Detecting changes in SAR images based on image fusion using Curvelet Transform

This paper proposes the change detection of SAR images based on image fusion which is done by curvelet transform and classifying changed and unchanged regions by using fuzzy clustering algorithm. The image fusion is a type of data fusion technique is used to generate a difference image by using mean ratio image and log Ratio image. The fused image may provide increased interpretation capabilities and more reliable results since data with different characteristics. Moreover, image fusion can be performed at three different processing levels according to the stage at which the fusion takes: pixel, feature and decision level. Here image fusion done based on curvelet transform which have better shift invariance property end directional selectivity. It is a multi-scale transforms which have the elements identified by scale and location parameter and also the directional parameter. It is an extension of wavelet concept. Curvelet transform represent the edges better than the wavelet transforms. Also a fuzzy local information C-means clustering algorithm is used for classifying the changed and unchanged regions in the fused difference image.