Efficient image de-noising and edge enhancement by singular value decomposition on anisotropie diffused image data

This paper presents a two stage process for image de-noising and edge enhancement by applying singular value decomposition technique on anisotropic diffused images. The two diffused versions of the input noisy image are generated in the first stage by anisotropic diffusion. The first diffused image is a well smoothed image and the second diffused image is sharp edge detected image. Singular value decomposition is applied on the two diffused versions individually to remove noise and to sharpen the detected edges respectively. Finally, the two singular value decomposition filtered images are linearly added to get the output image with reduced noise and sharp edges. Experimental results have been compared with recently developed singular value decomposition techniques and advanced anisotropic diffusion methods in terms of signal to noise ratio which shows that the proposed method is efficient for image enhancement as well as de-noising.