Texture feature fusion-based segmentation method of SAR images
一种基于纹理特征融合的SAR图像分割方法

This paper presented a new method for segmentation of synthetic aperture radar (SAR) images. It proposed a Gaussian autoregressive (GAR) model under a multiresolution pairwise Markov framework based on texture feature fusion images from in part gray level co-occurrence probability statistics, examined the texture segmentation of SAR image using the multi-resolution maximization of the posterior marginal (MPM) estimate with corresponding unsupervised segmentation algorithm on those texture feature fusion images. This method used the pixel gray level information, and also used pixel space location information, reduced the speckle noise effect for the segmentation. For some SAR images, compared with multiresolution pariwise Markov-GAR model texture segmentation based on gray level images, the results of experimentation show that the segmentation precision can be improved by the method in this paper.