Multi-Sensor Image Fusion for Impulse Noise Reduction in Digital Images
Abstract – This paper introduces the concept of Multi-sensor image fusion technique for impulse noise reduction in digital images. Image fusion is the process of combining two or more images into a single image while retaining the important features of each image. Multiple sensor image fusion is an important technique used in military, remote sensing and medical applications. The images captured by five different sensors undergo filtering using five different vector median filtering algorithms and the filtered images are fused into a single image, which combines the uncorrupted pixels from each one of the filtered image. The fusion algorithm is based on quality assessment of the spatial domain from the individual de-noised images. The performance evaluation of our algorithm is evaluated using PSNR between original image and individually filtered and the fused image. Experimental results show that this fusion algorithm produce a high quality image compared to individually de-noised images.
