Image fusion at pixel and feature levels based on pyramid imaging

Advancement in the recent technology affects a wide research in the field of Image Fusion. It is the more researched challenges in Computer vision, Remote sensing, Medical Imaging, and Target Recognition. The idea behind the image fusion is merging complementary and redundant information from multiple images in such a way, as to retain the most desirable characteristics of every image. The single fused image is relatively high informative when compared to the original images. The Laplacian pyramid method is a Multi-resolution method, in which low resolution images are fused to produce a high resolution image. This paper mainly worked on multi resolution images of same scene and provides results of performance measures namely mean, standard deviation, entropy, Peak Signal to Noise Ratio at Pixel-Level fusion, Feature-Level fusion using techniques like Simple average method, Principle Component Analysis method based on Laplacian pyramid levels of images. Results also include Histograms of both source images and fused output image. These results show higher resolution and better features than the original images.