Image enhancement method and system

Abstract

The invention provides an image enhancement method and system. The method includes: acquiring input brightness values, and calculating a logarithmic average value of the input brightness values; processing an input image on the basis of a Retinex image enhancement algorithm to obtain first brightness gain values; calculating and obtaining a brightness gain control factor according to the logarithmic average value of the input brightness values; calculating and obtaining second brightness gain values according to the brightness gain control factor and the first brightness gain values; and enhancing the input image according to the second brightness gain values to obtain an output image. According to the method, the Retinex image enhancement algorithm is adopted to enhance the input image, through adopting the brightness gain control factor, the first brightness gain values can be relatively highly compressed when image brightness is relatively low, and the first brightness gain values are relatively lowly compressed when the image brightness is relatively high, and thus brightness gain of a dark image can be enabled to become low; and effective control on brightness of the output image is realized, and the brightness of the output image can be enabled to be increased, and can also be enabled to accord with a real environment.

Description

technical field [0001] The invention relates to the technical field of digital image processing, in particular to an image enhancement method and system based on a Retinex image enhancement algorithm. Background technique [0002] The video capture process is affected by many factors, such as insufficient light and low brightness under shooting conditions at night or in dark light; light occlusion makes part of the formed image bright and the other part dark, resulting in uneven lighting; reflection or strong light source makes the acquired The brightness distribution of the image is uneven, and the details of the highlighted area are blurred. Insufficient illumination or uneven illumination will cause poor subjective image effects on the one hand, and it is difficult to meet the needs of people's visual senses. On the other hand, it will have a great impact on subsequent image processing such as pattern recognition and target tracking. Therefore, image enhancement technolog...

AI Technical Summary

Problems solved by technology

Multi-scale Retinex (MSR, Multi-Scale Retinex) and MSR with color restoration (MSRCR, Multi-Scales Retinex with Color Restoration) are two methods that are widely used. However, these two algorithms are not suitable for image processing with multiple light sources. The effect is not good, and it is prone to halo artifacts

For a darker image, the brightness of the output image is too high. Although it looks clearer, it is not in line with the real scene; especially when the image quality is poor, the output image is accompanied by noise, block effects, and the effect becomes worse.

Images