A system and method to correct white balance

A white balance and correction parameter technology, applied in the field of white balance correction, can solve problems such as image color error, impossibility to achieve, poor correction effect, etc., to achieve good image quality

Inactive Publication Date: 2007-04-25
VIMICRO CORP
View PDF0 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For some specific light sources, the intensity of some colors will be large (such as the R component), and when the G component is small, the correction effect is not good
Moreover, due to the complexity of light sources in natural scenes (may include mixed light sources, new light sources (light sources that have not been trained), light sources that exceed the color temperature range of the training model, etc.) and the complexity of the scene content, it is desirable to pass the above correction method It is impossible to correct the white balance in one step
And, if this one-step correction produces a large error, the color of the entire image after correction will have a large error

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A system and method to correct white balance
  • A system and method to correct white balance
  • A system and method to correct white balance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054]The core idea of ​​the present invention is: identify the mixed light source in the image to be processed or its downsampled image, obtain the correction parameters of the mixed light source according to the information of each single light source in the mixed light source, and correct the image to be processed according to the correction parameters of the mixed light source to obtain first image;

[0055] Acquiring correction parameters of each color component according to information of pixels in the first image or its down-sampled image, and correcting and outputting the first image according to the correction parameters of each color component.

[0056] In the embodiment of the present invention, two-level correction is performed. The first-level correction is to use the method of light source classification and identification to perform preliminary correction on the image, which is equivalent to rough adjustment; the second-level correction is to perform fine adjustm...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a method for correcting white balance and relative system. Wherein, it recognizes target image or downloads the mixed light source of sampled image; based on the information of single light source of mixed light source, it obtains the correct parameter of mixed light source; based on the correct parameter, it corrects the target image to obtain the first image; based on the information of pixels of first image or downloaded sampled image, it obtains the correct parameter of each color component, and based on the correct parameter of each color component, it corrects and outputs the first image. The invention can obtain accurate white balance and the image with high quality.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method and system for correcting white balance. Background technique [0002] At present, in order to correct the white balance of the image, the correction method used is: [0003] Statistically calculate the average values ​​of the RGB components of all pixels in the image, where the average value of the R component is Rmean, the average value of the G component is Gmean, and the average value of the B component is Bmean, and then the correction of the R component is calculated separately The parameter gr_gain and the correction parameter gb_gain of the B component: [0004] gr_gain=Gmean / Rmean [0005] gb_gain=Gmean / Bmean [0006] Then, with the G channel as a reference, the R and B channels are corrected respectively, that is, the RGB component value of each pixel is processed as follows to obtain the corrected RGB component value of the pixel: [0007] R'=R * gr_gain ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): H04N9/73
Inventor 沈操黄英王浩
Owner VIMICRO CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap