Image enhancement method based on non-convex total variation type regularization

Abstract

The invention provides an image enhancement method based on non-convex total variation regularization, which is used for solving the problem that the existing image enhancement method has little attention to noise, does not consider the sparsity of an image and cannot obtain a high-quality restoration result. According to the method, data fitting items based on exponential transformation and one regular item are adopted to describe noise prior information, and then the sparsity of piecewise constants is punished by utilizing the regular item of a non-convex total variation (simulation) norm. According to the image structure, the index p is selected from (0, 1); and finally, based on a Retinex theory, calculating an illumination part, and removing illumination to obtain a reflection part, i.e., essential characteristics of the image, so as to achieve the purpose of offset field correction. According to the method, the interference of noise on the image is considered, the sparsity of theimage is punished through the regularization term, and meanwhile, logarithm transformation is replaced by exponential transformation, so that the contrast ratio is improved, and the model has higherrobustness.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image enhancement method based on non-convex total variation (TV) regularization, mainly related to image offset field correction, which can be used for uneven illumination and color images of medical images shadow removal etc. Background technique [0002] Given an image, the human visual system tends to see the same color under different lighting conditions, a phenomenon known as color constancy. In other words, it ensures that information such as the color and grayscale of the object remains unchanged in the case of lighting changes. The most typical example is the Adelson checkerboard shadow illusion, such as figure 2 As shown in (a), region A is visually darker than region B. However, if you directly open the image with a drawing software and use the color picker function to confirm, you will find that the colors of these two areas are exactly the same...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the technical problems that the existing image enhancement methods rarely pay attention to the existence of noise, do not consider the sparsity of the image, and cannot obtain high-quality restoration results, the present invention proposes a method based on The image enhancement method of non-convex fully variable fractal regularization takes into account the interference of noise on the image, and punishes the sparsity of the image through the regularization term to improve the restoration result of the image

Images