Retinex-theory-based nonlinear image enhancement method and system

Abstract

The invention relates to the field of image enhancement and discloses a Retinex-theory-based nonlinear image enhancement method and system. According to the method and the system, a gradient-domain-transformation-based edge-preserving filter manner is used for replacing the conventional Gaussian filter manner to obtain illumination components. On the one hand, the phenomenon of halo artifact near a high-contrast edge is effectively overcome; on the other hand, the edge-preserving filter of color images can be carried out in real time. In addition, a nonlinear compression function is constructed on account of the illumination components, a highlight area is suppressed and a dark area is effectively improved; the phenomenon of overexposure of the images is avoided; the image luminance is mapped to an ideal dynamic range; a self-adaptive local nonlinear enhancement manner is used for enhancing image details, so that the local details of reflection components are enhanced, the quality of the images is well improved; the enhanced images are closer to real natural sites; the details are more clear.

Description

technical field [0001] The invention relates to the field of image enhancement, in particular to the field of nonlinear image enhancement based on Retinex theory. Background technique [0002] Retinex is a compound word composed of retina (retina) + cortex (cerebral cortex). [0003] The Retinex theory is a computational theory based on a large number of experiments by Edwin H.Land based on the perception model of brightness and color of human vision. He believes that color constancy is the result of the joint action of the retina and the cerebral cortex. Among them, the human eye's perception of the color of an object depends on the reflection characteristics of the object's surface to light with three wavelengths of long-wave, medium-wave and short-wave. The long-wave, medium-wave, and short-wave light rays correspond to the three color channels of R, G, and B of the digital image respectively. The image to be enhanced in the three channels of R, G, and B is regarded as...

AI Technical Summary

Problems solved by technology

The inventors of the present invention found that this method requires multiple iterations to obtain the illumination map by means of mean shift filtering, and the calculation speed is slow, and the global Gamma correction for the brightness component not only stretches the dark area of ​​the image, but also further enlarges the image The high light area of ​​the image makes the image appear "overexposed" phenomenon

Images