模糊图像的反卷积复原算法-外文翻译.docx

Restoration of Blurred Images Using BlindDeconvolution AlgorithmMs.S.RamyaKalasalingam University, Anand Nagar, Krishnankoil Ms.T.Mercy ChristialKalasalingam University, Anand Nagar, KrishnankoilAbstract:Image restoration is the process of recovering the originalimage from the degraded image. Aspire of the project is torestore the blurred/degraded images using BlindDeconvolution algorithm. The fundamental task of Imagedeblurring is to de-convolute the degraded image with the PSFthat exactly describe thedistortion. Firstly, the original imageis degraded using the Degradation Model. It can be done byGaussian filter which is a low-pass filter used to blur an image.In the edges of the blurred image, the ringing effect can bedetected using Canny Edge Detection method and then it canbe removed before restoration process. Blind Deconvolutionalgorithm is applied to the blurred image. It is possible torenovate the original image without having specific knowledgeof degradation filter, additive noise and PSF. To get theeffective results[1], the Penalized Maximum Likelihood (PML)Estimation Technique is used with our proposed BlindDeconvolution Algorithm.Key words：Blind Deconvolution Algorithm; Canny EdgeDetection; Degradation Model; Image restoration; PML; PSF1 IntroductionImage deblurring is an inverse problem which whoseaspire is to recover an image which has suffered from lineardegradation. The blurring degradation can be spaceinvariantor space-in variant. Image deblurring methods canbe divided into two classes: nonblind, in which the blurringoperator is known. And blind, in which the blurring operatoris unknown[2].Blurring is a form of bandwidth reduction of the imagedue to imperfect image formation process. It can be causedby relative motion between camera and original image.Normally, an image can be degraded using low-pass filtersand its noise. This low-pass filter is used to blur/smooth theimage using certain functions.Image restoration is to improve the quality of thede