Rapid automatic white balance and color correction method based on deep learning

Abstract

The invention provides a rapid automatic white balance and color correction method based on deep learning. In the aspect of speed, awb and color correction can achieve real-time performance on common embedded equipment, and the calculated amount is reduced compared with that of a traditional algorithm; in the aspect of effects, the method solves the problem that a traditional method is inaccurate in white balance estimation of a large-area pure-color picture, the good white balance and color correction effect is achieved in the low-color-temperature and low-illumination environment, the gray scale reduction degree of white balance is 90% or above under the low-color-temperature and low-illumination environment through an imagtest, delta(C) is less than 8% after color correction, delta(E) is less than 15% after color correction, the white balance reduction degree at high color temperature exceeds 95%, and the color saturation is basically greater than 100. The gray scale reduction degree of a traditional white balance algorithm under low color temperature and low illumination can only reach 60%-80%; in the aspect of applicability, the method is suitable for multiple sensors and can be expanded to other task fields.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a fast automatic white balance and color correction method based on deep learning. Background technique [0002] The traditional AWB algorithm includes the following algorithms: [0003] Advanced white balance algorithm, its algorithm flow is: [0004] 1. Take gray card pictures at different color temperatures (D75, D65, D50, CWF, H, A) in the light box, and the gray card is full of the whole live image; [0005] 2. Calibrate the white balance reference point at each color temperature, and then determine the reference white point to draw the reference white area; [0006] 3. Calculate the reference white point of the image to be corrected that currently falls into the reference white area, and calculate the white balance color compensation of the image to be corrected according to the combination of these gray points and weights; [0007] The grayscale wor...

AI Technical Summary

Problems solved by technology

[0028] The main problem of the advanced white balance algorithm is that there is inaccurate detection of the gray area of ​​the white point, and there will be wrong white point detection for the detection of the gray area of ​​the large-area solid color background, which will eventually be corrected into a white balance image with a color cast

[0029] The main problem with the grayscale world method is that if the color of the image is relatively single, then the grayworld assumption is no longer satisfied.

[0030] The main problem of the perfect reflection method is that it is greatly affected by the parameter of the threshold T

[0035] For these neural network tasks, it is difficult to calculate white balance and color correciton parameters in real time and it is not practical for multiple sensors

Images