Unlock instant, AI-driven research and patent intelligence for your innovation.

Image white balance processing method, device and camera

A white balance and image technology, applied in the field of image processing, can solve the problems of poor effect and low user experience, and achieve the effect of small calculation amount and accurate channel gain.

Active Publication Date: 2017-06-23
ZHEJIANG DAHUA TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention provides an image white balance processing method, device and camera, which are used to solve the problem that the image white balance method in the prior art has poor effect after white balance processing on the image, and the user experience is not high

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
  • Image white balance processing method, device and camera
  • Image white balance processing method, device and camera
  • Image white balance processing method, device and camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0147] Assume that the number of initial particles corresponding to each frame image is two, such as Image 6 As shown, for the first frame image captured by the camera, perform the following steps:

[0148] Step 601, calculate g / r and g / b corresponding to each pixel in the first frame image.

[0149] Step 602, respectively calculate the average value d1 of g / r and the average value d2 of g / b in the first frame image.

[0150] In step 603, the vector composed of d1 and d2 is used as the first frame image corresponding to the first initial particle.

[0151] Step 604, use the vector composed of d1-l and d2 as the first frame image corresponding to the second initial particle.

[0152] Step 605, using the first initial mass point and the second initial mass point corresponding to the first frame image as the initial mass point of the K-means clustering algorithm, and after executing the K-means algorithm, two actual mass points corresponding to the first frame image are obtain...

Embodiment 2

[0161] On the basis of Example 1, as Figure 7 As shown, for the first frame image captured by the camera, perform the following steps:

[0162] Step 701, use the two actual particles corresponding to the first frame image as the two initial particles corresponding to the second frame image, and according to the two initial particles corresponding to the second frame image and the K-means clustering algorithm, get The two actual particles corresponding to the second frame image.

[0163] Step 702, for each actual mass point, calculate the actual mass point in log 2 (g / r) is the abscissa, in log 2 (g / b) is a corresponding coordinate point in the coordinate system of the ordinate, and the color temperature zone to which the coordinate point belongs is determined.

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 present invention provides a white balance processing method, device and camera. This method includes: according to the preset cluster algorithm, the pixels in the frame image are carried out to obtain the number of settings corresponding to the current frame image.The massive point, the actual texture point is the actual cluster center after the clustering of the preset clustering algorithm; according to the corresponding relationship between the color temperature interval of each actual texture point and the preset color temperature interval and the right value, determine each actual texture pointCorresponding rights value; calculate the R, G, and B channel gains of the current frame image according to the right value corresponding to each actual mass point; based on the current frame image of the R, G and B channel gains, the current frame image is adjusted white balance.The present invention can improve the accuracy and effect of white balance on the image, and the user experience is relatively improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image white balance processing method, device and camera. Background technique [0002] When we look at objects with the naked eye under different light conditions, we have basically the same perception of different colors. For example, when the sun rises in the morning, the object seen by the naked eye is white; Seeing the object, it still feels white. This is because during the growth of human beings, the brain has adapted to the color reproduction of objects under different light conditions. However, camera equipment (such as a video camera) does not have the adaptability of the human eye. Due to the unbalanced output of the CCD (Charge-coupled Device, charge-coupled device), the camera equipment will produce color casts for the same color under different light, resulting in The color reproduction of the camera equipment is distorted, namely: the higher the color...

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 Patents(China)
IPC IPC(8): H04N9/73G06K9/62
CPCH04N9/73H04N23/88G06F18/23213
Inventor 王廷鸟
Owner ZHEJIANG DAHUA TECH CO LTD