Research On Motion Blurred Image Restoration Based On Regularization

Image is an important source for human to access to information and which occupies an important position in modern society. However, the acquired images are always blurring due to camera shake or the movement of objects in the scene during the capture process and which seriously affects the use of the image and its subsequent processing. The purpose of image de-blurring is to recovery clear images that contain a wealth of information from blurred ones by a certain method. When the blur kernel is unknown, image deblurring problem becomes to be the so-called blind image deblurring problem, and which is a very challenging ill-posed problem. Image deblurring is an important topic in digital processing and computer vision which is widely used in areas such as photography, optics, astronomy, medical images, monitoring, remote sensing and military research et al. It’s also a hot topic of academia in recent years. Therefore, it has important theoretical and practical significance.In the thesis, a blind motion blurred image restoration problems involved in the study. The main work are at follows:Firstly, in order to make the blurred image of degradation more consistent with the generally accepted one, a fuzzy nuclear striked before the introduction of the blurred image preprocessing. According to the characteristics of the blurred image, choseing a method that combined the bilateral filter and impact filter to reduce the noise of the blurred image edge enhancement which is advantageous to the fuzzy kernel estimationSecondly, for the ill-posed problem of blind image restoration, given the use of a priori constraint solving spatially invariant blur kernel of blurred images iterative methods.Thirdly, on the basis of prior knowledge that determining the fuzzy core and clear images of statistics, analysing the experimental that can be seen the super Laplace method has a a advantage of deconvocution and can get a clear image.Finally, on the basis of existing image quality evaluation method, proposed a method that based on mahal distance method and the objective image quality evaluation method. The image of the improved algorithms is also taken into consideration, to make the structure and texture information of image evaluation more objective.