Image enhancement method and system, and storable medium

Abstract

The invention discloses an image enhancement method and system, and a storable medium, and relates to the field of image processing. The method comprises the following steps: inputting a to-be-recognized image; obtaining an edge contour enhancement image of the to-be-recognized image and a contrast limit histogram of the to-be-recognized image; calculating a local contrast difference between the edge contour enhancement image and the contrast-limited histogram of the to-be-recognized image; calculating a weight fusion function of the contrast difference through an anti-trigonometric function; and obtaining a final picture through the weight fusion function. According to the method, a high-quality fused image can be generated, and the nature of hue, saturation and brightness is kept while most details of an original input image are obtained.

Description

technical field [0001] The present invention relates to the field of technical image processing, and more specifically relates to an image enhancement method, system, and storage medium. Background technique [0002] At present, the methods of endoscopic image enhancement mainly include: methods based on histogram enhancement; methods based on machine learning; methods based on homomorphic filtering. All of the above methods have their own advantages and disadvantages, and no one method can completely replace the other methods. It is very difficult for an endoscopic image enhancement algorithm to have a good enhancement effect on all endoscopic images. [0003] 1. Method based on histogram enhancement; [0004] The grayscale histogram of the image represents the number of each grayscale pixel in the grayscale image, which reflects the frequency of each grayscale in the image and is one of the basic statistical characteristics of the image. The histogram equalization metho...

AI Technical Summary

Problems solved by technology

There are two shortcomings in the enhancement of grayscale images through histograms: one is that the gray level of the processed image is reduced, causing some details to disappear; the other is that some images, such as the histogram has peaks, etc. Contrast tends to be unnaturally over-enhanced

This method has fast calculation speed, but it also has some disadvantages. First, it is prone to halo phenomenon in the strong light and shadow transition area; second, it is not good for brighter images; last, the color retention ability is weak.

Unsuitable for endoscopic surgery

[0009] How to solve the problem that the image is too bright or too dark in the image processing process, and how to ensure the normal color tone are technical problems that need to be solved urgently in this field

Images