Automatic white balance method and device, computer readable storage medium and electronic equipment

Abstract

The invention discloses an automatic white balance method and device, a computer readable storage medium and electronic equipment, relates to the technical field of image processing, and provides a method for more accurately calibrating image color cast. According to the main technical scheme, the method comprises the steps of obtaining an RGB image corresponding to an original image; carrying out white point detection processing on the RGB image to obtain a reference white point contained in the RGB image; a plurality of preset color temperature ellipses are utilized to screen the reference white points to obtain target white points, and the color temperature ellipses are used for representing light source information of scenes under different color temperatures; calculating an image gain corresponding to the original image according to the RGB value of the target white point; and performing automatic white balance processing on the original image according to the image gain to obtain a target image subjected to color cast correction. The method and the device are mainly used for correcting the color cast problem of the image.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular, to an automatic white balance method, apparatus, computer-readable storage medium and electronic device. Background technique [0002] With the advancement of image processing technology, image capturing devices such as cameras and mobile phones are widely used, and people have higher and higher requirements for image quality, and at the same time, the shooting scenes are becoming more and more complex. When shooting with a camera, the color of the image will inevitably be affected by many factors such as the image sensor itself or the external environment, so that the color of the image will be distorted. For example, when the color temperature changes due to these factors, the color of the captured image will also change, resulting in a color cast. [0003] At present, the automatic white balance method is mainly used to suppress the color cast of the imag...

AI Technical Summary

Problems solved by technology

[0004] The grayscale world algorithm is based on certain assumptions. When there are large areas of color blocks and other obvious color casts in the scene, if the assumptions are not true, the adjustment effect of the algorithm will be greatly deviated; the perfect reflection algorithm is based on the fact that there are abnormal Based on the overexposed white point, but when there are pixels with too high brightness (that is, overexposed pixels) in the image, the effect of the perfect reflection algorithm will not be good, because the R of the overexposed pixels , G, and B components are saturated, and when calculating the gains of the three channels, the calculation results are always unique; the color gamut mapping algorithm and the neural network algorithm, these two algorithms are more complicated and difficult to use hardware to implement, especially the neural network algorithm, It requires a large number of high-quality sample training to ensure the accuracy of the algorithm, and the quality and integrity of the samples are difficult to guarantee

[0005] Above, the grayscale world algorithm and the perfect reflection algorithm are limited to hypothetical conditions or constrained scenarios, and the color gamut mapping algorithm and neural network algorithm are limited to high algorithm complexity and difficulty in implementation. It is difficult to accurately calibrate the bias image using these four algorithms still need to find a better automatic white balance method to solve the problem of color cast in the image

Images