length synthetic aperture radar image segmentation
IEEE Transactions on Image Processing
Hi-index | 0.00 |
A new segmentation method based on Kullback-Leibler distance (KLD) of Edgeworth is proposed to accurately segment synthetic aperture radar (SAR) images into homogeneous regions and reduce the over-segmentation phenomenon. The proposed method uses a coarse-to-fine scheme. In the coarse phase, the SAR image is divided into fragments based on KLD, in which the Edgeworth expansion is employed to represent SAR data. In the fine phase, the divided fragments with the same shape or texture are merged in order to achieve an integrated segmentation. Experiments are performed based on highresolution satellite SAR images and the experimental results demonstrate the efficiency of the proposed method.