Blind Separation Of Permuted Alias Image With Motion Blurred Based On NSCT Domain

Blind source separation is observed only from the complex signal,separating with an unknown source process,signal processing category of research focus,which are widely used in the fields of image processing,radar,biomedicine.Permuted alias image is a special single-channel mixed signal,which is different from the traditional superposition alias mode.It is difficult to separate from the permuting image using traditional methods and theories.This dissertation focused on the issue that motion blurred permuted alias image blind separation based on NSCT domain was proposed.Because NSCT domain has good directionality and anisotropy,the motion blurred permuted alias image was obtained by spare decomposition based on NSCT domain.Since separating the permuting image is to extract variation characters of the permuting image and the permuted image,which can be set an appropriate threshold to separate the permuting image.The main contributions of this research are summarized as follows:(1)Through the mathematical model of the existing image analysis,the permuting image is motion blurred version was proposed.Using the advantage of NSCT domain with good directionality and anisotropy,the issue that motion blurred permuted alias image blind separation based on NSCT domain was proposed.(2)Focused on the issue that blind separation of motion blurred permuted alias image,using double blur correlation blind separation based on NSCT domain was proposed.There are differences between the motion blurred permuted alias image and the nature image,obtaining extraction characteristic differences through spare decomposition based on NSCT domain.Firstly,the permuted alias image was blurred again,low frequency sub-band coefficients and varieties of directional bandpass sub-band coefficients of the original image and the blurred version were obtained by spare decomposition based on NSCT domain.Secondly,summation image was gotten by coefficient redundancy.Then,the summation image was blocked,the correlation coefficients were estimated by each corresponding sub-block,the permuting image could be separated by using threshold method.Experimental results show that the proposed algorithm can separate the permuting image effectively from the permuted alias image in spite of the motion blurred direction,blur degree,size,location and number of permuting image.(3)Focused on the issue that blind separation of motion blurred permuted alias image,an algorithm using image enhancement based on NSCT domain was proposed.Permuted alias image was decomposed into one low-frequency sub-band and many high-frequency sub-bands,which were achieved by spare decomposition based on NSCT.Coefficients of high-frequency sub-bands were enhanced in accordance with nonlinear gain function and Bayesian shrinkage threshold,and the enhanced version was got by this method.Then the permuted alias image and the enhanced version were blocked,the correlation coefficients were estimated by each corresponding sub-block,because the permuting image was changed larger,the permuting image could be separated by using threshold method.Experimental results show that the proposed algorithm can separate the permuting image effectively from the permuted alias image in spite of the blur degree,location,size,and the number of permuting image.