SAR Image Segmentation with Superpixel Constraint and Fuzzy Clustering

Abstract

Image segmentation is a very important task in the application of synthetic aperture radar (SAR) images, especially to feature extraction of SAR images. Because of speckle noise in SAR images, it is easy to produce many isolated points if fuzzy clustering is performed directly on SAR images. Aiming at this, a SAR image segmentation method based on superpixel constraints and fuzzy clustering is proposed in this paper, which is named FCM_SS. The FCM_SS algorithm firstly introduces the improved SNIC algorithm to produce uniform superpixels, and then averages the pixels in the superpixels, which are used as the input for subsequent fuzzy clustering. The experimental results suggest that the FCM_SS algorithm has high segmentation accuracy and strong robustness to noise.