Segmentation of Sar Images Using Fuzzy C Means with Non Local Spatial Information

The Segmentation of the Images refers to extracting the needed region from the image based on some specified methodologies. Thresholding Approach, Model-based Approach, Level Set Approach are some of the segmentation methodologies. The clustering methodologies can provide accurate results for most of the cases. As the number of clusters separated from the image increases, the segmentation accuracy also increases. The fuzzy c means is one of the clustering based methodologies. It has been extensively used for segmentation of images. Even FCM has some drawback. The main drawback is that the performance is degraded by noise. This problem can be overcome by Fuzzy C Means with Non Local spatial Information which can be derived from the pixels with similar neighborhood configuration to the current pixels so that impact of Noise level in the Image is reduced. Experimental results obtained for synthetic and real SAR (Synthetic Aperture Radar) Images demonstrate the improved robustness and effectiveness.