CN111612702A - Neutral color correction post-processing method for color migration - Google Patents

Neutral color correction post-processing method for color migration Download PDF

Info

Publication number
CN111612702A
CN111612702A CN202010263116.XA CN202010263116A CN111612702A CN 111612702 A CN111612702 A CN 111612702A CN 202010263116 A CN202010263116 A CN 202010263116A CN 111612702 A CN111612702 A CN 111612702A
Authority
CN
China
Prior art keywords
color
image
correction
saturation
follows
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
CN202010263116.XA
Other languages
Chinese (zh)
Other versions
CN111612702B (en
Inventor
沈徐铭
邹安娥
张显斗
王勇
陈伟贲
李思远
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.)
Hangzhou Dianzi University
Original Assignee
Hangzhou Dianzi University
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 Hangzhou Dianzi University filed Critical Hangzhou Dianzi University
Priority to CN202010263116.XA priority Critical patent/CN111612702B/en
Publication of CN111612702A publication Critical patent/CN111612702A/en
Application granted granted Critical
Publication of CN111612702B publication Critical patent/CN111612702B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20224—Image subtraction

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Facsimile Image Signal Circuits (AREA)
  • Color Image Communication Systems (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a neutral color correction post-processing method for color migration. The invention comprises the following steps: step (1) calculating L of original image*a*b*A saturation map in color space; step (2) standardizing and enhancing the saturation map obtained in the step (1); step (3) calculating L of the original image and the migration image*a*b*Three channels are differenced to obtain a difference image; step (4) according to the neutral color correction intention, carrying out saturation weighting on the difference image obtained in the step (3), and calculating to obtain a neutral color correction image; step (5) carrying out tone correction on the neutral color correction image to obtain a final correction image; and then converting the final corrected image back to the sRGB color space for storage and display. According to the invention, through the calculation of the chroma saturation information, the original color cast neutral color after color migration is corrected on the premise of ensuring a better overall color migration effect, so that the visual quality of the image after color migration is improved.

Description

Neutral color correction post-processing method for color migration
Technical Field
The invention relates to a neutral color correction post-processing method for color migration. Belongs to the technical fields of computer vision, image fusion, color correction and the like.
Background
Color migration is a popular problem in the field of computer vision, and by transferring the color style of a reference image to an original image and by using different reference images, the color style can be changed on the premise of not changing the content of the original image, so that different illumination, weather conditions, scene materials and even artistic color effects can be simulated.
Currently, the research of color migration focuses on how to achieve more accurate transmission and more similar color style conversion, such as color migration based on texture, color migration based on high-level semantic correspondence, color migration based on local regions, and artifact reduction caused by color migration.
In the current color migration method, neutral color (black, white, gray) weighting or retention is not considered. When evaluating the image quality, the human eye vision is more sensitive to neutral color than to the region with obvious non-neutral color information, and if the chromaticity of neutral color is greatly changed before and after the migration, the image quality is significantly reduced, as shown in fig. 1.
Disclosure of Invention
The technical scheme adopted by the invention for solving the practical application problem is a neutral color correction post-processing method aiming at various existing color migration methods, and the processing process is in L*a*b*The color space comprises the following specific steps:
step (1) calculating L of original image*a*b*A saturation map in color space;
step (2) standardizing and enhancing the saturation map obtained in the step (1);
step (3) calculating L of the original image and the migration image*a*b*Three channels are differenced to obtain a difference image;
the original image and the migration image are images with different color styles and the same content;
step (4) according to the neutral color correction intention, carrying out saturation weighting on the difference image obtained in the step (3) and calculating a neutral color correction image;
step (5) carrying out tone correction on the neutral color correction image to obtain a final correction image; and then converting the final corrected image back to the sRGB color space for storage and display.
Further, the color space of the default image storage in the step (1) is the sRGB color space, and the sRGB color space is L*a*b*The color space conversion of (2) first requires inverse gamma correction, and the calculation method is as follows:
Figure BDA0002440167400000021
wherein, rgb is three channel values of sRGB color space, and its dynamic range is [0, 255 ]. And the gamma (x) function is calculated as follows:
Figure BDA0002440167400000022
cannot be converted directly to L by RGB*a*b*Space, the middle needs to be transformed through XYZ space. The calculation method for converting XYZ from RGB is as follows:
Figure BDA0002440167400000023
through XYZ space, L pair can be realized*a*b*The calculation method is as follows:
Figure BDA0002440167400000024
wherein ,XnYnZnIs the XYZ value of standard white, and the standard white tristimulus value under the illumination condition of a D65 light source is generally taken as XnYnZn，(Xn，Yn，Zn)＝（0.95047，1，1.08883)。
And the function f (t) is calculated as follows:
Figure BDA0002440167400000025
the saturation map S of the original image is calculated as follows:
Figure BDA0002440167400000031
further, in step (2), in order to enable the low-saturation image to still retain most of the color migration effect after the neutral color correction, the saturation map S needs to be normalized to obtain a normalized saturation map S', which is as follows:
Figure BDA0002440167400000032
wherein ,SminIs the minimum value of all pixels in the saturation map S, and SmaxIs the maximum value of all pixels in the saturation map S.
In order to further ensure the color migration effect, the saturation value of the specific percentile of the saturation is used for further weighting to realize enhancement, and an enhanced saturation map S is obtained*The method comprises the following steps:
Figure BDA0002440167400000033
wherein ,SnThe normalized saturation value at the nth% after the normalized saturation map is ranked from small right to large right, where n is 30, i.e. the normalized saturation map is ranked at the saturation value of 30% from small right to large right.
Since the saturation is higher than 1 after the processing of the formula (8), the abnormal value processing is required, as follows:
Figure BDA0002440167400000034
for the final saturation map
Figure BDA0002440167400000035
A further Gaussian filter with a convolution kernel size of × size is performed, the size being represented by a saturation map
Figure BDA0002440167400000036
M and n are saturation diagrams
Figure BDA0002440167400000037
The number of pixels in length, width, where round () is a rounding function; the method comprises the following specific steps:
Figure BDA0002440167400000038
further, L of the original image and the transition image is calculated in the step (3)*a*b*And obtaining a difference image by three-channel difference, wherein the difference image is as follows:
Figure BDA0002440167400000039
wherein ,
Figure BDA0002440167400000041
for transferring L of an image*a*b*The values of the three channels are set to be,
Figure BDA0002440167400000042
is L of the original image*a*b*Three channel values. Note that Δ L*Δa*Δb*Positive and negative values are distinguished.
Further, in the step (4), a color migration image for neutral color correction is calculated based on the intention for neutral color correction.
If the neutral color correction is intended to be completely reserved for neutral color, the correction calculation method is as follows:
Figure BDA0002440167400000043
if the intent of the neutral color correction is to preserve chromaticity (complete shift of luminance) for neutral color, the correction calculation method is as follows:
Figure BDA0002440167400000044
further, in step (5), in order to ensure color consistency before and after neutral color correction, tone correction is performed to obtain a final corrected image, and a solution target is as follows:
Figure BDA0002440167400000045
wherein ,
Figure BDA0002440167400000046
the solution uses the following formula:
Figure BDA0002440167400000047
wherein
Figure BDA0002440167400000048
wherein
Figure BDA0002440167400000049
Finally, in order to
Figure BDA0002440167400000051
Taking the Lab space three-channel value as the final correction image, and converting the color space in the step (1) in an inverse manner to obtain the final correction image from L*a*b*And converting the color space into an sRGB color space to obtain a color migration image corrected by the neutral color.
The technical scheme provided by the invention has the beneficial effects that:
aiming at the problems that the color cast of the neutral color is serious, the image quality and the visual experience are influenced and the like in the existing color migration method, the neutral color with the serious color cast in the image after the color migration is corrected by calculating the chroma saturation information on the premise of ensuring the better overall color migration effect and realizing the color style conversion, so that the visual quality of the image after the color migration is improved.
Drawings
FIG. 1 illustrates the color shift problem of neutral color in the prior art image migration method;
FIG. 2 is an original image in an embodiment;
FIG. 3 is a migration image of neutral color cast obtained by Reinhard's method in an example;
FIG. 4 is a saturation map of an original image in an embodiment;
FIG. 5 is a normalized saturation map of the original image after normalization in the example;
FIG. 6 is the result of the overall enhancement of the saturation map using the saturation magnitude at the 30% percentile from small to large normalized saturation in the example;
FIG. 7 is a final saturation map obtained by performing convolution smoothing on the saturation map of FIG. 6 by a Gaussian filter kernel according to an embodiment;
FIG. 8 is a color shifted image with neutral chroma preservation correction;
fig. 9 is a color-shifted image of a neutral-color-complete-remaining correction.
Detailed Description
The invention is further illustrated by the following figures and examples.
The invention mainly provides a neutral color correction post-processing method for color migration. For the migration image and the original image after color migration, the probability of neutral color of each pixel is judged according to the saturation information of each pixel of the original image, an algorithm hyper-parameter is obtained through calculation of the saturation information through a continuous and smooth prior function, and the hyper-parameter determines the degree of color migration. For the pixels with medium and high saturation, high-degree color migration is carried out; for low saturation pixels, a lower degree of migration is performed. While neutral color regions tend to be of low saturation, thereby allowing neutral color correction post-processing for color migration.
Embodiments of the present invention are common landscape images. Referring to fig. 2 (original image) and fig. 3 (color migration image obtained by Reinhard method), the flow of the embodiment of the present invention includes the following steps:
step (1) calculating L of original image*a*b*A saturation map in color space;
step (2) standardizing and enhancing the saturation map obtained in the step (1);
step (3) calculating L of the original image and the migration image*a*b*Three channels are differenced to obtain a difference image;
step (4) according to the neutral color correction intention, carrying out saturation weighting on the difference image obtained in the step (3), and calculating to obtain a neutral color correction image;
step (5) carrying out tone correction on the neutral color correction image to obtain a final correction image; and then converting the final corrected image back to the sRGB color space for storage and display.
In step (1), taking fig. 2 as an example of an original image, the value of L is calculated*a*b*A saturation image in color space, as shown in fig. 4. Since the default stored color space of an image is the sRGB color space, the sRGB color space goes to L*a*b*The color space conversion of (2) first requires inverse gamma correction, and the calculation method is as follows:
Figure BDA0002440167400000061
wherein, rgb is three channel values of sRGB color space, and its dynamic range is [0, 255 ]. And the gamma (x) function is calculated as follows:
Figure BDA0002440167400000062
cannot be converted directly to L by RGB*a*b*Space, the middle needs to be transformed through XYZ space. The calculation method for converting XYZ from RGB is as follows:
Figure BDA0002440167400000063
by XYZ, we can realize the pair L*a*b*The calculation method is as follows:
Figure BDA0002440167400000071
wherein ,XnYnZnIs the XYZ value of standard white, and the standard white tristimulus value under the illumination condition of a D65 light source is generally taken as XnYnZn，(Xn，Yn，Zn)＝(0.95047，1，1.08883)。
And the function f (t) is calculated as follows:
Figure BDA0002440167400000072
the original image saturation information is calculated as follows:
Figure BDA0002440167400000073
in step (2), in order to enable the low-saturation image to still retain most of the color migration effect after the neutral color correction, the saturation map S needs to be normalized to obtain a normalized saturation map S', as shown in fig. 5, the process is as follows:
Figure BDA0002440167400000074
wherein ,SminIs the minimum value of all pixels in the saturation map S, and SmaxIs the maximum value of all pixels in the saturation map S;
in order to further ensure the color migration effect, the saturation value of the saturation specific percentile is used for further weighting to realize enhancement, and an enhanced saturation map S is obtained*As shown in fig. 6, the following are specific:
Figure BDA0002440167400000075
wherein ,SnThe normalized saturation value at the nth% after the normalized saturation map is ordered from small right to large right, wherein n is 30, namely the normalized saturation map is ordered from small right to large saturation value at 30%;
since the saturation is higher than 1 after the processing of the formula (8), the abnormal value processing is required, as follows:
Figure BDA0002440167400000081
for the final saturation map
Figure BDA0002440167400000082
Performing Gaussian filtering with convolution kernel size of × size to obtain filtered image shown in FIG. 7, wherein the size is represented by saturation map
Figure BDA0002440167400000083
M and n are saturation diagrams
Figure BDA0002440167400000084
The number of pixels in length, width, where round () is a rounding function; the method comprises the following specific steps:
Figure BDA0002440167400000085
calculating L of the original image and the migration image in the step (3)*a*b*And obtaining a difference image by three-channel difference, wherein the difference image is as follows:
Figure BDA0002440167400000086
wherein ,
Figure BDA0002440167400000087
for transferring L of an image*a*b*The values of the three channels are set to be,
Figure BDA0002440167400000088
is L of the original image*a*b*Three channel values. Note that Δ L*Δa*Δb*Positive and negative values are distinguished.
And (4) calculating a color migration image for neutral color correction according to the neutral color correction intention.
If the neutral color correction is intended to be completely retained for the neutral color, and the resulting neutral color corrected image is as shown in fig. 9, the correction calculation method is as follows:
Figure BDA0002440167400000089
if the neutral color correction is intended to preserve the chromaticity of the neutral color, i.e., the luminance is completely shifted, and the obtained neutral color corrected image is as shown in fig. 8, the correction calculation method is as follows:
Figure BDA0002440167400000091
in the step (5), in order to ensure the consistency of the color before the neutral color correction, the color tone correction is needed, so that a final corrected image is obtained; converting the tone correction into a form of target solving, and specifically solving the target as follows:
Figure BDA0002440167400000092
wherein ,
Figure BDA0002440167400000093
the solution uses the following formula:
Figure BDA0002440167400000094
wherein
Figure BDA0002440167400000095
wherein
Figure BDA0002440167400000096
Finally, in order to
Figure BDA0002440167400000097
Taking the Lab space three-channel value as the final correction image, and converting the color space in the step (1) in an inverse manner to obtain the final correction image from L*a*b*And converting the color space into an sRGB color space to obtain a color migration image corrected by the neutral color.
Thus, L of the neutral color corrected image is obtained*a*b*Characterization in space, it is also necessary to transform it back into sRGB color space.
Finally, the final corrected image is converted from L by the color space conversion in the step (1) which is realized reversely*a*b*Converting the color space into sRGB color space to obtain neutral color corrected Reinhard color migration image, and converting L*a*b*The first step in the conversion of the color space back to the XYZ color space is as follows:
Figure BDA0002440167400000101
wherein the inverse of f (x) is solved as follows:
Figure BDA0002440167400000102
the calculation of the conversion back to XYZ color space is as follows:
Figure BDA0002440167400000103
wherein ,(Xn，Yn，Zn)＝(0.95047，1，1.08883)。
And the first step conversion of the XYZ color space to the sRGB color space is as follows:
Figure BDA0002440167400000104
by inverse gamma correction, the transformation to the sRGB color space can be done.
Figure BDA0002440167400000105
Wherein the inverse gamma correction function is as follows:
Figure BDA0002440167400000106
this completes the neutral color correction of the color transition image based on the original image saturation information.
The foregoing is a more detailed description of the invention, taken in conjunction with the preferred embodiments, and it is not intended that the invention be limited to the specific embodiments disclosed. It will be understood by those skilled in the art that various changes in detail may be effected therein without departing from the scope of the invention as defined by the appended claims.

Claims (6)

1. A neutral color correction post-processing method for color migration is characterized by comprising the following steps:
step (1) calculating L of original image*a*b*A saturation map in color space;
step (2) standardizing and enhancing the saturation map obtained in the step (1);
step (3) countingCalculating L of original image and migration image*a*b*Three channels are differenced to obtain a difference image;
step (4) according to the neutral color correction intention, carrying out saturation weighting on the difference image obtained in the step (3), and calculating to obtain a neutral color correction image;
step (5) carrying out tone correction on the neutral color correction image to obtain a final correction image; and then converting the final corrected image back to the sRGB color space for storage and display.
2. The method for post-processing neutral color correction of color migration according to claim 1, wherein in step (2), in order to make the low saturation image still retain most of the color migration effect after the neutral color correction, the saturation map S needs to be normalized to obtain a normalized saturation map S', the process is as follows:
Figure FDA0002440167390000011
wherein ,SminIs the minimum value of all pixels in the saturation map S, and SmaxIs the maximum value of all pixels in the saturation map S;
in order to further ensure the color migration effect, the saturation value of the specific percentile of the saturation is used for further weighting to realize enhancement, and an enhanced saturation map S is obtained*The method comprises the following steps:
Figure FDA0002440167390000012
wherein ,SnThe normalized saturation value at the nth% after the normalized saturation map is ordered from small right to large right, wherein n is 30, namely the normalized saturation map is ordered from small right to large saturation value at 30%;
since the saturation is higher than 1 after the processing of the formula (8), the abnormal value processing is required, as follows:
Figure FDA0002440167390000013
for the final saturation map
Figure FDA0002440167390000021
A further Gaussian filter with a convolution kernel size of × size is performed, the size being represented by a saturation map
Figure FDA0002440167390000022
M and n are saturation diagrams
Figure FDA0002440167390000023
The number of pixels in length, width, where round () is a rounding function; the method comprises the following specific steps:
Figure FDA0002440167390000024
3. the method of claim 2, wherein the L of the original image and the L of the migrated image are calculated in step (3)*a*b*And obtaining a difference image by three-channel difference, wherein the difference image is as follows:
Figure FDA0002440167390000025
wherein ,
Figure FDA0002440167390000026
for transferring L of an image*a*b*The values of the three channels are set to be,
Figure FDA0002440167390000027
is L of the original image*a*b*Three channel values; note that Δ L*Δa*Δb*Positive and negative values are distinguished.
4. The method for post-processing neutral color correction of color shift according to claim 3, wherein the step (4) calculates a color shift image for neutral color correction according to the intention of neutral color correction as follows:
if the neutral color correction is intended to be completely reserved for neutral color, the correction calculation method is as follows:
Figure FDA0002440167390000028
if the intention of neutral color correction is to preserve the chromaticity of neutral color, i.e. the luminance is completely shifted, the correction calculation method is as follows:
Figure FDA0002440167390000029
5. the method for post-processing neutral color correction of color shift according to claim 4, wherein in step (5), to ensure the consistency of the color before neutral color correction, color tone correction is required, so as to obtain the final corrected image; converting the tone correction into a form of target solving, and specifically solving the target as follows:
Figure FDA0002440167390000031
wherein ,
Figure FDA0002440167390000032
the solution uses the following formula:
Figure FDA0002440167390000033
wherein
Figure FDA0002440167390000034
wherein
Figure FDA0002440167390000035
Finally, in order to
Figure FDA0002440167390000036
Taking the Lab space three-channel value as the final correction image, and converting the color space in the step (1) in an inverse manner to obtain the final correction image from L*a*b*And converting the color space into an sRGB color space to obtain a color migration image corrected by the neutral color.
6. The method for post-treatment of neutral color correction of color migration according to claim 1 or 5, wherein the step (1) is implemented as follows:
since the default stored color space of an image is the sRGB color space, the sRGB color space goes to L*a*b*The color space conversion of (2) first requires inverse gamma correction, and the calculation method is as follows:
Figure FDA0002440167390000037
wherein, rgb is three channel values of sRGB color space, and the dynamic range is [0, 255 ]; and the gamma (x) function is calculated as follows:
Figure FDA0002440167390000038
cannot be converted directly to L by RGB*a*b*Space, the middle needs to be transformed through XYZ space; the calculation method for converting XYZ from RGB is as follows:
Figure FDA0002440167390000041
through XYZ, realize to L*a*b*The calculation method is as follows:
Figure FDA0002440167390000042
wherein ,XnYnZnIs the XYZ value of standard white, and the standard white tristimulus value under the illumination condition of a D65 light source is generally taken as XnYnZn，(Xn，Yn，Zn) (0.95047, 1, 1.08883); and the function f (t) is calculated as follows:
Figure FDA0002440167390000043
the saturation map of the original image is calculated as follows:
Figure FDA0002440167390000044
CN202010263116.XA 2020-04-07 2020-04-07 Neutral color correction post-treatment method for color migration Active CN111612702B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010263116.XA CN111612702B (en) 2020-04-07 2020-04-07 Neutral color correction post-treatment method for color migration

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010263116.XA CN111612702B (en) 2020-04-07 2020-04-07 Neutral color correction post-treatment method for color migration

Publications (2)

Publication Number Publication Date
CN111612702A true CN111612702A (en) 2020-09-01
CN111612702B CN111612702B (en) 2023-04-21

Family

ID=72203667

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010263116.XA Active CN111612702B (en) 2020-04-07 2020-04-07 Neutral color correction post-treatment method for color migration

Country Status (1)

Country Link
CN (1) CN111612702B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20050015107A (en) * 2003-08-02 2005-02-21 삼성전자주식회사 Image enhancement apparatus and method thereof
CN1708137A (en) * 2004-06-09 2005-12-14 三星电子株式会社 Saturation-adaptive image enhancement apparatus and method
WO2008068884A1 (en) * 2006-11-30 2008-06-12 Nikon Corporation Image processing apparatus for correcting image color and image processing program
CN101621702A (en) * 2009-07-30 2010-01-06 北京海尔集成电路设计有限公司 Method and device for automatically adjusting chroma and saturation
US20100214310A1 (en) * 2009-02-23 2010-08-26 Yasuhiro Kuwahara Image processing apparatus, image processing method, recording medium, and integrated circuit
CN108416741A (en) * 2018-01-23 2018-08-17 浙江工商大学 Rapid image defogging method based on luminance contrast enhancing and saturation degree compensation
CN110276727A (en) * 2019-05-21 2019-09-24 杭州电子科技大学 A kind of color image color Enhancement Method towards dyschromatopsia
CN110349097A (en) * 2019-06-17 2019-10-18 深圳市华星光电技术有限公司 The color enhancement method and image processing apparatus of the significant property of image
CN110728722A (en) * 2019-09-18 2020-01-24 苏宁云计算有限公司 Image color migration method and device, computer equipment and storage medium

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20050015107A (en) * 2003-08-02 2005-02-21 삼성전자주식회사 Image enhancement apparatus and method thereof
CN1708137A (en) * 2004-06-09 2005-12-14 三星电子株式会社 Saturation-adaptive image enhancement apparatus and method
WO2008068884A1 (en) * 2006-11-30 2008-06-12 Nikon Corporation Image processing apparatus for correcting image color and image processing program
US20100214310A1 (en) * 2009-02-23 2010-08-26 Yasuhiro Kuwahara Image processing apparatus, image processing method, recording medium, and integrated circuit
CN101621702A (en) * 2009-07-30 2010-01-06 北京海尔集成电路设计有限公司 Method and device for automatically adjusting chroma and saturation
CN108416741A (en) * 2018-01-23 2018-08-17 浙江工商大学 Rapid image defogging method based on luminance contrast enhancing and saturation degree compensation
CN110276727A (en) * 2019-05-21 2019-09-24 杭州电子科技大学 A kind of color image color Enhancement Method towards dyschromatopsia
CN110349097A (en) * 2019-06-17 2019-10-18 深圳市华星光电技术有限公司 The color enhancement method and image processing apparatus of the significant property of image
CN110728722A (en) * 2019-09-18 2020-01-24 苏宁云计算有限公司 Image color migration method and device, computer equipment and storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
REINHARD E ETC: "Color transfer between images" *
林森;迟凯晨;李文涛;唐延东;: "基于优势特征图像融合的水下光学图像增强" *

Also Published As

Publication number Publication date
CN111612702B (en) 2023-04-21

Similar Documents

Publication Publication Date Title
CN106780368B (en) Underwater image enhancement method based on foreground model
CN105915909B (en) A kind of high dynamic range images layered compression method
CN106780311B (en) Rapid face image beautifying method combining skin roughness
CN103593830B (en) A kind of low illumination level video image enhancement
CN106897972A (en) A kind of self-adapting histogram underwater picture Enhancement Method of white balance and dark primary
CN108711140B (en) Image brightness uniformity real-time recovery method based on inter-class variance description
CN104537634B (en) The method and system of raindrop influence is removed in dynamic image
CN105761227A (en) Underwater image enhancement method based on dark channel prior algorithm and white balance
US7933469B2 (en) Video processing
CN106997584A (en) A kind of haze weather image enchancing method
Wang et al. Variational single nighttime image haze removal with a gray haze-line prior
CN109325918B (en) Image processing method and device and computer storage medium
CN110298812B (en) Image fusion processing method and device
CN111028181B (en) Image enhancement processing method, device, equipment and storage medium
CN111968065A (en) Self-adaptive enhancement method for image with uneven brightness
Pierre et al. Luminance-hue specification in the RGB space
US8565523B2 (en) Image content-based color balancing
CN109636739B (en) Detail processing method and device for enhancing image saturation
CN110766622A (en) Underwater image enhancement method based on brightness discrimination and Gamma smoothing
CN104463806A (en) Highly adaptive image contrast enhancing method based on data driving technology
CN114037641A (en) Low-illumination image enhancement method, device, equipment and medium
US8351724B2 (en) Blue sky color detection technique
WO2023241339A1 (en) Color cast correction method and apparatus, device, storage medium and program product
WO2012153661A1 (en) Image correction device, image correction display device, image correction method, program, and recording medium
CN111612702B (en) Neutral color correction post-treatment method for color migration

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