CN111405260B - Self-adaptive white balance control method and system thereof - Google Patents
Self-adaptive white balance control method and system thereof Download PDFInfo
- Publication number
- CN111405260B CN111405260B CN202010216510.8A CN202010216510A CN111405260B CN 111405260 B CN111405260 B CN 111405260B CN 202010216510 A CN202010216510 A CN 202010216510A CN 111405260 B CN111405260 B CN 111405260B
- Authority
- CN
- China
- Prior art keywords
- light source
- white balance
- image
- value
- source area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
- H04N23/84—Camera processing pipelines; Components thereof for processing colour signals
- H04N23/88—Camera processing pipelines; Components thereof for processing colour signals for colour balance, e.g. white-balance circuits or colour temperature control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
- H04N23/84—Camera processing pipelines; Components thereof for processing colour signals
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Color Television Image Signal Generators (AREA)
- Processing Of Color Television Signals (AREA)
Abstract
The invention relates to the technical field of white balance control, in particular to a self-adaptive white balance control method and a system thereof.
Description
Technical Field
The invention relates to the technical field of white balance control, in particular to a self-adaptive white balance control method and a system thereof.
Background
Image capturing apparatuses using an image sensor, such as digital cameras and digital video cameras, have a white balance control function to adjust the color tone of a captured image, the white balance control being processing of correcting pixel values based on a white balance coefficient so as to capture an image of a white object as white.
Conventional white balance control may be divided into regional white balance control and global white balance control by calculation block.
In the area white balance control, a white area in an image needs to be appointed in shooting, a control circuit informs equipment, the equipment calculates the color channel of the area, and then a white balance coefficient is obtained; such white balance control has an advantage of providing a satisfactory effect, but has a problem that a white region must be set in advance, and flexibility is lacking.
In the global white balance control, a control circuit calculates the coloring channel of the full-frame image by default and then obtains a white balance coefficient; in such white balance control, there are problems that excessive invalid data participate in calculation, the effect is not ideal, and the calculation amount is large; the method needs to be matched with white paper correction, and the effect is ideal.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: an adaptive white balance control method and system for implementing white balance correction are provided.
In order to solve the above technical problems, a first technical solution adopted by the present invention is:
an adaptive white balance control method comprising the steps of:
s1, collecting an effective light source area in the light source area of the image, and extracting effective data of the effective light source area in the light source area of the collected image;
s2, calculating a white balance gain value according to the extracted effective data;
and S3, performing white balance processing on the image according to the calculated white balance gain value.
The second technical scheme adopted by the invention is as follows:
an adaptive white balance control system comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
s1, collecting an effective light source area in the light source area of the image, and extracting effective data of the effective light source area in the light source area of the collected image;
s2, calculating a white balance gain value according to the extracted effective data;
and S3, performing white balance processing on the image according to the calculated white balance gain value.
The invention has the beneficial effects that:
according to the scheme, the effective light source area in the light source area of the image is collected, the effective data of the effective light source area in the light source area of the collected image is extracted, the white balance gain value is calculated according to the extracted effective data, the white balance gain value calculated by the control method of the scheme is high in accuracy, the step that the light source area is preset for regional white balance control can be omitted, user experience is improved, invalid data of global white balance control can be removed, hardware computing power is saved, and the white balance coefficient is extracted more accurately.
Drawings
FIG. 1 is a flow chart of the steps of an adaptive white balance control method according to the present invention;
FIG. 2 is a schematic diagram of an adaptive white balance control system according to the present invention;
FIG. 3 is a captured gray scale image of an adaptive white balance control method according to the present invention;
FIG. 4 is a histogram of a gray scale plot of an adaptive white balance control method according to the present invention;
FIG. 5 is a schematic diagram of an acquired image for an adaptive white balance control method according to the present invention;
FIG. 6 is a schematic diagram of an acquired image for an adaptive white balance control method according to the present invention;
description of reference numerals:
1. a processor; 2. a memory.
Detailed Description
In order to explain technical contents, achieved objects, and effects of the present invention in detail, the following description is made with reference to the accompanying drawings in combination with the embodiments.
Referring to fig. 1, a technical solution provided by the present invention:
an adaptive white balance control method comprising the steps of:
s1, collecting an effective light source area in the light source area of the image, and extracting effective data of the effective light source area in the light source area of the collected image;
s2, calculating a white balance gain value according to the extracted effective data;
and S3, performing white balance processing on the image according to the calculated white balance gain value.
From the above description, the beneficial effects of the present invention are:
according to the scheme, the effective light source area in the light source area of the image is collected, the effective data of the effective light source area in the light source area of the collected image is extracted, the white balance gain value is calculated according to the extracted effective data, the white balance gain value calculated by the control method of the scheme is high in accuracy, the step that the light source area is preset for regional white balance control can be omitted, user experience is improved, invalid data of global white balance control can be removed, hardware computing power is saved, and the white balance coefficient is extracted more accurately.
Further, the method for calculating the white balance gain value comprises the following steps:
s21, calculating a threshold value of an effective light source area of the acquired image according to the light source area of the acquired image to obtain a first light source mask value;
and S22, calculating the red and blue gain values of the color components in the light source area of the image according to the first light source mask value to obtain a white balance gain value.
As can be seen from the above description, the white balance gain value calculated by the above method has higher accuracy, so that the accuracy of the finally extracted white balance coefficient is better.
Further, the following steps are included between step S21 and step S22:
and calculating to obtain a second light source mask value according to the first light source mask value.
As can be seen from the above description, more accurate light source mask values can be obtained through the above steps, and the accuracy of the white balance gain values that can be obtained is higher, so that the accuracy of the finally extracted white balance coefficients is better.
Further, the method for acquiring the effective light source area in the light source area of the image is as follows:
and carrying out foreground separation on the acquired image to obtain an effective light source area.
Referring to fig. 2, another technical solution provided by the present invention:
an adaptive white balance control system comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
s1, collecting an effective light source area in the light source area of the image, and extracting effective data of the effective light source area in the light source area of the collected image;
s2, calculating a white balance gain value according to the extracted effective data;
and S3, performing white balance processing on the image according to the calculated white balance gain value.
From the above description, the beneficial effects of the present invention are:
according to the scheme, the effective light source area in the light source area of the image is collected, the effective data of the effective light source area in the light source area of the collected image is extracted, the white balance gain value is calculated according to the extracted effective data, the white balance gain value calculated by the control method of the scheme is high in accuracy, the step that the light source area is preset for regional white balance control can be omitted, user experience is improved, invalid data of global white balance control can be removed, hardware computing power is saved, and the white balance coefficient is extracted more accurately.
Further, the processor, when executing the computer program, further implements the following steps:
s21, calculating a threshold value of an effective light source area of the acquired image according to the light source area of the acquired image to obtain a first light source mask value;
and S22, calculating the red and blue gain values of the color components in the light source area of the image according to the first light source mask value to obtain a white balance gain value.
As can be seen from the above description, the white balance gain value calculated by the above method has higher accuracy, so that the accuracy of the finally extracted white balance coefficient is better.
Further, the processor, when executing the computer program, further implements the following steps:
and calculating to obtain a second light source mask value according to the first light source mask value.
As can be seen from the above description, more accurate light source mask values can be obtained through the above steps, and the accuracy of the white balance gain values that can be obtained is higher, so that the accuracy of the finally extracted white balance coefficients is better.
Further, the processor, when executing the computer program, further implements the following steps:
and carrying out foreground separation on the acquired image to obtain an effective light source area.
Referring to fig. 1, a first embodiment of the present invention is:
an adaptive white balance control method comprising the steps of:
s1, collecting an effective light source area in the light source area of the image, and extracting effective data of the effective light source area in the light source area of the collected image; the method for acquiring the effective light source area in the light source area of the image comprises the following steps: and carrying out foreground separation on the acquired image to obtain an effective light source area.
The image is generated by the induction of the camera photoreceptor to light radiation, the light source uniformly radiates photons outwards, when the image passes through an observation object, the observation object absorbs, reflects and refracts the light radiation, so that the uniform light radiation is non-uniform, therefore, the image can be divided into an observation area and a non-observation area, namely the image is divided into a foreground and a background (light source), if the non-uniform area can be removed, namely the foreground is stripped, and the remaining background is a light source area (uniform radiation area) required by people;
the image in the step can use an image sensor to obtain original image data Raw; effective data of an effective light source area in a light source area of an acquired image is extracted through an algorithm built in an industrial camera, a modeling image is a foreground plus a background, a light source mask is obtained by segmenting the background in front of the image through edge extraction, and then the effective data are further accurately obtained by using a morphological algorithm for the mask.
S2, calculating a white balance gain value according to the extracted effective data;
the method for calculating the white balance gain value comprises the following steps:
s21, calculating a threshold value of an effective light source area of the acquired image according to the light source area of the acquired image to obtain a first light source mask value; the specific implementation manner of step S21 is: performing histogram statistics on the image, traversing the histogram by using a least square method to find a value with the maximum front background variance as a threshold value T, and traversing a pixel P to obtain a first light source mask value I1;
the specific operation steps are as follows:
probability distribution function pi＝ni/N，niThe gray scale is the number of i, N is the total number, and the histogram data is imported to obtain the distribution condition, and the obtained formula is as follows:
probability of foreground
Background probability
Foreground gray scale
Background gray scale
Whole image gray scale
Step 3, calculating variance:
after T is obtained, judging the light source area occupation ratio, if the light source area occupation ratio is larger than the range [ T +1, 255], if the light source area occupation ratio is smaller than the range [0, T ], executing the step 1 again, and circularly confirming the light source area occupation ratio;
corroding the light source area after the proportion is reasonable;
the gray map is binarized according to a threshold value (i.e., T) of edge detection; the binary gray map is an image operation, and the obtained T can be used as a threshold value to process the gray map according to a formula P (i, j), wherein the value is less than T and is set to be 0, and the value is more than or equal to T and is set to be 255, so that the gray map is converted into a binary image with only two values, which is the basis for judging valid data later.
The formula:
this allows a mask of valid data to be obtained.
In order to reduce the light source area, remove the buffer area of the previous north view and more accurately find the expansion foreground of the light source area, and the binary image has many details such as boundaries or noise, the boundaries are eliminated by adopting expansion, so that the background range is reduced, and the effectiveness of the light source area is ensured as much as possible; the expansion is to merge all background points in contact with the object into the object, and slide the pixel function by an expansion factor; a process of expanding the boundary to the outside.
The determination of foreground and background is determined by convolution of the expansion factor with the pixel function.
The expansion factor coefficient is determined by searching the maximum white area scale in the horizontal and vertical directions of the binary image and taking the white area scale as an expansion factor, so that the white area can be reserved on the premise of reducing the white area.
And S22, calculating the red and blue gain values of the color components in the light source area of the image according to the first light source mask value to obtain a white balance gain value. The specific implementation manner of step S22 is: according to a light source mask matrix I, dot-multiplying original image data, counting a red-blue channel and Sum _ C of light source effective data, I · Raw, and then dividing by a mask effective pixel number I _ pixels to obtain an effective data average value Avg ═ Sum _ C/I _ pixels, thereby calculating to obtain a white balance gain matrix M ═ AvgG/Avg ═ 1, AvgG/avgb, where AvgG/avgr represents a gain value of the red channel, 1 represents a gain value of the green channel, and AvgG/avgb represents a gain value of the blue channel, and the specific calculation process is as follows:
calculating a gain value of a red channel by taking the green channel as a reference, wherein the gain value of the red channel is an average value of effective data of the green channel divided by an average value of effective data of the red channel, namely avgg/avgr; similarly, the gain value of the green channel is AvgG/AvgG ═ 1, and the gain value of the blue channel is AvgG/avgb, which is expressed in a matrix form of 1x3, that is, M ═ AvgG/Avg ═ (AvgG/avgr, 1, AvgG/avgb).
Between step S21 and step S22, the following steps are further included:
and calculating to obtain a second light source mask value according to the first light source mask value. The method specifically comprises the following steps: the first light source mask value I1 is etched using morphology to further refine the first light source mask value I1 to obtain a second light source mask value I2.
And S3, performing white balance processing on the image according to the calculated white balance gain value. The specific implementation manner of step S3 is: in the embodiment of step S22, a white balance gain matrix M is obtained, and this module applies white balance gain to the whole original image data Raw to restore the image color, i.e. matrix operation.
The foregoing adaptive white balance control method is implemented as follows:
and step S1, obtaining image data RAW through the image sensor, decoding to obtain a source color image and converting the source color image into a gray scale image.
Step S2, calculating a white balance gain value according to the extracted effective data;
including step S21 and step S22, as follows:
the specific implementation manner of step S21 is: histogram statistics (histogram as in fig. 4) were performed on the gray scale map (fig. 3), and the data obtained are shown in table 1:
table 1:
the variance of the foreground and background is found by traversing the histogram using the least squares method when the threshold T is 96
Equal to 5265689904473.8643 is maximum.
Binarizing the gray map according to the threshold value of edge detection (i.e., T-96), and traversing the pixel P to obtain a first light source mask value I1 (i.e., fig. 5);
the first light source mask value I1 is etched using morphology to further refine the first light source mask value I1 to obtain a second light source mask value I2 (i.e., fig. 6).
Step S22, according to the light source mask value, calculating the red and blue gain value of the color component in the light source area of the image to obtain a white balance gain value; the method specifically comprises the following steps: according to the light source mask matrix I, dot-multiplying the original image data, counting the red-blue channel and Sum _ C ═ I · Raw of the light source valid data (where I and Raw are converted into wide-by-high (mxn) dimensional vector dot-multiplication, which results in a constant, and because Raw is a common formula containing three channels, red, green and blue, which results in a 1x3 matrix Sum _ C of the Sum of red, green and blue valid pixels, then the valid pixel Sum of the red channel is 116433161.28, the valid pixel Sum of the green channel is 118094642.64, the valid pixel Sum of the blue channel is 98883314.88, and then dividing by the mask valid pixel number I _ pixels 719256, which results in the valid data average Avg ═ Sum _ C/I _ pixels ═ 161.88, 164.19, 137.48), and the white balance gain matrix M ═ Avg/Avg ═ 161.88, 25/637, I _ pixels ═ 137.48, 6851.0141, 6851.194).
Step S3, according to the calculated white balance gain value, white balance processing is carried out on the image; the specific implementation manner of step S3 is: in the specific implementation of step S22, a white balance gain matrix M is obtained, and this module applies a white balance gain to the whole original image data Raw, restores the image color, that is, performs matrix operation, and finally realizes a white balance function;
the following data obtained from the area white balance method, the global white balance method and the adaptive white balance method of the plant cell image and the skeletal muscle slice image are shown in table 2 below:
table 2:
from the data in the above table, it can be known that the value of the deviation of the image after the adaptive white balance processing is better than that after the global white balance processing, and is slightly smaller than or equal to that after the regional white balance processing.
The importance of the YCrCb color space is that its luminance signal Y and chrominance signals Cr, Cb are separated.
YCrCb and RGB interconversion formula is as follows
The color difference can be calculated by RGB, and the formula is as follows:
in the same way
Referring to fig. 2, the second embodiment of the present invention is:
an adaptive white balance control system comprising a memory 2, a processor 1 and a computer program stored on the memory 2 and executable on the processor 1, the processor 1 implementing the following steps when executing the computer program:
s1, collecting an effective light source area in the light source area of the image, and extracting effective data of the effective light source area in the light source area of the collected image;
s2, calculating a white balance gain value according to the extracted effective data;
and S3, performing white balance processing on the image according to the calculated white balance gain value.
The processor 1 further realizes the following steps when executing the computer program:
s21, calculating a threshold value of an effective light source area of the acquired image according to the light source area of the acquired image to obtain a first light source mask value;
and S22, calculating the red and blue gain values of the color components in the light source area of the image according to the first light source mask value to obtain a white balance gain value.
The processor 1, when executing the computer program, further implements the steps of:
and calculating to obtain a second light source mask value according to the first light source mask value.
The processor 1 further realizes the following steps when executing the computer program:
and carrying out foreground separation on the acquired image to obtain an effective light source area.
In summary, according to the adaptive white balance control method and system provided by the invention, the effective light source area in the light source area of the image is acquired, the effective data of the effective light source area in the light source area of the acquired image is extracted, the white balance gain value is calculated according to the extracted effective data, the white balance gain value calculated by the control method of the scheme has high accuracy, the step of presetting the light source area for area white balance control can be omitted, the user experience is improved, the invalid data of global white balance control can be removed, the hardware calculation power is saved, and the white balance coefficient is extracted more accurately.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all equivalent changes made by using the contents of the present specification and the drawings, or applied directly or indirectly to the related technical fields, are included in the scope of the present invention.
Claims (6)
1. An adaptive white balance control method, comprising the steps of:
s1, collecting an effective light source area in the light source area of the image, and extracting effective data of the effective light source area in the light source area of the collected image;
s2, calculating a white balance gain value according to the extracted effective data;
s3, performing white balance processing on the image according to the calculated white balance gain value;
the method for calculating the white balance gain value comprises the following steps:
s21, calculating a threshold value of an effective light source area of the acquired image according to the light source area of the acquired image to obtain a first light source mask value;
s22, calculating the red and blue gain values of the color components in the light source area of the image according to the first light source mask value to obtain a white balance gain value;
step S21 specifically includes: performing histogram statistics on the image, traversing the histogram by using a least square method to find a value with the maximum front background variance as a threshold value T, and traversing a pixel P to obtain a first light source mask value I1;
step 1, setting a threshold value T to be 1;
step 2, a foreground interval [0, T ] and a background interval [ T +1, 255 ];
the probability distribution function pi is ni/N, ni is the number of gray scales i, N is the total number, and the histogram data is imported to obtain the distribution, and the obtained formula is as follows:
probability of foreground
Background probability
Foreground gray scale
Background gray scale
Whole image gray scale
Step 3, calculating variance:
step 4, circulating T from 0 to 255: circulating the steps 1-3, and searching T when the variance is maximum as a threshold value;
step S22 specifically includes:
according to the light source mask matrix I, dot multiplication is carried out on original image data, a red-blue channel and Sum _ C of effective light source data are counted, and then the obtained result is divided by the number of effective mask pixels I _ pixels to obtain an effective data mean value Avg Sum _ C/I _ pixels, so that a white balance gain matrix M is calculated to obtain an AvgG/Avg ═ 1, AvgG/avgb, wherein the AvgG/avgr represents a gain value of the red channel, the 1 represents a gain value of the green channel, and the AvgG/avgb represents a gain value of the blue channel.
2. The adaptive white balance control method according to claim 1, further comprising, between step S21 and step S22, the steps of:
and calculating to obtain a second light source mask value according to the first light source mask value.
3. The adaptive white balance control method according to claim 1, wherein the method of acquiring an effective light source region in the light source region of the image is:
and carrying out foreground separation on the acquired image to obtain an effective light source area.
4. An adaptive white balance control system comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor when executing the computer program implementing the steps of:
s1, collecting an effective light source area in the light source area of the image, and extracting effective data of the effective light source area in the light source area of the collected image;
s2, calculating a white balance gain value according to the extracted effective data;
s3, performing white balance processing on the image according to the calculated white balance gain value;
the processor, when executing the computer program, further implements the steps of:
s21, calculating a threshold value of an effective light source area of the acquired image according to the light source area of the acquired image to obtain a first light source mask value;
s22, calculating the red and blue gain values of the color components in the light source area of the image according to the first light source mask value to obtain a white balance gain value;
step S21 specifically includes: performing histogram statistics on the image, traversing the histogram by using a least square method to find a value with the maximum front background variance as a threshold value T, and traversing a pixel P to obtain a first light source mask value I1;
step 1, setting a threshold value T to be 1;
step 2, a foreground interval [0, T ] and a background interval [ T +1, 255 ];
the probability distribution function pi is ni/N, ni is the number of gray scales i, N is the total number, and the histogram data is imported to obtain the distribution, and the obtained formula is as follows:
probability of foreground
Background probability
Foreground gray scale
Background gray scale
Whole image gray scale
Step 3, calculating variance:
step 4, circulating T from 0 to 255: circulating the steps 1-3, and searching T when the variance is maximum as a threshold value;
step S22 specifically includes:
according to the light source mask matrix I, dot multiplication is carried out on original image data, a red-blue channel and Sum _ C of effective light source data are counted, and then the obtained result is divided by the number of effective mask pixels I _ pixels to obtain an effective data mean value Avg Sum _ C/I _ pixels, so that a white balance gain matrix M is calculated to obtain an AvgG/Avg ═ 1, AvgG/avgb, wherein the AvgG/avgr represents a gain value of the red channel, the 1 represents a gain value of the green channel, and the AvgG/avgb represents a gain value of the blue channel.
5. The adaptive white balance control system according to claim 4, wherein the processor when executing the computer program further performs the steps of:
and calculating to obtain a second light source mask value according to the first light source mask value.
6. The adaptive white balance control system according to claim 4, wherein the processor when executing the computer program further performs the steps of:
and carrying out foreground separation on the acquired image to obtain an effective light source area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010216510.8A CN111405260B (en) | 2020-03-25 | 2020-03-25 | Self-adaptive white balance control method and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010216510.8A CN111405260B (en) | 2020-03-25 | 2020-03-25 | Self-adaptive white balance control method and system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111405260A CN111405260A (en) | 2020-07-10 |
| CN111405260B true CN111405260B (en) | 2022-01-18 |
Family
ID=71431191
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010216510.8A Active CN111405260B (en) | 2020-03-25 | 2020-03-25 | Self-adaptive white balance control method and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111405260B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112995632B (en) * | 2021-04-21 | 2021-08-31 | 贝壳找房(北京)科技有限公司 | Image white balance processing method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008219838A (en) * | 2007-03-08 | 2008-09-18 | Matsushita Electric Ind Co Ltd | Imaging apparatus, white balance control device and white balance control method |
| CN101610420A (en) * | 2008-06-20 | 2009-12-23 | 睿致科技股份有限公司 | The method of Automatic white balance |
| CN105282530A (en) * | 2014-05-28 | 2016-01-27 | 深圳中兴力维技术有限公司 | Method and device for implementing automatic white balance based on background modeling |
| CN108881875A (en) * | 2018-08-16 | 2018-11-23 | Oppo广东移动通信有限公司 | Image white balancing treatment method, device, storage medium and terminal |
-
2020
- 2020-03-25 CN CN202010216510.8A patent/CN111405260B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008219838A (en) * | 2007-03-08 | 2008-09-18 | Matsushita Electric Ind Co Ltd | Imaging apparatus, white balance control device and white balance control method |
| CN101610420A (en) * | 2008-06-20 | 2009-12-23 | 睿致科技股份有限公司 | The method of Automatic white balance |
| CN105282530A (en) * | 2014-05-28 | 2016-01-27 | 深圳中兴力维技术有限公司 | Method and device for implementing automatic white balance based on background modeling |
| CN108881875A (en) * | 2018-08-16 | 2018-11-23 | Oppo广东移动通信有限公司 | Image white balancing treatment method, device, storage medium and terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111405260A (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106920221B (en) | Take into account the exposure fusion method that Luminance Distribution and details are presented | |
| US11538175B2 (en) | Method and apparatus for detecting subject, electronic device, and computer readable storage medium | |
| CN110796041B (en) | Principal identification method and apparatus, electronic device, and computer-readable storage medium | |
| CN110428389B (en) | Low-light-level image enhancement method based on MSR theory and exposure fusion | |
| CN108154492B (en) | A kind of image based on non-local mean filtering goes haze method | |
| CN112529854B (en) | Noise estimation method, device, storage medium and equipment | |
| CN103065334A (en) | Color cast detection and correction method and device based on HSV (Hue, Saturation, Value) color space | |
| CN110298796B (en) | Low-illumination image enhancement method based on improved Retinex and logarithmic image processing | |
| CN109285183B (en) | Multimode video image registration method based on motion region image definition | |
| CN111210393A (en) | Color image enhancement method and system based on edge extraction and storage medium | |
| CN106355560A (en) | Method and system for extracting atmospheric light value in haze image | |
| CN111405260B (en) | Self-adaptive white balance control method and system thereof | |
| CN114998122A (en) | Low-illumination image enhancement method | |
| CN111539975B (en) | Method, device, equipment and storage medium for detecting moving object | |
| CN110334606B (en) | Picture-in-picture positioning method and device | |
| CN110136085B (en) | Image noise reduction method and device | |
| Park et al. | Image enhancement for extremely low light conditions | |
| CN113411555B (en) | White balance processing method and device, storage medium and image capturing equipment | |
| CN111028309B (en) | Insect density map construction method and device based on LoRa node | |
| JP2018160024A (en) | Image processing device, image processing method and program | |
| CN113850814A (en) | CNN model-based litchi leaf pest and disease identification method | |
| CN113824894A (en) | Exposure control method, device, equipment and storage medium | |
| CN111932470A (en) | Image restoration method, device, equipment and medium based on visual selection fusion | |
| CN113888657B (en) | Screen color acquisition method and device, camera equipment and storage medium | |
| CN113221909B (en) | Image processing method, image processing apparatus, and computer-readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |