Two stage image de-noising by SVD on large scale heterogeneous anisotropic diffused image data

Abstract

De-noising of images along with the edge enhancement has always been a challenging task in large scale heterogeneous image data. This paper presents a two stage image de-noising as well as edge enhancement method where in the first stage two copies of input noisy image are created through diffusion. The first copy is got by using anisotropic diffusion method which employ optimal diffusion function while the second copy is generated to improve the sharp edges by applying the combination of inverse heat diffusion and Canny edge detector. In the next stage, the singular value decomposition is applied on the two copies achieved in first stage to reduce the noise and improve the quality of detected edges. The optimal number of significant singular values have been estimated by the analysis of signal to noise ratio of singular value decomposed images of first copy. The singular values extracted from the second copy of the diffused image are superimposed with non decreasing weights from linear weighting function. Finally the sharp edged and noise reduced output image is generated by taking the linear combination of two singular value decomposed images. The performance of the proposed method has been compared with existing methods based on singular value decomposition as well as anisotropic diffusion. The experimental results exhibit that the proposed method efficiently enhances the edges by reducing the noisy significantly.