CN103065334A - Color cast detection and correction method and device based on HSV (Hue, Saturation, Value) color space - Google Patents

Color cast detection and correction method and device based on HSV (Hue, Saturation, Value) color space Download PDF

Info

Publication number
CN103065334A
CN103065334A CN2013100382779A CN201310038277A CN103065334A CN 103065334 A CN103065334 A CN 103065334A CN 2013100382779 A CN2013100382779 A CN 2013100382779A CN 201310038277 A CN201310038277 A CN 201310038277A CN 103065334 A CN103065334 A CN 103065334A
Authority
CN
China
Prior art keywords
channel
value
color
color cast
cast
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.)
Granted
Application number
CN2013100382779A
Other languages
Chinese (zh)
Other versions
CN103065334B (en
Inventor
胡勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jinling Institute of Technology
Original Assignee
Jinling Institute of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jinling Institute of Technology filed Critical Jinling Institute of Technology
Priority to CN201310038277.9A priority Critical patent/CN103065334B/en
Publication of CN103065334A publication Critical patent/CN103065334A/en
Application granted granted Critical
Publication of CN103065334B publication Critical patent/CN103065334B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Facsimile Image Signal Circuits (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides a color cast detection and correction method and device, relating to the technical field of digital image processing. The method comprises the following steps of: inputting an image to be detected of an RGB (Red, Green, Blue) color space; calculating an S channel in the HSV (Hue, Saturation, Value) color space; counting the histogram vector h of the S channel; quantizing and filtering the histogram vector h; judging whether color cast exists in the image according to a histogram vector h' obtained after the quantizing and the filtering; if the image is judged to has color cast, respectively counting the contribution rates of an RGB channel to the maximum matrix and the minimum matrix, and judging a color cast channel according to the contribution rates; adjusting the value of the color cast channel in the RGB color space, recalculating the value of the S channel and judging whether color cast exists in the S channel, and repeating to execute until no color cast exists; and if the image is judged to have no color cast, ending the program. By using the color cast detection and correction method and device, various types of color cast images can be effectively detected and corrected, and the defects in the traditional method are overcome; and the color cast detection and correction method and device are favorable in adaptability to different scenes and high in algorithm efficiency.

Description

Color cast detection and correction method and device based on HSV color space
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to application of algorithms such as color space conversion, histogram statistics and median filtering in color cast detection and correction.
Background
Color is one of the important features of an image and is also an important basis for image processing and analysis. In a physical sense, the color of an object as viewed by the human eye is not only determined by its reflective properties, but also by the color of the light directed at the object. The human visual system has color constancy, can eliminate the influence of factors such as illumination conditions on the color to a certain extent, and accurately sense the color of an object. However, the imaging device does not have such a "adjustment" function, and the acquired image often has a certain degree of error, i.e. color cast, with the true color of the surface of the object. The color cast phenomenon is determined by different color temperatures of the external light source, and the degree of color cast is directly related to the change of the color temperature of the external light source.
The automatic white balance algorithm is an algorithm for detecting and correcting color cast of an image, and aims to reduce color difference caused by an external light source as much as possible, compensate color cast phenomenon caused by non-ideal characteristics of an external device, restore the original color of a photographed target under different color temperature conditions, keep color constancy of different equipment and different observation environments and enable a processed image to conform to the habit of human vision as much as possible.
With the increasing popularization of technologies such as internet, multimedia and the like, the application range of color images is continuously expanded, the detection and correction of color cast are more and more important, and accurate and effective color cast detection and correction can provide effective references for subsequent digital image processing, mode recognition, image retrieval and the like.
In the current color cast detection and correction technology, the classical algorithm mainly comprises: gray World algorithm (Gray World), Perfect reflection algorithm (Perfect Reflector), Fuzzy Neural Network algorithm (Fuzzy Neural Network), white balance algorithm based on edge detection, and improved algorithm based on the above algorithms. The grey world algorithm is based on the grey world assumption of Von-Kries coefficient theory, which assumes: for an image with sufficient color variation, the statistical average of the R, G, B three color components should tend to be the same gray value. The perfect reflection method has the advantages of simple calculation and good restoration effect when high-brightness areas exist in the image. However, the detection of white spots often lacks versatility, and does not work well when no mirror surface is present in the image or the image brightness is low. However, the current classical algorithms all have certain disadvantages, such as: for images with monotonous colors or images containing large-area color blocks, the gray world algorithm often has the problem of correction failure and sometimes generates over correction; when no mirror surface exists in the image or the image brightness is low, the perfect reflection algorithm is not good; edge-based white balance algorithms often fail when large-scale colored textures appear in the image; for the fuzzy neural network algorithm, a large amount of prior knowledge needs to be learned, and the problems of high logic unit consumption, high power consumption and the like exist. The algorithm provided by the invention can effectively detect different types of color cast images, has low algorithm complexity, can effectively overcome the problem of correction failure of the classical algorithm, and is suitable for various different scenes.
Disclosure of Invention
The embodiment of the invention provides a color cast detection and correction method based on an HSV color space, and the algorithm can effectively detect and correct different types of color cast images, is low in complexity and is suitable for various different scenes.
The invention adopts the following technical scheme:
1. inputting an image to be detected (generally, an RGB color space);
2. calculating an S channel in the HSV color space;
3. counting a histogram vector h of the S channel;
4. quantizing and filtering the histogram vector h;
5. judging whether the image is color cast according to the quantized and filtered histogram vector h';
6. if the image color cast is judged, respectively counting the contribution rates of the RGB channels to the maximum matrix and the minimum matrix, and judging the color cast channel according to the contribution rates;
7. in the RGB color space, adjusting the value of the color cast channel, and returning to the step 2;
8. if the image is determined not to be color-cast, the process ends.
An image color cast detection and correction apparatus comprising:
the calculation unit is used for calculating the value of an S channel in the HSV color space and counting a histogram vector h of the S channel;
a preprocessing unit for quantizing and filtering the histogram vectors;
the judging unit judges whether the image has color cast or not, and the program is ended;
the determining unit is used for judging a color cast channel;
and the correcting unit is used for correcting the color cast image and returning to the statistical unit.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings described below are only part of the drawings of some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a color cast detection and correction method provided in embodiment 1 of the present invention.
FIG. 2 is a graph comparing the effects of the present invention and the conventional method; FIG. 2(a) a patch test pattern lacking highlight regions; FIG. 2(b) is a graph of the algorithm results of the present invention; FIG. 2(c) a graph of the gray world algorithm results; FIG. 2(d) is a graph of the results of the perfect reflection algorithm.
[ Special description ] of: since fig. 2, which was submitted as a black and white picture, does not show the better contrast effect of the present invention, a color picture 2 was submitted in other documentations.
Fig. 3 is a structural diagram of a color cast detection and correction device provided in embodiment 2 of the present invention.
Fig. 4 is a structural diagram of the calculation unit 11 provided in embodiment 2 of the present invention.
Fig. 5 is a structural diagram of the preprocessing unit 12 provided in embodiment 2 of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1:
an embodiment 1 of the present invention provides a color cast detection and correction method based on an HSV color space, as shown in fig. 1, the method includes:
101. inputting to-be-detected image of RGB color space
Color Space (Color Space), also known as a Color coordinate system, is a method of abstracting and describing colors. The RGB color space is one of the most common color models, and images output by digital imaging devices are often in RGB format.
102. Computing S-channels in HSV color space
The existing color cast detection algorithm usually converts the RGB color space into the HSV color space, and then extracts the S channel for color cast detection, while the H channel and the V channel do not participate in the subsequent processing process. The invention adopts a method of directly calculating the S channel, thereby greatly reducing the calculation amount and reducing the time and space overhead of the algorithm. The formula for calculating the S channel in HSV color space from RGB color space is as follows:
1) statistical maximum and minimum value matrix
Figure 532258DEST_PATH_IMAGE001
Formula 1;
2) calculating the value of S channel
Figure 910150DEST_PATH_IMAGE002
Equation 2.
103. Histogram vector h of statistical S channel
Obtaining a histogram of an image is well known to those skilled in the art and will not be described in detail herein.
104. Quantizing and filtering the histogram vector h
The quantization and filtering of the histogram vectors can be seen as a pre-processing step of the data.
1) And (3) quantification: quantizing the histogram vector, and reserving 4 bits after the decimal point, wherein the 5 th bit is cut into 5 according to 4;
2) improved one-dimensional median filtering is adopted:
Figure 448578DEST_PATH_IMAGE003
equation 3
Wherein,
Figure 911921DEST_PATH_IMAGE004
the median filter function is represented.
105. Judging whether the image has color cast according to the histogram vector h' after quantization and filtering
If the first N elements in the histogram vector satisfy one of the following conditions, the image is determined to be color-biased, otherwise, the image is determined not to be color-biased (according to statistics of various types of images, N is preferably 15-25):
1) the values of the first N elements are all zero or very close to zero;
setting a threshold TVTo quantify the degree of approach to zero. If the average of the first N elements is less than the threshold, the values of the first N elements are considered to be very close to zero.
2) The values of the first N elements show a phenomenon of oscillation, namely: multiple occurrences of a local maximum and minimum;
setting a threshold TN(3-5) for quantifying the number of occurrences of the local maximum and minimum. If the calculated number of times is greater than the threshold, the first N elements are considered to exhibit an oscillation phenomenon.
Is provided with
Figure 443265DEST_PATH_IMAGE005
To representThe first N elements in the histogram vector, let:
equation 4
Using function statisticsIs obtained by sign change inThe number of times a local maximum minimum occurs in the sequence.
Figure 172132DEST_PATH_IMAGE009
Equation 5.
106. If the image color cast is judged, the contribution rates of the RGB channels to the maximum matrix and the minimum matrix are respectively counted, and the color cast channel is judged according to the contribution rates
Here, the contribution rate of the RGB channel to the maximum and minimum value matrices refers to a ratio of the number of pixels of a channel providing the maximum value or the minimum value divided by the number of all pixels of the channel when counting the maximum and minimum value matrices. Taking the R channel as an example, the contribution ratio to the maximum and minimum value matrices is calculated by the following formula:
Figure 462299DEST_PATH_IMAGE010
equation 6
Wherein,
Figure 326219DEST_PATH_IMAGE011
the counting function is used for counting the number of pixel points meeting the conditions in the matrix.
Maximum contribution rate of RGB channel
Figure 764153DEST_PATH_IMAGE012
Respectively subtracting the corresponding minimum contribution rates
Figure 388033DEST_PATH_IMAGE013
And obtaining three difference values, wherein the channel corresponding to the minimum value is the color cast channel.
107. And in the RGB color space, adjusting the value of the color cast channel and returning to the step 2.
And (3) multiplying the numerical value of the color cast channel by a correction coefficient k (the value of k is 1.02-1.05) to obtain a new image, and repeating the step 2.
108. If the image is determined not to be color-cast, the process ends.
Fig. 2 is a graph comparing the effect of the present invention with the conventional method (gray world algorithm and perfect reflection algorithm). FIG. 2(a) is a color block test image without highlight, which shows a yellowish color; FIG. 2(b) is the correction result by the algorithm, and it can be seen from the figure that the adjusted color block is pure and accords with the visual effect of human eyes; fig. 2(c) is a correction result using the gray world algorithm, the image is somewhat bluish, showing that the white balance correction of the algorithm is insufficient due to: the test image contains large-area color blocks, and the average value of the RGB three channels does not accord with the precondition assumption of a gray world algorithm; fig. 2(d) is a correction result using a perfect reflection algorithm, which substantially matches the visual effect of human eyes, but also has a yellowish phenomenon (overcorrection) due to the following reasons: there are no distinct highlighted areas in the image, so that the standard white assignment is biased. From experimental results of a plurality of actual color cast images, the algorithm improves automatic white balance adjustment, has a good correction effect on different types of color cast images, and shows wide applicability of the algorithm.
Example 2:
an embodiment 2 of the present invention provides a color cast detection and correction device based on an HSV color space, and as shown in fig. 3, the method includes: a calculation unit 11, a preprocessing unit 12, a judgment unit 13, a determination unit 14 and a correction unit 15.
Wherein,
the calculation unit 11 is configured to calculate a value of an S channel in the HSV color space, and count a histogram vector h of the S channel;
a preprocessing unit 12 for quantizing and filtering the histogram vectors;
a judging unit 13 for judging whether the image is color-cast;
a determination unit 14 for determining a color cast channel;
and the correcting unit 15 is used for correcting the color cast channel of the image and returning to the statistical unit.
Further, as shown in fig. 4, the calculation unit 11 includes: a calculation module 111, a statistics module 112; as shown in fig. 4, the preprocessing unit 12 includes: a quantization module 121 and a filtering module 122.
When the calculating unit 11 shown in fig. 4 is used to calculate S channel and count histogram thereof, the specific process can be seen in the methods 102 and 103 in embodiment 1.
When the preprocessing unit 12 shown in fig. 5 implements quantization and filtering, the specific process can be referred to the method shown as 104 in embodiment 1.
The embodiment of the invention is mainly applied to the processing of the color cast detection of the image, the technical scheme provided by the embodiment of the invention is not limited by scenes or priori knowledge, has universal adaptability, and simultaneously improves the accuracy and the reliability of the color cast detection.

Claims (13)

1. A color cast detection and correction method based on HSV color space comprises the following steps:
(1) inputting an image to be detected;
(2) calculating the value of an S channel in the HSV color space;
(3) counting a histogram vector h of the S channel;
(4) quantizing and filtering the histogram vector h;
(5) judging whether the image is color cast according to the quantized and filtered histogram vector h';
(6) if the image color cast is judged, respectively counting the contribution rates of the RGB channels to the maximum matrix and the minimum matrix, and judging the color cast channel according to the contribution rates;
(7) in the RGB color space, adjusting the value of the color cast channel, and returning to the step 2;
(8) if the image is determined not to be color-cast, the process ends.
2. The method of calculating the value of the S channel of claim 1 by: 1) and counting the maximum value matrix and the minimum value matrix of the S channel, and respectively recording as:(ii) a 2) Calculating the value of S channel by
Figure 871681DEST_PATH_IMAGE002
And (5) obtaining the value of the S channel by a formula.
3. The HSV color space-based color cast detection and correction method of claim 1, wherein: and (4) quantizing the histogram vector h by reserving 4 bits after decimal point of a quantized value, and rounding 5 in the 5 th bit according to 4.
4. The HSV color space-based color cast detection and correction method of claim 1, wherein: and (4) filtering the histogram vector h by using an improved one-dimensional median filtering formula:
Figure 983862DEST_PATH_IMAGE003
wherein,is the median filter function.
5. The HSV color space-based color cast detection and correction method of claim 1, wherein: and (5) judging whether the histogram vector h 'is color cast or not by taking the first N elements in the histogram vector h' for judgment, wherein the value range of N is a positive integer between 15 and 25.
6. The HSV color space-based color cast detection and correction method of claim 1, wherein: the method for judging whether the histogram vector h 'is color cast in the step (5) is to take the average value of the first N elements of the histogram vector h' and the threshold value TVComparing if the average value is less than the threshold value TVThen a color cast is considered, threshold TVThe value of (a) is in the range of 0.0002 to 0.0005.
7. The HSV color space-based color cast detection and correction method of claim 1, wherein: the method for judging whether the histogram vector h 'is color cast in the step (5) is to take the values of the first N elements of the histogram vector h', if the number of the calculated local maximum and minimum values is greater than the threshold value TNIf the color is color cast, the threshold value TNThe value of (a) is a positive integer between 3 and 5.
8. The statistical method of the local range occurrence of the maximum and minimum values according to claim 7
Figure 472929DEST_PATH_IMAGE005
And
Figure 445696DEST_PATH_IMAGE006
and (5) formula statistics.
9. The HSV color space-based bias of claim 1The color detection and correction method is characterized in that: step (6) determining the color cast channel method is to determine the maximum value contribution rate of each RGB channel
Figure 530326DEST_PATH_IMAGE007
Respectively subtracting the corresponding minimum contribution ratesAnd obtaining three difference values, wherein the channel corresponding to the minimum value is the color cast channel, and the contribution rate of the maximum and minimum value matrixes is the ratio of the number of pixels of the maximum or minimum value provided by a certain channel to the number of all pixels of the channel when counting the maximum and minimum value matrixes.
10. The HSV color space-based color cast detection and correction method of claim 1, wherein: and (5) the method for adjusting the color cast channel value in the step (7) is to multiply the value of the color cast channel by a correction coefficient k, wherein the value range of k is 1.02-1.05.
11. An apparatus for detecting and correcting color cast of an image, comprising:
the calculation unit is used for calculating the value of an S channel in the HSV color space and counting a histogram vector h of the S channel;
a preprocessing unit for quantizing and filtering the histogram vectors;
a judging unit for judging whether the image has color cast or not, if the average value of the first N elements in the histogram vector is less than the preset threshold value TVOr the number of times of local maximum minimum value appearing in the first N elements in the histogram vector is more than a threshold value TNIf the input image is determined to be color-cast, otherwise, the input image is determined not to be color-cast, the program is ended, the value range of N is a positive integer between 15 and 25, and the threshold value T isVThe value range of (1) is 0.0002-0.0005, and the threshold value TNThe value range of (1) is a positive integer between 3 and 5;
a determining unit for determining color cast channel and determining maximum contribution rate of each RGB channel
Figure 926858DEST_PATH_IMAGE007
Respectively subtracting the corresponding minimum contribution rates
Figure 382110DEST_PATH_IMAGE008
Obtaining three difference values, wherein the channel corresponding to the minimum value is a color cast channel;
and the correction unit is used for correcting the color cast image, multiplying the numerical value of the color cast channel by a correction coefficient k (k takes the value of 1.02-1.05), and returning to the statistical unit.
12. The computing unit of claim 11, comprising:
a calculation module for calculating S channel value in HSV color space by using formula
Figure 219616DEST_PATH_IMAGE002
The maximum and minimum matrices of the S channel are respectively noted as: MX and MN;
and the statistical module is used for counting the square vector h of the S channel.
13. The pre-processing unit of claim 11, comprising:
the quantization module is used for quantizing the histogram vector by a method of reserving 4 bits after decimal point of a quantized value, and the 5 th bit is divided into 5 bits according to 4 bits;
the filtering module is used for filtering the histogram vector and adopting an improved one-dimensional median filtering formula to carry out filtering, wherein the formula is as follows:
wherein,
Figure 507302DEST_PATH_IMAGE004
is the median filter function.
CN201310038277.9A 2013-01-31 2013-01-31 A kind of color cast detection based on hsv color space, bearing calibration and device Active CN103065334B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310038277.9A CN103065334B (en) 2013-01-31 2013-01-31 A kind of color cast detection based on hsv color space, bearing calibration and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310038277.9A CN103065334B (en) 2013-01-31 2013-01-31 A kind of color cast detection based on hsv color space, bearing calibration and device

Publications (2)

Publication Number Publication Date
CN103065334A true CN103065334A (en) 2013-04-24
CN103065334B CN103065334B (en) 2015-12-09

Family

ID=48107951

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310038277.9A Active CN103065334B (en) 2013-01-31 2013-01-31 A kind of color cast detection based on hsv color space, bearing calibration and device

Country Status (1)

Country Link
CN (1) CN103065334B (en)

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103500457A (en) * 2013-10-23 2014-01-08 武汉东智科技有限公司 Method of color cast detection of video image
CN103702111A (en) * 2013-12-24 2014-04-02 北京佳讯飞鸿电气股份有限公司 Method for detecting camera video color cast
CN104050645A (en) * 2014-06-23 2014-09-17 小米科技有限责任公司 Image processing method and device
CN105957111A (en) * 2016-04-27 2016-09-21 武汉大学 Sequence remote sensing image tone consistency correction method and system
CN106162161A (en) * 2016-07-05 2016-11-23 青岛海信电器股份有限公司 A kind of image detecting method and display device
CN106296751A (en) * 2016-08-16 2017-01-04 中国石油化工股份有限公司 The color processing method that a kind of view-based access control model is experienced
CN107209927A (en) * 2014-09-19 2017-09-26 巴尔科股份有限公司 The method for improving contrast using the visual artifacts of reduction
CN107341767A (en) * 2016-04-29 2017-11-10 杭州海康威视数字技术股份有限公司 A kind of method for correcting image and device
CN107644437A (en) * 2016-07-21 2018-01-30 宁波舜宇光电信息有限公司 Color cast detection system and method based on piecemeal
CN108242061A (en) * 2018-02-11 2018-07-03 南京亿猫信息技术有限公司 A kind of supermarket shopping car hard recognition method based on Sobel operators
CN109815875A (en) * 2019-01-17 2019-05-28 柳州康云互联科技有限公司 One kind is for versicolor system in internet detection
CN111898449A (en) * 2020-06-30 2020-11-06 北京大学 Pedestrian attribute identification method and system based on monitoring video
CN112667187A (en) * 2020-12-23 2021-04-16 深圳市尊正数字视频有限公司 Color matching method and system of monitor, intelligent terminal and storage medium
CN112668426A (en) * 2020-12-19 2021-04-16 中国民用航空飞行学院 Fire disaster image color cast quantization method based on three color modes

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1489832A1 (en) * 2003-06-18 2004-12-22 Agfa-Gevaert AG Method for automatic correction of skin tones in digital image data
EP2051210A1 (en) * 2007-10-17 2009-04-22 Qualcomm Incorporated Effective red eye removal in digital images without face detection
CN102005046A (en) * 2010-11-10 2011-04-06 新太科技股份有限公司 Novel method for detecting image color cast by color saturation detecting technology
CN102169585A (en) * 2011-03-31 2011-08-31 汉王科技股份有限公司 Method and device for detecting image color cast

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1489832A1 (en) * 2003-06-18 2004-12-22 Agfa-Gevaert AG Method for automatic correction of skin tones in digital image data
EP2051210A1 (en) * 2007-10-17 2009-04-22 Qualcomm Incorporated Effective red eye removal in digital images without face detection
CN102005046A (en) * 2010-11-10 2011-04-06 新太科技股份有限公司 Novel method for detecting image color cast by color saturation detecting technology
CN102169585A (en) * 2011-03-31 2011-08-31 汉王科技股份有限公司 Method and device for detecting image color cast

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
郑建铧 等: "利用色彩直方图特征进行偏色图象的自动检测和校正", 《中国图象图形学报》, vol. 8, no. 9, 30 September 2003 (2003-09-30) *

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103500457B (en) * 2013-10-23 2016-06-22 武汉东智科技有限公司 A kind of method of video image color cast detection
CN103500457A (en) * 2013-10-23 2014-01-08 武汉东智科技有限公司 Method of color cast detection of video image
CN103702111A (en) * 2013-12-24 2014-04-02 北京佳讯飞鸿电气股份有限公司 Method for detecting camera video color cast
CN103702111B (en) * 2013-12-24 2016-01-27 北京佳讯飞鸿电气股份有限公司 A kind of method detecting camera video color cast
CN104050645B (en) * 2014-06-23 2017-01-11 小米科技有限责任公司 Image processing method and device
CN104050645A (en) * 2014-06-23 2014-09-17 小米科技有限责任公司 Image processing method and device
CN107209927B (en) * 2014-09-19 2020-07-03 巴尔科股份有限公司 Method for improving contrast with reduced visual artifacts
CN107209927A (en) * 2014-09-19 2017-09-26 巴尔科股份有限公司 The method for improving contrast using the visual artifacts of reduction
CN105957111A (en) * 2016-04-27 2016-09-21 武汉大学 Sequence remote sensing image tone consistency correction method and system
CN105957111B (en) * 2016-04-27 2018-09-18 深圳积木易搭科技技术有限公司 The color tone consistency bearing calibration of sequence remote sensing image and system
CN107341767A (en) * 2016-04-29 2017-11-10 杭州海康威视数字技术股份有限公司 A kind of method for correcting image and device
CN107341767B (en) * 2016-04-29 2020-07-03 杭州海康威视数字技术股份有限公司 Image correction method and device
CN106162161A (en) * 2016-07-05 2016-11-23 青岛海信电器股份有限公司 A kind of image detecting method and display device
CN107644437B (en) * 2016-07-21 2021-01-26 宁波舜宇光电信息有限公司 Color cast detection system and method based on blocks
CN107644437A (en) * 2016-07-21 2018-01-30 宁波舜宇光电信息有限公司 Color cast detection system and method based on piecemeal
CN106296751A (en) * 2016-08-16 2017-01-04 中国石油化工股份有限公司 The color processing method that a kind of view-based access control model is experienced
CN108242061A (en) * 2018-02-11 2018-07-03 南京亿猫信息技术有限公司 A kind of supermarket shopping car hard recognition method based on Sobel operators
CN108242061B (en) * 2018-02-11 2022-04-08 南京亿猫信息技术有限公司 Supermarket shopping cart hand identification method based on Sobel operator
CN109815875A (en) * 2019-01-17 2019-05-28 柳州康云互联科技有限公司 One kind is for versicolor system in internet detection
CN111898449A (en) * 2020-06-30 2020-11-06 北京大学 Pedestrian attribute identification method and system based on monitoring video
CN112668426A (en) * 2020-12-19 2021-04-16 中国民用航空飞行学院 Fire disaster image color cast quantization method based on three color modes
CN112667187A (en) * 2020-12-23 2021-04-16 深圳市尊正数字视频有限公司 Color matching method and system of monitor, intelligent terminal and storage medium

Also Published As

Publication number Publication date
CN103065334B (en) 2015-12-09

Similar Documents

Publication Publication Date Title
CN103065334B (en) A kind of color cast detection based on hsv color space, bearing calibration and device
CN108600725B (en) White balance correction device and method based on RGB-IR image data
CN107451969B (en) Image processing method, image processing device, mobile terminal and computer readable storage medium
US8472717B2 (en) Foreground image separation method
Banić et al. Improving the white patch method by subsampling
CN112073703B (en) Method and device for adjusting color correction matrix, terminal equipment and medium
CN109785240B (en) Low-illumination image enhancement method and device and image processing equipment
CN108230407B (en) Image processing method and device
CN104504722B (en) Method for correcting image colors through gray points
JP2000171304A (en) Detecting method of color illumination color temperature and device therefor
EP2953340B1 (en) Image processing device, image processing method, program, and recording medium
US10224004B2 (en) Automatic white balance based on surface reflection decomposition
CN113301318A (en) Image white balance processing method and device, storage medium and terminal
CN110766636B (en) Intelligent image processing method for AI chip
CN110175967B (en) Image defogging processing method, system, computer device and storage medium
CN110188640B (en) Face recognition method, face recognition device, server and computer readable medium
CN107424134B (en) Image processing method, image processing device, computer-readable storage medium and computer equipment
US20180176420A1 (en) Automatic white balance based on surface reflection decomposition and chromatic adaptation
CN112699760A (en) Face target area detection method, device and equipment
CN110086997B (en) Face image exposure brightness compensation method and device
CN110648297A (en) Image defogging method and system, electronic equipment and storage medium
JP2003209856A (en) White balance correction method
CN109246406B (en) Method for realizing automatic white balance of color camera
CN113591630A (en) Certificate photo automatic processing method, system, terminal equipment and storage medium
KR101005625B1 (en) A method for color compensation based on color characteristic curve of a camera

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant