Image Fusion By Global Energy Merging

One of the most important fields about image analysis and computer vision is image fusion. With the development of multi-sensors, it is possible to obtain data from different sensors A new and improved image can be got if taking into account all the images. So image fusion has emerged as a promising research field in recent years and it is of great importance in many applications, such as medical imaging, object detection, Automatic Target Recognition, remote sensing, computer vision, smart buildings, complex machinery, meteorological imaging and military applications. This paper proposes Image fusion by using Global Energy merging scheme in discrete wavelet Transform. The scheme used is a region-based analysis approach. Multi-resolution wavelet decomposition on each source image is performed and the energy of each 3*3 matrix region is calculated. The match measures are calculated for the fused image, it can be produced using wavelet decomposition coefficient and the energy. Finally by applying the inverse wavelet transform the final fused image is obtained. The fused images can preserve more relevant information about edges. Experiments showed that proposed paper will have very low RMSE (Root Mean Square Error) value and high quality fused image there by resulting in better performance than existing image fusion methods.