Image Denoising and Magnification via Kernel Fitting and Modified SVD

Image denoising and magnification play an important role in most visual applications such as visual material examination for public security and image-based medical diagnosis. We propose a 1-D kernel fitting algorithm for denoising in space domain and wavelet transformed (WT) domain, and for magnification in space domain. In the algorithm, the values of a column or a row from an image or its transformed version are taken as the measured results of a fitting function. The fitting coefficients are estimated by least square (LS) method. An image is denoised or magnified by resampling the fitted function, or followed by inverse transform if fitting is carried out in a transformed domain. We also discuss a modified singular value decomposition (SVD) method for comparison. To illustrate the application feasibility, the presented methods are experimentally compared with the basic wavelet-thresholding algorithm for image denoising, and with the standard bicubic interpolation method for magnification.