Development of Image Fusion Algorithm for Impulse Noise Removal in Digital Images using the quality Assessment in Spatial Domain

Now a days remote sensing plays very important role in satellite based communication. Satellite gives images in digital format. Digital images are often corrupted during acquisition, transmission or due to faulty memory locations in hardware. The noise density varies depending on various factors namely reflective surfaces, atmospheric variations, noisy communication channels etc. Impulse noise corruption is very common in digital images. In this paper, the images captured by different sensors, producing different impulse noisy images are considered. As order statistics filters exhibit better performance, these noisy images are filtered individually using non linear filtering algorithms namely, Vector Median Filter (VMF), Rank Conditioned VMF, Rank conditioned and Threshold VMF, Center Weighted VMF and Absolute Deviation VMF. These filtered images are combined to a single image called image fusion, which retains the important features of the images from individual sensors. The filtered images are fused into a single image by using the image fusion technique which is based on the quality assessment in spatial domain. Now this fused image is again filtered using absolute deviation VMF which performs better than fused image. The performance evaluation of the filtered and the fused image with respect to the original image is done using mean square error(MSE), peak signal to noise ratio(PSNR) and structural similarity index(SSIM). KeywordsMedian Filter, Fusion, Order Static filters