Contents I. Introduction
One level higher than pixel level image fusion is feature level image fusion. One technique of achieving this is with a region based fusion scheme. Initially an image is segmented to produce a set of regions. Various region properties can be calculated. The properties can be used to determine which features from which images are used in the fused image. Feature level image fusion has some advantages over pixel level image fusion as more intelligent semantic fusion rules can be considered based on actual feature in the image rather than on single pixel. Feature is very important than the actual pixel. Hence it is better to incorporate the feature information in the process of fusion [1]. Segmentation algorithm plays a vital role in region based image fusion process. Features should be segmented as single regions. Feature may split into more than one region and each region has to be treated separately. If possible, less number of regions should be generated to reduce the computational burden
