CN114820385B - Locally adaptive underwater image color correction method - Google Patents

Locally adaptive underwater image color correction method Download PDF

Info

Publication number
CN114820385B
CN114820385B CN202210555492.5A CN202210555492A CN114820385B CN 114820385 B CN114820385 B CN 114820385B CN 202210555492 A CN202210555492 A CN 202210555492A CN 114820385 B CN114820385 B CN 114820385B
Authority
CN
China
Prior art keywords
color
image
color channel
channel
maximum
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
Application number
CN202210555492.5A
Other languages
Chinese (zh)
Other versions
CN114820385A (en
Inventor
张卫东
李国厚
金松林
周玲
郑颖
安金梁
曲培新
白林峰
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.)
Henan Institute of Science and Technology
Original Assignee
Henan Institute of Science and 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 Henan Institute of Science and Technology filed Critical Henan Institute of Science and Technology
Priority to CN202210555492.5A priority Critical patent/CN114820385B/en
Publication of CN114820385A publication Critical patent/CN114820385A/en
Application granted granted Critical
Publication of CN114820385B publication Critical patent/CN114820385B/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
    • G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/40—Image enhancement or restoration using histogram techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/73—Deblurring; Sharpening
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/05—Underwater scenes
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Databases & Information Systems (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Processing Of Color Television Signals (AREA)
  • Image Processing (AREA)

Abstract

The invention provides a local self-adaptive underwater image color correction method, which comprises the steps of firstly obtaining a color distortion underwater image, counting the total pixel mean value of RGB three-color channels, redefining the total pixel mean value as a maximum color channel, a middle color channel and a minimum color channel; establishing a minimum color loss criterion based on gray world hypothesis and constructing color loss terms among three color channels, and processing the maximum color channel by using a linear transmission strategy; for the middle color channel and the minimum color channel, firstly constructing a compensation item to carry out iterative compensation, and then adopting a linear transmission strategy to process the middle color channel and the minimum color channel; estimating a color channel with the most serious attenuation in an original image by adopting a maximum attenuation map estimation strategy; the detail image and the color transmission image are subjected to pixel-by-pixel adjustment of the original image under the guidance of the maximum attenuation map to obtain a color correction image. The method reduces the color information loss and the attenuation of the lamplight, and the applicability and the robustness are enhanced.

Description

Locally adaptive underwater image color correction method
Technical Field
The invention relates to the technical field of underwater image processing, in particular to a local self-adaptive underwater image color correction method.
Background
In the field of underwater vision, high quality underwater images are important carriers for understanding and perceiving real scenes under water. However, the complex underwater physical environment often causes the underwater image to face serious quality degradation problems such as color distortion, low visibility, low contrast, detail loss and the like.
Among them, color distortion is a major degradation problem faced by most underwater images. In order to correct color distortion of underwater images, linear transformation, color compensation, color transmission and mixing methods have been demonstrated to be effective.
Recently, the linear transformation method and the color compensation method have demonstrated effectiveness in color correction of underwater images. However, these methods may introduce reddish distortions or underenhancement to the enhanced underwater image.
Color transmission is used as a precursor method for color correction of underwater images, and the method has remarkable effect on color correction, but the method needs to rely on a land image as a reference image for color transmission. Thus, the robustness and applicability of this type of approach faces serious challenges.
In addition, a method of combining linear transformation and color compensation is also gradually becoming a mainstream method of color correction of underwater images. Although this type of method has better color correction performance, its effectiveness and robustness need to be further improved for severely degraded underwater images.
The application number is as follows: 202210006725.6, the invention name is: according to the invention, the underwater image is divided into five types according to the average RGB channel ratio of an original image, then the color loss rate is calculated through the optical attenuation characteristic under the condition of not considering color cast, the loss rate error is calculated under the condition of considering color cast, the final color loss rate is obtained, and the color cast problem of the underwater image is corrected. The method solves the problem from the attenuation compensation point of view, and has relatively single solution and no wide applicability.
In general, conventional color transfer methods rely on referenceable land images for color correction, and such methods are not widely applicable to underwater images with color distortion diversity.
In order to solve the above problems, an ideal technical solution is always sought.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a local self-adaptive color correction method for the underwater image, which corrects the color distortion of the underwater image according to the fusion criterion guided by the minimum color loss criterion and the maximum attenuation chart and can overcome the problems of poor robustness and applicability of the traditional method.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows: a local self-adaptive underwater image color correction method comprises the following steps:
step 1) obtaining a color distortion underwater image, decomposing the color distortion underwater image into R, G and B three-color channels, counting the total pixel mean value of each color channel, and redefining the color distortion underwater image as the maximum, middle and minimum three color channels according to the total pixel mean value;
the formula for the total pixel mean for each color channel is as follows:
Figure BDA0003654692020000021
where H and W represent the height and width of the input image I.
Step 2) establishing a minimum color loss criterion based on the redefined three color channels in step 1) and on gray world assumptions, and establishing a color loss term between the redefined three color channels based on the minimum color loss criterion;
the gray world assumption is a gray world algorithm, and the assumption is that for a pair of images with a large number of color changes, the average value of the R, G, B three components tends to be the same gray value.
The minimum color loss criterion is a color loss calculation based on a gray value in a gray world hypothesis, which is the minimum color loss.
The formula of the color loss term is as follows:
Figure BDA0003654692020000031
wherein the redefined three color channels are respectively the maximum color channel I l Intermediate color channel I m And minimum color channel I s ，
Figure BDA0003654692020000032
And->
Figure BDA0003654692020000033
Respectively representing redefined three color channels I l 、I m And I s Is used for the average pixel value of (a).
Step 3) since the maximum color channel of the redefined three color channels decays less than the other two color channels, a simple and efficient linear transmission strategy is used for the maximum color channel only to expand the dynamic range of the maximum color channel.
The linear transmission strategy formula is expressed as follows:
Figure BDA0003654692020000034
wherein,,
Figure BDA0003654692020000035
is I l Is provided;
Figure BDA0003654692020000036
and->
Figure BDA0003654692020000037
Representing minimum and maximum pixel values of the input image, respectively;
Figure BDA0003654692020000038
and->
Figure BDA0003654692020000039
Respectively indicate the stretching range, & lt & gt>
Figure BDA00036546920200000310
And->
Figure BDA00036546920200000311
Set to 0 and 255, respectively.
Step 401) for the middle color channel and the smallest color channel of the redefined three color channels, constructing a compensation term between the largest color channel and the middle color channel and between the largest color channel and the smallest color channel, and performing compensation on the middle color channel and the smallest color channel by using the compensation term;
the formula for constructing the compensation term between the maximum color channel and the middle color channel and between the maximum color channel and the minimum color channel is as follows:
Figure BDA00036546920200000312
Figure BDA00036546920200000313
wherein,,
Figure BDA00036546920200000314
and->
Figure BDA00036546920200000315
Respectively represent I m And I s Is provided.
Step 402), in order to ensure that the histogram distribution and the mean value of each color channel are similar, adopting an iterative compensation method to enable the middle color channel and the minimum color channel to meet the constraint condition of color loss;
the constraint of the color loss is expressed as follows:
Figure BDA00036546920200000316
the threshold for the color loss constraint is set to 0.01-0.02, and the compensation formula of step 401) is iteratively optimized by minimizing the color loss constraint until convergence.
Step 403) adopts the same linear transmission strategy as that of step 3) to expand the dynamic ranges of the compensated middle color channel and the minimum color channel, and then combines the processing of step 3) on the maximum color channel to obtain a color transmission image.
Step 5) in order to accurately estimate the light attenuation related to the wavelength, estimating a color channel with the most serious attenuation in the R, G and B three-color channels in the original image of the color distortion underwater image by adopting a maximum attenuation map estimation strategy;
the solving process of the maximum attenuation map is represented as follows:
Figure BDA0003654692020000041
wherein, gamma and a parameter representing the intensity of the control received light are set to 1-1.2.
Step 6) adjusting the detail image of the original image and the color transmission image obtained in step 403) pixel by pixel under the guidance of the maximum attenuation map obtained in step 5) to obtain a color correction image. Wherein the detail image is obtained by a detail sharpening method.
The maximum attenuation map guided fusion process is as follows:
Figure BDA0003654692020000042
wherein,,
Figure BDA0003654692020000043
representing the color transmission image obtained by step 403);
Figure BDA0003654692020000044
representing the maximum attenuation map obtained by step 5);
Figure BDA0003654692020000045
representing a final color corrected image;
d represents a detail image expressed as D c ＝I c -G c *I c ；
The detail image is an image obtained by subtracting gaussian kernel blur from the input image, and represents a convolution operation.
Compared with the prior art, the invention has outstanding substantive characteristics and remarkable progress, in particular to the invention cuts in from the angle of minimum color information loss, redefines each color channel for the original underwater image, respectively carries out targeted processing on the three color channels based on the minimum color loss criterion, and obtains the color transmission image. Then, the detail image, the original image and the color transmission image are mixed pixel by pixel based on a fusion criterion guided by the maximum attenuation map under the RGB three channels, and a final color correction image is obtained. The method solves the problems of poor robustness and applicability faced by the traditional color transmission method, especially when the land image is used as a reference image for carrying out the color correction of the underwater image.
In addition, the invention reduces the color information loss of different color channels by using the minimum color loss criterion, reduces the attenuation of lamplight by using the fusion strategy guided by the maximum attenuation image, and corrects the color underwater image to keep the inherent characteristics of the original image.
Drawings
Fig. 1 is a flow chart of a method for correcting colors of an underwater image in a locally adaptive manner.
Fig. 2 is an enhanced result and gray level histogram for a blue-distorted underwater image according to the present invention and other methods.
Fig. 3 is an enhanced result and gray level histogram for green distorted underwater images according to the present invention and other methods.
Fig. 4 is an enhanced result and gray level histogram for a yellow-distorted underwater image according to the present invention and other methods.
Fig. 5 is a graph of enhancement results and gray level histograms for bluish-green distorted underwater images according to the present invention and other methods.
Detailed Description
In order to verify the effectiveness of the color correction, the invention selects the underwater images with different color distortion types as a test set, and simultaneously carries out subjective and objective comparison with Gray-Edge (GE), shades-of-Gray (SOG), max-RGB (MR), gray-World (GW) and Weight-Gray-Edge (WGE) methods.
As shown in fig. 1, a locally adaptive underwater image color correction method includes the following steps:
step 1) obtaining a color distortion underwater image, decomposing the color distortion underwater image into R, G and B three-color channels, counting the total pixel mean value of each color channel, and redefining the color distortion underwater image as the maximum, middle and minimum three color channels according to the total pixel mean value;
the total pixel mean for each color channel is calculated by the following formula:
Figure BDA0003654692020000051
where H and W represent the height and width of the input image I.
Step 2) based on the three redefined color channels in step 1), establishing a minimum color loss criterion based on gray world assumptions, and constructing a color loss term between the redefined three color channels based on the minimum color loss criterion, calculated by the following formula:
Figure BDA0003654692020000061
wherein the redefined three color channels are respectively the maximum color channel I l Intermediate color channel I m And minimum color channel I s ，
Figure BDA0003654692020000062
And->
Figure BDA0003654692020000063
Respectively representing redefined three color channels I l 、I m And I s Is used for the average pixel value of (a).
Step 3) since the attenuation of the largest color channel of the redefined three color channels is smaller than the other two color channels, a simple and efficient linear transmission strategy is used only for the largest color channel to expand the dynamic range of the largest color channel as follows:
Figure BDA0003654692020000064
wherein,,
Figure BDA0003654692020000065
is I l Is provided;
Figure BDA0003654692020000066
and->
Figure BDA0003654692020000067
Representing minimum and maximum pixel values of the input image, respectively;
Figure BDA0003654692020000068
and->
Figure BDA0003654692020000069
Respectively indicate the stretching range, & lt & gt>
Figure BDA00036546920200000610
And->
Figure BDA00036546920200000611
Set to 0 and 255, respectively.
Step 401) for the middle color channel and the smallest color channel of the redefined three color channels, constructing a compensation term between the largest color channel and the middle color channel and between the largest color channel and the smallest color channel, and performing compensation on the middle color channel and the smallest color channel by using the compensation term;
the formula for constructing the compensation term between the maximum color channel and the middle color channel and between the maximum color channel and the minimum color channel is as follows:
Figure BDA00036546920200000612
Figure BDA00036546920200000613
wherein,,
Figure BDA00036546920200000614
and->
Figure BDA00036546920200000615
Respectively represent I m And I s Is provided.
Step 402), in order to ensure that the histogram distribution and the mean value of each color channel are similar, adopting an iterative compensation method to enable the middle color channel and the minimum color channel to meet the constraint condition of color loss;
the constraint of the color loss is expressed as follows:
Figure BDA0003654692020000071
the threshold for the color loss constraint is set to 0.02, the compensation formula of optimization step 401) is iterated until convergence by minimizing the color loss constraint, and in other embodiments, may be set to 0.01 or other values between 0.01 and 0.02.
Step 403) adopts the same linear transmission strategy as that of step 3) to expand the dynamic ranges of the compensated middle color channel and the minimum color channel, and then combines the processing of step 3) on the maximum color channel to obtain a color transmission image.
Step 5) in order to accurately estimate the light attenuation related to the wavelength, a maximum attenuation map estimation strategy is adopted to estimate the color channel with the most serious attenuation in the R, G and B three-color channels in the original image of the color distortion underwater image, and the solving process is expressed as follows:
Figure BDA0003654692020000072
where γ and the parameter representing the control of the intensity of the received light are set to 1.2, in other embodiments 1, or other values between 1 and 1.2 may be used.
Step 6) adjusting the detail image of the original image and the color transmission image obtained in step 403) pixel by pixel under the guidance of the maximum attenuation map obtained in step 5) to obtain a color correction image. Wherein the detail image is obtained by a detail sharpening method.
The maximum attenuation map guided fusion process is as follows:
Figure BDA0003654692020000073
wherein,,
Figure BDA0003654692020000074
representing the color transmission image obtained by step 403);
Figure BDA0003654692020000075
representing the maximum attenuation map obtained by step 5);
Figure BDA0003654692020000076
representing a final color corrected image;
d represents a detail image expressed as D c ＝I c -G c *I c ；
The detail image is an image obtained by subtracting gaussian kernel blur from the input image, and represents a convolution operation.
As shown in fig. 2, the present invention provides corrected images and gray histograms for blue-distorted underwater images with other algorithms, and it can be seen from the experimental results that six color correction methods correct blue distortion to some extent, the GE, MR and WGE methods do not correct blue distortion well, the SOG and GW methods correct blue distortion, but the SOG method corrects blue distortion incompletely, and the GW method introduces reddish distortion. The invention effectively corrects blue distortion and improves image visibility and contrast. In terms of histogram distribution, the histogram distribution of the corrected color image of the present invention is more uniform, broad and similar.
As shown in fig. 3, the present invention provides corrected images and gray histograms for green-distorted underwater images with other algorithms, and from experimental results, it can be seen that six color correction methods correct green distortion to some extent, GE and WGE methods do not correct green distortion well, SOG and GW methods correct blue distortion, but they introduce reddish distortion, and MR cannot correct green distortion thoroughly. The invention effectively corrects green distortion and improves image visibility and contrast. In terms of histogram distribution, the histogram distribution of the corrected color image of the present invention is more uniform, broad and similar.
As shown in fig. 4, the present invention provides corrected images and gray histograms for yellow-distorted underwater images with other algorithms, and it can be seen from experimental results that six color correction methods correct yellow distortion to some extent, GE, MR, SOG and WGE methods do not correct yellow distortion well, and GW method introduces local blue distortion. The invention effectively corrects yellow distortion and improves the image visibility and contrast. In terms of histogram distribution, the histogram distribution of the corrected color image of the present invention is more uniform, broad and similar.
As shown in fig. 5, the present invention provides corrected images and gray histograms for bluish-green distorted underwater images with other algorithms, and it can be seen from experimental results that six color correction methods correct bluish-green distortion to some extent, GE and WGE methods do not correct yellow distortion well, GW, MR and SOG methods correct bluish-green distortion, but the correction is incomplete and reddish distortion is introduced. The invention effectively corrects bluish green distortion and improves the image visibility and contrast. In terms of histogram distribution, the histogram distribution of the corrected color image of the present invention is more uniform, broad and similar.
In this embodiment, the experimental results of the different methods are contrasted by the underwater image quality metric index UIQM, and as can be seen from the data in table 1, the GE and WGE methods have values of UIQM greater than the original image for fig. 2, 3 and 5, but lower than the original image for fig. 4. SOG, MR, GW and LACC methods have larger UIQM values for the four images than the original image, while the LACC of the present invention has the highest UIQM value. In summary, the present invention is superior to the comparative method in both subjective and objective assessment.
Figure BDA0003654692020000091
Table 1 UIQM value contrast of corrected images for the method of the present invention and other methods
Finally, it should be noted that the above-mentioned embodiments are only for illustrating the technical scheme of the present invention and are not limiting; while the invention has been described in detail with reference to the preferred embodiments, those skilled in the art will appreciate that: modifications may be made to the specific embodiments of the present invention or equivalents may be substituted for part of the technical features thereof; without departing from the spirit of the invention, it is intended to cover the scope of the invention as claimed.

Claims (3)

1. A local self-adaptive underwater image color correction method is characterized in that: the method comprises the following steps:
step 1) obtaining a color distortion underwater image, decomposing the color distortion underwater image into R, G and B three-color channels, counting the total pixel mean value of each color channel, and redefining the color distortion underwater image as the maximum, middle and minimum three color channels according to the total pixel mean value; the formula for the total pixel mean for each color channel is as follows:
Figure FDA0004245891230000011
wherein H and W represent the height and width of the input image I;
step 2) establishing a minimum color loss criterion based on the redefined three color channels in step 1) and on gray world assumptions, and establishing a color loss term between the redefined three color channels based on the minimum color loss criterion; the formula of the color loss term is as follows:
Figure FDA0004245891230000012
wherein the redefined three color channels are respectively the maximum color channel I l Intermediate color channel I m And minimum color channel I s ，
Figure FDA0004245891230000013
And->
Figure FDA0004245891230000014
Respectively representing redefined three color channels I l 、I m And I s Average pixel value of (a);
step 3) for the largest color channel of the three color channels redefined in step 1), using a linear transmission strategy to expand the dynamic range of the largest color channel;
the linear transmission strategy formula is expressed as follows:
Figure FDA0004245891230000015
wherein,,
Figure FDA0004245891230000016
is I l Is provided;
Figure FDA0004245891230000017
and->
Figure FDA0004245891230000018
Representing minimum and maximum pixel values of the input image, respectively;
Figure FDA0004245891230000019
and->
Figure FDA00042458912300000110
Respectively indicate the stretching range, & lt & gt>
Figure FDA00042458912300000111
And->
Figure FDA00042458912300000112
Set to 0 and 255, respectively;
step 401) for the middle color channel and the smallest color channel of the redefined three color channels, constructing a compensation term between the largest color channel and the middle color channel and between the largest color channel and the smallest color channel, and performing compensation on the middle color channel and the smallest color channel by using the compensation term;
the formula for constructing the compensation term between the maximum color channel and the middle color channel and between the maximum color channel and the minimum color channel is as follows:
Figure FDA0004245891230000021
Figure FDA0004245891230000022
wherein,,
Figure FDA0004245891230000023
and->
Figure FDA0004245891230000024
Respectively represent I m And I s Color compensation channels of (a);
step 402), adopting an iterative compensation method to enable the intermediate color channel and the minimum color channel to meet the constraint condition of color loss; the constraint of the color loss is expressed as follows:
Figure FDA0004245891230000025
the threshold of the color loss constraint is set to 0.01-0.02;
step 403) expanding the dynamic ranges of the compensated middle color channel and the minimum color channel by adopting a linear transmission strategy, and combining the processing of the maximum color channel in step 3) to obtain a color transmission image;
step 5) estimating color channels with the most serious attenuation in R, G and B three-color channels in an original image of the color distortion underwater image by adopting a maximum attenuation map estimation strategy; the solving process of the maximum attenuation map is represented as follows:
Figure FDA0004245891230000026
wherein, gamma and a parameter for controlling the intensity of the received light are set to 1-1.2;
step 6) adjusting the detail image of the original image and the color transmission image obtained in step 403) pixel by pixel under the guidance of the maximum attenuation map obtained in step 5) to obtain a color correction image.
2. The locally adaptive underwater image color correction method of claim 1, wherein: the linear transmission strategy in step 403) is the same formula used for the linear transmission strategy in step 3).
3. The locally adaptive underwater image color correction method of claim 2, characterized in that: in step 6), the maximum attenuation map guided fusion process is as follows:
Figure FDA0004245891230000027
wherein,,
Figure FDA0004245891230000031
representing the color transmission image obtained by step 403);
Figure FDA0004245891230000032
representing the maximum attenuation map obtained by step 5);
Figure FDA0004245891230000033
representing a final color corrected image;
d represents a detail image expressed as D c ＝I c -G c *I c ；
The detail image is an image obtained by subtracting gaussian kernel blur from the input image, and represents a convolution operation.
CN202210555492.5A 2022-05-20 2022-05-20 Locally adaptive underwater image color correction method Active CN114820385B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210555492.5A CN114820385B (en) 2022-05-20 2022-05-20 Locally adaptive underwater image color correction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210555492.5A CN114820385B (en) 2022-05-20 2022-05-20 Locally adaptive underwater image color correction method

Publications (2)

Publication Number Publication Date
CN114820385A CN114820385A (en) 2022-07-29
CN114820385B true CN114820385B (en) 2023-06-23

Family

ID=82517891

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210555492.5A Active CN114820385B (en) 2022-05-20 2022-05-20 Locally adaptive underwater image color correction method

Country Status (1)

Country Link
CN (1) CN114820385B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115861450A (en) * 2022-10-28 2023-03-28 河南科技学院 Piecewise linear stretching underwater image color correction method

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3547639A (en) * 1966-09-01 1970-12-15 Eastman Kodak Co Color-and-tone-correcting separation film
US3644785A (en) * 1968-10-09 1972-02-22 Sveriges Radio Ab Illumination arrangement for recording and/or reproduction in color
CN108416742A (en) * 2018-01-23 2018-08-17 浙江工商大学 Sand and dust degraded image Enhancement Method based on colour cast correction and information loss constraint
CN109671124A (en) * 2018-12-27 2019-04-23 湖南师范大学 A kind of mineral flotation foam image color calibration method and foam color detection system
CN110517327A (en) * 2019-08-30 2019-11-29 大连海事大学 A kind of underwater picture Enhancement Method based on color correction and contrast stretching
CN110689490A (en) * 2019-09-09 2020-01-14 天津大学 Underwater image restoration method based on texture color features and optimized transmittance
US10764471B1 (en) * 2019-09-27 2020-09-01 Konica Minolta Business Solutions U.S.A., Inc. Customized grayscale conversion in color form processing for text recognition in OCR
CN113284061A (en) * 2021-05-17 2021-08-20 大连海事大学 Underwater image enhancement method based on gradient network
CN114418876A (en) * 2022-01-05 2022-04-29 大连海事大学 Underwater image enhancement method based on light scattering characteristics

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7525702B2 (en) * 2004-08-02 2009-04-28 Seiko Epson Corporation Methods and systems for correcting color distortions

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3547639A (en) * 1966-09-01 1970-12-15 Eastman Kodak Co Color-and-tone-correcting separation film
US3644785A (en) * 1968-10-09 1972-02-22 Sveriges Radio Ab Illumination arrangement for recording and/or reproduction in color
CN108416742A (en) * 2018-01-23 2018-08-17 浙江工商大学 Sand and dust degraded image Enhancement Method based on colour cast correction and information loss constraint
CN109671124A (en) * 2018-12-27 2019-04-23 湖南师范大学 A kind of mineral flotation foam image color calibration method and foam color detection system
CN110517327A (en) * 2019-08-30 2019-11-29 大连海事大学 A kind of underwater picture Enhancement Method based on color correction and contrast stretching
CN110689490A (en) * 2019-09-09 2020-01-14 天津大学 Underwater image restoration method based on texture color features and optimized transmittance
US10764471B1 (en) * 2019-09-27 2020-09-01 Konica Minolta Business Solutions U.S.A., Inc. Customized grayscale conversion in color form processing for text recognition in OCR
CN113284061A (en) * 2021-05-17 2021-08-20 大连海事大学 Underwater image enhancement method based on gradient network
CN114418876A (en) * 2022-01-05 2022-04-29 大连海事大学 Underwater image enhancement method based on light scattering characteristics

Also Published As

Publication number Publication date
CN114820385A (en) 2022-07-29

Similar Documents

Publication Publication Date Title
US20060262206A1 (en) Noise reduction method
US7444035B2 (en) Better picture for inexpensive cameras
CN117058026A (en) Underwater image color correction method guided by attenuation map
CN110782407B (en) Single image defogging method based on sky region probability segmentation
CN114820385B (en) Locally adaptive underwater image color correction method
CN110827221A (en) Single image defogging method based on double-channel prior and side window guide filtering
CN115578297A (en) Generalized attenuation image enhancement method for self-adaptive color compensation and detail optimization
CN109118437A (en) A kind of method, storage medium that can handle muddy water image in real time
CN111476744B (en) Underwater image enhancement method based on classification and atmospheric imaging model
WO2020093441A1 (en) Detail processing method and device for image saturation enhancement
CN112488968B (en) Image enhancement method for hierarchical histogram equalization fusion
CN114897735B (en) Locally adaptive underwater image contrast enhancement method
CN111028181B (en) Image enhancement processing method, device, equipment and storage medium
CN116862794A (en) Underwater image processing method based on double compensation and contrast adjustment
CN108765310B (en) Adaptive transmissivity restoration image defogging method based on multi-scale window
JP5327766B2 (en) Memory color correction in digital images
CN116309146A (en) Retinex-based edge-preserving color low-illumination image enhancement method
Bae et al. Gamut-adaptive correction in color image processing
US7570808B2 (en) Better picture for inexpensive cameras
US8416323B2 (en) Noise reduction method and noise reduction apparatus
CN110148188B (en) Method for estimating low-illumination image illumination distribution based on maximum difference image
CN115908179B (en) Underwater image contrast enhancement method based on double priori optimization
CN115861450A (en) Piecewise linear stretching underwater image color correction method
CN117714656A (en) Underwater image color correction method based on colorless reference transfer
CN111292263B (en) Image enhancement method based on color correction and deblurring

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