Method and device for correcting image with uneven illumination, and equipment

Abstract

The embodiment of the invention provides a method and device for correcting an image with uneven illumination, and equipment The method comprises the steps: converting a to-be-processed image into a gray-scale map, and cutting out an image block from the gray-scale map, wherein the image block comprises N * M pixel points; calculating the gradient values of each pixel point in the image block in four directions of 0 degree, 90 degrees, 180 degrees and 90 degrees, and calculating characteristic values in the four directions according to the gradient values; calculating the distance between thepixel value of each pixel point and the characteristic values in the four directions, and replacing the pixel value with the minimum value in the distances to obtain a noise image; and subtracting thenoise image subjected to feature equalization processing from the to-be-processed image to obtain a corrected image. In this way, illumination distribution points can be accurately recorded, uneven illumination parts are removed, the gradient of each pixel and neighborhood pixel values are used for obtaining features, details and edge features of the image are stored to the greatest extent, background and a foreground targets are distinguished, and the image is not prone to sharpening.

Description

technical field [0001] Embodiments of the present invention generally relate to the field of image processing, and more specifically, relate to a method, device and equipment for correcting images with uneven illumination. Background technique [0002] In the process of image acquisition, sampling, transmission and encoding, it must be affected by the external environment and the equipment itself, which will make the final image unevenly illuminated and affect the subsequent processing of the image. According to the image quality and different application scenarios, different technical means are used to reveal the useful information of the image, and to reduce or eliminate information irrelevant to the application so as to achieve the purpose of enhancing local or overall features. At present, there is no unified model or processing method for image enhancement technology, and different processing methods need to be adopted according to different scenes. Among them, for the ...

AI Technical Summary

Problems solved by technology

However, it is difficult to determine the cut-off frequency parameter based on the homomorphic filtering enhancement algorithm, which needs to be set empirically, and the processing efficiency is low

Images