Method of using illumination estimation to correct image color

Abstract

The invention discloses a method of using illumination estimation to correct an image color, which belongs to the technical field of computer vision and image processing. The method is quick in speed and good in robustness, and image color correction can be carried out in real time. The color is one of the most basic and the most direct features in vision information, and can be widely applied to application fields such as image retrieval and object recognition. However, the color feature is also a vision feature which is extremely instable, and is likely to be influenced by illumination changes. The image in an unknown illumination condition is corrected to an image under a standard white light, and the process is simply summarized that the illumination color in the case of image imaging is estimated firstly, and the image is mapped to the standard white light by using a Von Kries model. Better image white balance effects can be acquired. The method of the invention has the advantages that the parameters are few; the calculation is simple; the speed is quick; the effects are good; real-time processing can be carried out; and the method is particularly suitable for using a pretreated front end of a built-in camera to carry out color correction on the image.

Description

technical field [0001] The invention relates to a mechanism for correcting image color by estimating the illumination value of an image in an image acquisition system, which belongs to the technical field of computer vision and image processing and a color correction method for color images. The system uses the Gray-Edge frame color constancy algorithm to pass Change the parameter system, estimate the illumination value of the image under standard white light, and then perform color correction on it through the diagonal model. Background technique [0002] At present, most color lighting estimation algorithms assume that the lighting in the scene is uniformly distributed, that is, there is only one lighting in the entire scene. In real life, however, there are often multiple lights in a scene. In indoor scenes, some areas are mainly illuminated by indoor tungsten lights, and some areas are illuminated by both indoor tungsten lights and outdoor lights. In outdoor scenes, sh...

AI Technical Summary

Problems solved by technology

[0021] (1) The supervised color constancy algorithms in the prior art all use the binarized chromaticity histogram of the original image to form the feature vector, and do not make full use of information such as the edge structure of the image

[0022] (2) The training speed of BP neural network is very slow, and it is easy to fall into local optimum; while the selection of kernel function and its parameters based on SVR method is a relatively cumbersome problem, because there are multiple kernel functions! Moreover, there are multiple parameters for each kernel function, so how to choose the optimal kernel function and its corresponding parameter pair can only be done through experience and trial methods, and the implementation cost is relatively high.

Images