Natural image blind motion blur elimination method based on L0 regularization

Abstract

The invention provides a natural image blind motion blur elimination method based on L0 regularization. Gradient information of a natural image and the sparse characteristic of a motion blur core are utilized, and corresponding L0 regular terms are respectively introduced into a solving model of the blur core. In the model solving process, a half-quadratic splitting method is firstly utilized to respectively solve a middle recovered image and the blur core, a pyramid model is utilized in the solving process for carrying out solving layer by layer so as to increase the robustness, only the gradient information of the image is utilized for the estimation of the blur core, and by means of Fourier transform, the solving process is transformed to frequency domain, so that the deconvolution operation carried out directly on a space domain is avoided, and a rapid solving purpose is achieved; in addition, the obtained blur core is utilized, and a final recovered image is obtained by a non-blind deconvolution method based on the total-variable difference. The method provided by the invention has the advantages that the solving speed is high, the robustness is high, and the final recovered image has a good visual effect.

Description

technical field [0001] The present invention relates to the technical field of image restoration, and more specifically, to a method for blind motion blur removal of natural images based on L0 regularization. Background technique [0002] Images are an important way for people to obtain information in modern society. However, during the imaging process, the obtained image is often blurred due to camera shake or the movement of objects in the scene, which greatly hinders the normal use and subsequent processing of the image. [0003] Image blind deblurring can also be called image blind restoration or image blind deconvolution technology. Its purpose is to restore a clear image from a blurred image, and image blind motion blur is one of the important topics in image restoration. It is widely used in astronomical detection, military reconnaissance and early warning, public safety, and medical images. processing, etc., has very important practical significance. [0004] Ther...

AI Technical Summary

Problems solved by technology

[0004] There are two main difficulties in image blind motion blur removal. The first difficulty is how to accurately estimate the motion blur trajectory or also called blur kernel. Compared with non-blind image restoration, blind image restoration has higher pathological characteristics. Because it lacks prior knowledge and needs to estimate the two unknowns of blur kernel and clear image

The second difficulty is how to ensure that image blind motion blur removal has high robustness and achieves fast convergence

In the prior art, the prior constraints introduced in the simplest blind restoration model are based on the L2 or L1 paradigm. Although the introduction of the L2 paradigm can make the restoration model quickly solved, it will cause the estimated blur kernel to be dense, which will affect the final The restored image quality, and the restoration model based on the L1 paradigm will result in the estimation of discontinuous and noisy blur kernels, which will affect the final restored image quality

Images