Study on image denoising method based on an adaptive total variation model

In this paper, we present an algorithm for the restoration of images with an noisy, spatially-varying blur. Existing denoising methods for image restoration require the assumption that image is smooth or not existing edges. Our algorithm used an adaptive TV denoising model. First, we computed the order of regular terms which depending on local information of image, and then used the conjugate gradient method for solving linear equations which had the advantage of fast convergence. Finally, we used Lucy-Richardson iterative algorithm to restore the degraded image. The experimental results show that the effect of an Adaptive TV denoising model in image restoration is evident, and it keeps the image edge and texture information while denoising, avoiding the staircase effect. Peak Signal to Noise Ratio (PSNR) of the restored image is greatly improved comparing with other methods.