Self-adaptive image enhancement method

Abstract

The invention relates to the technical field of image enhancement, in particular to a self-adaptive image enhancement method, which comprises the following steps of S1, converting an original image tobe processed into an HSV color space from RGB, and decomposing the HSV color space into H, S and V components; s2, performing single-scale decomposition on the V component to obtain low-frequency component information and high-frequency component information of the V component of the image; s3, performing enhancement processing on the low-frequency component in the step S2, and then performing adaptive correction; s4, performing fuzzy enhancement on the high-frequency component in the step S2; s5, carrying out wavelet reconstruction on the low-frequency component and the high-frequency component after enhancement processing in the step S3 and the step S4 to obtain an enhanced brightness V component; s6, converting the HSV image back to the RGB color space; and S7, performing color restoration in the RGB space. According to the method, color distortion is avoided, the contrast and detail information of the image are improved, the visual effect of people is better met, and the method has self-adaptability.

Description

technical field [0001] The invention relates to the technical field of image enhancement, in particular to an adaptive image enhancement method. Background technique [0002] Image enhancement technology is a basic and very important technology in the field of image processing, and has been an unavoidable research topic in the field of image processing for a long time. How to properly enhance the image so that its features can be better protected while denoising the image, so as to improve the visual effect of the image and improve the clarity of the image is the problem to be solved in image enhancement. The traditional histogram equalization method is a relatively mature algorithm in the spatial domain, and its implementation is relatively simple. However, because this method will cause excessive image enhancement and cannot maintain the average brightness and entropy of the image, it is rarely used in actual engineering. For this reason, many improved histogram equalizat...

AI Technical Summary

Problems solved by technology

In terms of improving image clarity, there are sparse representation and dictionary learning methods for noise removal, Smart Deblur restoration methods for motion blur removal, dark channel prior theory for haze removal, etc., but these methods have no effect on image edge features and Detailed information can bring blur effect

In terms of image edge feature extraction, there are differential methods such as Roberts, Canny, and Laplacian, but these differential methods will strengthen the influence of noise on the image

There are also a variety of image enhancement algorithms based on Retinex theory for correction of uneven illumination, but most of these algorithms will produce whitening and graying, color distortion and low contrast

The above image enhancement methods have certain limitations due to different application requirements, that is, different image enhancement methods are suitable for images with different characteristics

Images