Super-Resolution algorithms reconstruct a high resolution image from a set of low resolution images of a scene. An accurate image registration is a fundamental stage in all Super-Resolution methods. In this paper a new restriction criteria for matching SIFT key points, for regis- tration under the condition of Super-Resolution problems is proposed. This is based on the assumption of normal dis- tribution for location and orientation differences of correct matches under global translational motion model. The ac- curacy of the proposed method is compared with some fa- mous registration methods. A quantitative comparison has been done with a collective of images with known motion vectors. Also a subjective comparison has been done with the results of various registration methods including the proposed method for Super-Resolution. The experimental results show the better performance of the proposed algo- rithm in compare with some other registration methods

Keywords