A Modified Technique of Hybrid Multiobjective Genetic Algorithm for Image Fusion

Sensors used in image acquisition. This sensor technology is going on upgrading as per user need or as per need of an application. Multiple sensors collect the information of their respective wavelength band. But one sensor is not sufficient to acquire the complete information of one scene. To gain the overall data of one part, it becomes essential to cartel the images from multiple sources. This is achieved through merging. It is the method of merging the data from dissimilar input sources to create a more informative image compared with an image from a single input source. These are multisensor photos e.g., panchromatic and multispectral images. The first image offers spatial records whereas the lateral image offers spectral data. Through visible inspections, the panchromatic photo is clearer than a multispectral photo however the grey shade image is. Articles are greater clear however nownot recognized whereasmultispectral picture displays one of a kind shades however performing distortion. So comparing the characteristics of these two images, the resultant image is greater explanatory than these enter images. Fusion is done using different transform methods as well as the Genetic Algorithm (GA). Comparing the results obtained by these methods, the output image by the GA is clearer. The feature of the resultant image is verified through parameters such as Root Mean Square Error (RMSE), peak signal to noise ratio, Mutual Information (MI), and Spatial Frequency (SF). In the subjective analysis, some transform techniques also giving exact fused images. The hybrid approach combines the transform technique and a GA is used for image fusion. This is again compared with GA results. The same performance parameters are used. And it is observed that the Hybrid Genetic Algorithm (HGA) is superior tothe AG. Here the only RMSE parameter is considered under the fitness function of the GA so only this parameter is far better than the remaining parameters. If we consider all parameters in the fitness function of the GA then all parameters using a HGA will give better performance. This method is called a Hybrid Multiobjective Genetic Algorithm (HMOGA) [14].