Super Resolution and Denoising of Images via Dictionary Learning

Improving the quality of image has always been an issue of image technology. Enhancing the quality of image is a continuous ongoing process. To ensure the quality of image in image processing noise estimation and removal are very important step before analysis or using image. An example-based method for super-resolution and denoising of images is proposed. The objective is to estimate a high-resolution image from a noisy low-resolution image, with the help of a given database of high and low-resolution image patch pairs. This method uses a redundant dictionary learning to reconstruct the HR image. The redundant dictionary is trained by K-SVD algorithm which is an iterative method that alternates between sparse coding of the examples based on the current dictionary, and a process of updating the dictionary atoms to better fit the data. Denoising and super-resolution of images in this paper is performed on each image patch. In this paper K-means Singular Value Decomposition (K-SVD) and Iterative Back Projection methods are proposed for denoising and Super Resolution of images. These algorithms significantly improve the resolution and eliminate the blur and noise associated with low resolution images, when compared with the other existing methods.