Blind deblurring method for image quality evaluation

Abstract

The invention discloses a blind deblurring method for image quality evaluation, and mainly solves the problems of distortion and scratches which are produced in the iterative deblurring process of most images. The blind deblurring method comprises the following steps: (1) initializing a blurring kernel vk into a Gaussian pulse function, initializing an evaluation image yk into a blurred image z, setting an initial iteration index k=0, and setting the maximum number of iterations kmax; (2) solving the image yk and denoising the image yk; (3) performing quality evaluation on the image yk, if the quality evaluation value is the current minimum value, storing the yk and setting the yk as an optimal image yA, otherwise solving the blurring kernel vk and denoising the blurring kernel vk; (4) setting k=k+1, if k>kmax, performing step (5), otherwise returning to the step (2); and (5) convolving the image yA by a Gaussian function H to obtain an image yB, and performing non-blind deblurring on the yB by using a total variation iteration method to obtain the final deblurred image F. By using the blind deblurring method, a clear image can be recovered; the ringing effect and distortion are reduced; scratches of the image, which are caused in the iteration process, can be repaired; and the method can be used for performing blind deblurring on various blurred images.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a blind deblurring method for blurred images, which can be used for deblurring blurred images of various unknown blur types. Background technique [0002] In real life, due to the limitations of the physical characteristics of the observation system itself and the influence of the observation environment, there are inevitably deviations and distortions between the observed image and the real image, which is called image degradation or image degradation. Image deblurring is the inverse process of image degradation or degradation. Image deblurring is a common problem in the field of image processing, and has become a research hotspot because of its importance and difficulty. There are two types of image deblurring: non-blind image deblurring and blind image deblurring. Image non-blind deblurring refers to knowing the blur kernel in the degradation process, and then findi...

AI Technical Summary

Problems solved by technology

This method can achieve the purpose of deblurring to a certain extent, but it is easy to produce image scratches in the iteration of frequency domain and time domain, which affects the visual effect

Images