Color cast detection method of video image based on lab chromaticity space

Abstract

The invention relates to a method for detecting the color cast of a video image based on Lab chrominance space. The method comprises the following steps: a) converting RGB (Red Green Blue) color space into the Lab chrominance space; b) calculating color cast factors. The invention provides a new color cast detecting factor, which is successively used for detecting the color cast of the image. First, the image is converted from the original RGB color space into the Lab chrominance space; then according to the distinction of the spatial gray level histogram distribution of a chrominance and b chrominance between a normal image without color cast and an abnormal image with color cast, the mean value of the spatial gray level histogram distribution of the a chrominance and the b chrominance are respectively calculated; then according to the statistical distribution between the mean value and the mid value of histograms, the color factors are calculated. A lot of experiments of real street view image databases prove that the new color cast detecting factor disclosed by the invention can really reflect the degree of color cast of images so as to complete color cast detection. The method has the advantages of high detection speed and accurate precision.

Description

technical field [0001] The invention relates to a video image color cast detection method, in particular to a video image color cast detection method based on Lab chromaticity space. Background technique [0002] Color is a very important information of a video image, because the color change of the image is often more irritating to the human eye than the brightness and other characteristic changes of the image. Therefore, the color information of video images is often an important basis for video analysis, and it is of great significance to the research in the fields of image segmentation, object detection and recognition, video retrieval, and video object tracking. [0003] In the real world, the human visual system has color constancy, that is, the human eye has a visual adaptation phenomenon to changes in the brightness and color of the lighting environment. As lighting conditions change, the visual system tries to minimize areas of difference in perceived color appeara...

AI Technical Summary

Problems solved by technology

Histogram statistics can give the overall color performance of the image, but in different applications of video images, the reasons for color cast are complicated, and it is difficult to obtain a comprehensive and accurate judgment based on the method of histogram statistics; It is assumed that the mean values ​​of R, G, and B of the image are equal, which is reflected as a neutral "gray". As a result, the gray balance method is almost completely ineffective; for images with specular reflection, the white balance master believes that the specular reflection or the highlight part reflected in the white area can reflect the chromaticity of the light source, so as to judge the color cast phenomenon, but when the object being photographed has no white or When the highlight part exists, the color cast detection result is distorted; the equivalent circle method uses the ratio of the average chromaticity of the image to the center distance of the chromaticity to measure the degree of color cast of the image according to the average chromaticity distribution of the image in the Lab space. color factor, but for the problem of color cast detection without reference, the correct choice of chromaticity center is random and difficult to determine

Images