CN112907474B - Underwater image enhancement method based on background light optimization and gamma transformation - Google Patents
Underwater image enhancement method based on background light optimization and gamma transformation Download PDFInfo
- Publication number
- CN112907474B CN112907474B CN202110199611.3A CN202110199611A CN112907474B CN 112907474 B CN112907474 B CN 112907474B CN 202110199611 A CN202110199611 A CN 202110199611A CN 112907474 B CN112907474 B CN 112907474B
- Authority
- CN
- China
- Prior art keywords
- underwater image
- background light
- image
- channel
- color
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000005457 optimization Methods 0.000 title claims abstract description 12
- 230000009466 transformation Effects 0.000 title claims abstract description 10
- 238000006243 chemical reaction Methods 0.000 claims abstract description 14
- 238000012937 correction Methods 0.000 claims abstract description 8
- 238000002834 transmittance Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 7
- 230000003321 amplification Effects 0.000 claims description 5
- 238000003384 imaging method Methods 0.000 claims description 5
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 5
- 239000003086 colorant Substances 0.000 claims description 4
- 238000011430 maximum method Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 8
- 230000000694 effects Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000000875 corresponding effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 3
- 230000002596 correlated effect Effects 0.000 description 2
- 238000012634 optical imaging Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000000149 argon plasma sintering Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000009365 direct transmission Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Processing Of Color Television Signals (AREA)
- Image Processing (AREA)
Abstract
The application discloses an underwater image enhancement method based on background light optimization and gamma transformation, which belongs to the field of computer vision, and comprises the following steps: defogging the underwater image to obtain a defogged underwater image; performing gamma conversion on the defogged underwater image to obtain an underwater image with improved contrast; color correction is carried out on the underwater image with improved contrast by adopting a main channel pixel maximum value method to obtain an underwater image with balanced color; aiming at the problems of color distortion, color cast and the like of the restored image, the method combining gamma conversion and color correction is utilized to improve the contrast of the image and improve the condition of uneven brightness of the image.
Description
Technical Field
The application relates to the field of computer vision, in particular to an underwater image enhancement method based on background light optimization and gamma transformation.
Background
The dark channel prior method is based on a rule obtained by counting a large number of natural and real images, and is a method for recovering the images by analyzing an image degradation model and solving an imaging model through inverse, and has good effect on defogging the images in a non-sky area. Considering that the propagation mode is different from that in the air, the underwater image enhancement method based on the dark channel prior theory generally introduces attenuation coefficients of water to light with different wavelengths when the transmissivity is estimated, and refines a transmission diagram by using a soft matting algorithm to acquire a smoother image.
For a light source area and a noise point part in an underwater image, the brightness of the three channels is balanced, the color saturation of the area is generally low, and background light exists in the background part of the image.
When the traditional dark channel prior method is applied to the underwater image, the background light estimation error of the underwater image is increased due to the influence of noise in water; and the image restored by the dark channel prior method still has the problems of color distortion and color cast, so that the visual effect is poor, and the restored image is not objective.
Disclosure of Invention
According to the problems existing in the prior art, the application discloses an underwater image enhancement method based on background light optimization and gamma transformation, which comprises the following steps:
s1: defogging the underwater image to obtain a defogged underwater image;
s2: performing gamma conversion on the defogged underwater image to obtain an underwater image with improved contrast;
s3: and carrying out color correction on the underwater image with the improved contrast by adopting a main channel pixel maximum value method to obtain the underwater image with balanced colors.
Further, the defogging process for the underwater image comprises the following steps:
extracting background light of the underwater image by combining the dark channel and the color saturation to obtain real background light of the underwater image, and estimating the transmittance of each channel of the underwater image to obtain the transmittance of the red, green and blue 3 channels of the underwater image, namely completing defogging treatment of the underwater image.
Further, the process of extracting the background light of the underwater image by combining the dark channel and the color saturation to obtain the real background light of the underwater image is as follows:
s1-1: selecting 0.1% of pixel points in front of a dark channel of an underwater image;
s1-2: selecting a point x with highest brightness according to the position of a 0.1% pixel point in front of a dark channel of an underwater image;
s1-3: calculating the color saturation S of the maximum brightness point x, establishing a local window W by taking the point x as the center, and setting a threshold S according to the average saturation in the local window W L ;
S1-4: when S > S L Setting the pixel value of the point x as background light when S is less than or equal to S L And selecting sub-bright pixel points and returning to S1-2.
Further, the imaging model of the underwater image is:
I λ (x)=J λ (x)t λ (x)+B λ,∞ (1-t λ (x)) (2)
wherein I is λ (x) For the observation image obtained, J λ (x) T is the real scene to be restored λ (x) For transmittance, B λ,∞ Is background light.
Further, the saturation S is defined as follows:
S=max x (R,G,B)-min x (R,G,B) (5)
wherein: max (max) x (R,G,B)、min x (R, G, B) are the maximum and minimum values, respectively, of the pixels in the three channels at point x.
Further, the threshold S L The expression of (2) is as follows:
wherein: ρ is a threshold adjustment coefficient,is the average color saturation.
Further, the gamma transformation formula is as follows:
V out =V max (V in /V max ) γ (14)
wherein: v (V) in 、V out Respectively the brightness of the pixels in the input and output images, V max Is the pixel value in the channel with the greatest brightness.
Further, the main channel pixel maximum method comprises the following steps:
s3-1: calculating the maximum pixel values of three color channels of red, blue and green of the underwater image with improved contrast;
s3-2: comparing the maximum pixel values of the red, blue and green color channels, and using the color channel corresponding to the maximum pixel value as the main channel, keeping the main channel unchanged, and using the other two color channels as secondary channels;
s3-3: and amplifying the pixel value of the secondary channel according to an amplification factor, so that the color of the underwater image with improved contrast is balanced.
Further, the amplification factor is defined as follows:
wherein: g min G for amplifying the gain of the lowest channel of pixel values med Centering the gain of the channel for amplifying the pixel values, R max ,G max ,B max Respectively, the maximum value of pixels in red, green and blue three channels.
Due to the adoption of the technical scheme, the underwater image enhancement method based on the background light optimization and the gamma transformation is mainly used for solving the problems of underwater image blurring, low contrast, color distortion and the like, is particularly suitable for the occasion of recovering an underwater real scene from a degraded image, and provides reliable support for feature detection, identification, matching and the like of the underwater image; the application adopts an improved background light estimation method, and utilizes the color saturation of the neighborhood of a candidate point to measure whether the point can be used as the background light of the whole image, thereby reducing the estimation error and improving the image quality; aiming at the problems of color distortion, color cast and the like of the restored image, the method combining gamma conversion and color correction is utilized to improve the contrast of the image and improve the condition of uneven brightness of the image; the method introduces a local average color saturation method based on a dark channel priori theory, combines the global background light of the brightness estimation image, improves the accuracy of background light estimation, considers the characteristic of light propagation under water, combines the attenuation rate estimation of light in water to respectively solve the transmittance of different channels of the underwater image, and improves the restoration quality of the underwater image.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to the drawings without inventive effort to those skilled in the art.
FIG. 1 is a schematic view of underwater optical imaging;
FIG. 2 is a schematic diagram of a partial tie color saturation calculation;
FIG. 3 is a flow chart of dark channel backlight selection in combination with color saturation;
fig. 4 (a) is an original picture; (b) The method is an effect diagram of the traditional DCP method after the original picture is processed; (c) The method is an effect graph after the original picture is processed.
Detailed Description
In order to make the technical scheme and advantages of the present application more clear, the technical scheme in the embodiment of the present application is clearly and completely described below with reference to the accompanying drawings in the embodiment of the present application:
the application designs an underwater image enhancement method based on background light optimization and gamma conversion, which is an underwater image restoration method combining an improved dark channel prior algorithm and gamma conversion, improves the accuracy of background light estimation by considering neighborhood pixel saturation information so as to realize the defogging function of an underwater image, and then combines gamma conversion and color correction to improve the contrast of the image so as to restore a real underwater image.
An underwater image enhancement method based on background light optimization and gamma transformation comprises the following steps:
s1: defogging the underwater image to obtain a defogged underwater image;
s2: performing gamma conversion on the defogged underwater image to obtain an underwater image with improved contrast;
s3: and carrying out color correction on the underwater image with the improved contrast by adopting a main channel pixel maximum value method to obtain the underwater image with balanced colors.
Further, the defogging process for the underwater image comprises the following steps:
extracting background light of the underwater image by combining the dark channel and the color saturation to obtain real background light of the underwater image, and estimating the transmittance of each channel of the underwater image to obtain the transmittance of the red, green and blue 3 channels of the underwater image, namely completing defogging treatment of the underwater image.
Typically, a complete underwater image is produced by direct transmission E D (x) Forward scatter E F (x) Backscattering E B (x) Three parts are formed, fig. 1 is a schematic view of underwater optical imaging, and the light intensity E received by a pixel point x in a camera λ (x) The method comprises the following steps:
E λ (x)=E D (x)+E F (x)+E B (x) (1)
neglecting image blurring caused by forward scattering, the underwater image imaging model is:
I λ (x)=J λ (x)t λ (x)+B λ,∞ (1-t λ (x)) (2)
wherein I is λ (x) For the observation image obtained, J λ (x) T is the real scene to be restored λ (x) For transmittance, B λ,∞ Is background light.
Dark channel prior theory uses dark pixels in an image to describe the projection information of fog and light, and the main task of restoring the image is to estimate the background light and the transmissivity of the image.
Firstly, background light is estimated:
the dark channel of an underwater image refers to the minimum value of the light intensity in a certain area in the image expressed as:
wherein Ω (x) is a local window centered on x, I λ (y) is the pixel value of a color channel in the image. According to the dark channel prior theory, in a natural image of a clear non-fog non-sky area, the dark channel value in a certain window area approaches to 0, namely:
J dark →0 (4)
the traditional dark channel prior method selects the first 0.1% of pixel points with the maximum brightness in the dark channel, and searches the point with the highest brightness value in the image as background light according to the positions of the points, but the underwater image is blurred due to uneven underwater illumination and dark overall brightness, the brightness of the dark channel is overall higher, the underwater image is seriously influenced by noise in water, the selection of the background light is easily disturbed, and an incorrect estimated value is obtained.
In order to ensure the accuracy of background light selection, the application provides an improved background light extraction method, which combines the characteristics of high brightness and color saturation of background light to judge whether candidate points are background light, and extracts the background light of an underwater image by combining a dark channel and the color saturation, wherein the process of obtaining the actual background light of the underwater image is as follows:
s1-1: selecting 0.1% of pixel points in front of a dark channel of an underwater image;
s1-2: selecting a point x with highest brightness according to the position of a 0.1% pixel point in front of a dark channel of an underwater image;
s1-3: calculating the color saturation S of the maximum brightness point x, establishing a local window W by taking the point x as the center, and setting a threshold S according to the average saturation in the local window W L ;
S1-4: when S > S L Setting the pixel value of the point x as background light when S is less than or equal to S L And selecting sub-bright pixel points and returning to S1-2.
The color saturation S of the present application is defined as follows:
S=max x (R,G,B)-min x (R,G,B) (5)
max in formula (5) x (R,G,B)、min x (R, G, B) are the maximum and minimum values of the pixels in the three channels at point x, respectively;
in formula (6): omega 1 、ω 2 The length and width of window W are respectively, and omega is taken in the application 1 =ω 2 =3,S i Color saturation at point i for the pixel;
s in (7) L For a preset threshold, ρ is a threshold adjustment coefficient.
When the saturation of the central pixel point in the window W is lower than the preset threshold, the point is considered to have no characteristic of the background light and is ignored, the point with sub-bright brightness in the dark channel is selected as the candidate background light, the steps are repeated until the saturation of the candidate point is higher than the preset saturation, the real background light is obtained, and a dark channel background light selection flow chart combining the color saturation is shown in fig. 3.
After obtaining the real background light of the underwater image, the transmittance t λ Estimation is carried out, and the method is obtained according to an underwater image imaging model (2) and an priori conditional formula (4):
since the attenuation coefficient of red light in water is the largest, the transmission of the red channel in an underwater image is the smallest, so the transmission estimated a priori using the dark channel is the transmission of the red channel:
after the transmissivity of the red channel is obtained, the transmissivity of the other two color channels is estimated; the inverse relation between the transmissivity of a pixel in the photographed underwater image and the distance d between the pixel and the camera and the attenuation coefficient eta of the corresponding wave band is expressed as follows:
since the distance d between the pixel point and the camera in the three channels is the same, the transmittance of different channels is solved by the ratio of the attenuation coefficients of different color channels, namely:
wherein t is λ (x) For the transmittance of the lambda channel at pixel point x, eta λ Is the attenuation coefficient of the λ channel, (λ=r, G, B).
In an underwater environment, the scattering rate b of the image global background light in water is positively correlated, and the attenuation rate of the image global background light in water is negatively correlated, namely:
and the relation between the light scattering rate and the wavelength is shown as follows:
b(λ)=(-0.00113λ+1.62517)b(λ c ) (13)
in the formula (13), lambda represents the wavelength lambda c For reference wavelength, the application selects the wavelengths of red, green and blue to be 620 nm, 540 nm and 450nm respectively. Thus, the background light of each channel obtained by estimation comprises three channel values, namely, B= [ Br, bg, bb]Carrying out formula (12) and solving by combining formula (13) to obtain the ratio of the scattering rate of each channel, and solving by formula (11) to obtain the transmittance of G, B channelAnd solving the transmittance of three channels.
Although the image restored by the dark channel method is clearer, the contrast ratio still has a larger improvement space, based on the fact that the image contrast ratio is further improved by introducing gamma conversion, the image is more layered, and a gamma conversion formula of the image used in the application is defined as follows:
V out =V max (V in /V max ) γ (14)
v in in 、V out Respectively the brightness of the pixels in the input and output images, V max Is the pixel value in the channel with the greatest brightness.
And finally, performing color correction on the restored underwater image, balancing the colors of all channels, and improving the overall visual effect of the underwater image.
The main channel pixel maximum method comprises the following steps:
s3-1: calculating the maximum pixel values of three color channels of red, blue and green of the underwater image with improved contrast;
s3-2: comparing the maximum pixel values of the red, blue and green color channels, and using the color channel corresponding to the maximum pixel value as the main channel, keeping the main channel unchanged, and using the other two color channels as secondary channels;
s3-3: and amplifying the pixel value of the secondary channel according to an amplification factor, so that the color of the underwater image with improved contrast is balanced.
Further, the magnification factor g min 、g med The definition is as follows:
applying magnification factors to the other two sub-channels to obtain balanced images:
wherein I is min (R max ,G max ,B max ) Color channel with minimum pixel maximum value, I med (R max ,G max ,B max ) Color channel centered for pixel maximum, I min 、I med The pixel values corresponding to the two color channels after being balanced.
Fig. 4 (a) is an original picture; (b) The method is an effect diagram of the traditional DCP method after the original picture is processed; (c) In order to adopt the method to process the effect graph of the original picture, the experimental result shows that the contrast of the image enhanced by the method is obviously improved, and the visual effect is better.
The foregoing is only a preferred embodiment of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art, who is within the scope of the present application, should make equivalent substitutions or modifications according to the technical scheme of the present application and the inventive concept thereof, and should be covered by the scope of the present application.
Claims (4)
1. An underwater image enhancement method based on background light optimization and gamma transformation is characterized by comprising the following steps of: the method comprises the following steps:
s1: defogging the underwater image to obtain a defogged underwater image;
s2: performing gamma conversion on the defogged underwater image to obtain an underwater image with improved contrast;
s3: performing color correction on the underwater image with improved contrast by adopting a main channel pixel maximum value method to obtain an underwater image with balanced colors;
the defogging process for the underwater image comprises the following steps:
extracting background light of the underwater image by combining the dark channel and the color saturation to obtain real background light of the underwater image, and estimating the transmittance of each channel of the underwater image to obtain the transmittance of 3 channels of the underwater image, namely finishing defogging treatment of the underwater image;
the process of extracting the background light of the underwater image by combining the dark channel and the color saturation to obtain the real background light of the underwater image is as follows:
s1-1: selecting 0.1% of pixel points in front of a dark channel of an underwater image;
s1-2: selecting a point x with highest brightness according to the position of a 0.1% pixel point in front of a dark channel of an underwater image;
s1-3: calculating the color saturation S of the maximum brightness point x, establishing a local window W by taking the point x as the center, and setting a threshold S according to the average saturation in the local window W L ;
S1-4: when S > S L Setting the pixel value of the point x as background light when S is less than or equal to S L Selecting sub-bright pixel points and returning to S1-2;
the saturation S is defined as follows:
wherein: max (max) x (R,G,B)、min x (R, G, B) are the maximum and minimum values of the pixels in the three channels at point x, respectively;
the threshold S L The expression of (2) is as follows:
wherein: ρ is a threshold adjustment coefficient,is the average color saturation;
the main channel pixel maximum method comprises the following steps:
s3-1: calculating the maximum pixel values of three color channels of red, blue and green of the underwater image with improved contrast;
s3-2: comparing the maximum pixel values of the red, blue and green color channels, and using the color channel corresponding to the maximum pixel value as the main channel, keeping the main channel unchanged, and using the other two color channels as secondary channels;
s3-3: and amplifying the pixel value of the secondary channel according to an amplification factor, so that the color of the underwater image with improved contrast is balanced.
2. The method for underwater image enhancement for background light optimization and gamma conversion according to claim 1, wherein: the imaging model of the underwater image is as follows:
I λ (x)=J λ (x)t λ (x)+B λ,∞ (1-t λ (x)) (2)
wherein I is λ (x) For the observation image obtained, J λ (x) T is the real scene to be restored λ (x) For transmittance, B λ,∞ Is background light.
3. The method for underwater image enhancement for background light optimization and gamma conversion according to claim 1, wherein: the gamma transformation formula is as follows:
V out =V max (V in /V max ) γ (14)
wherein: v (V) in 、V out Respectively the brightness of the pixels in the input and output images, V max Is the pixel value in the channel with the greatest brightness.
4. The method for underwater image enhancement for background light optimization and gamma conversion according to claim 1, wherein: the amplification factor is defined as follows:
wherein: g min G for amplifying the gain of the lowest channel of pixel values med Centering the gain of the channel for amplifying the pixel values, R max ,G max ,B max Respectively, the maximum value of pixels in red, green and blue three channels.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110199611.3A CN112907474B (en) | 2021-02-22 | 2021-02-22 | Underwater image enhancement method based on background light optimization and gamma transformation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110199611.3A CN112907474B (en) | 2021-02-22 | 2021-02-22 | Underwater image enhancement method based on background light optimization and gamma transformation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112907474A CN112907474A (en) | 2021-06-04 |
CN112907474B true CN112907474B (en) | 2023-08-25 |
Family
ID=76124322
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110199611.3A Active CN112907474B (en) | 2021-02-22 | 2021-02-22 | Underwater image enhancement method based on background light optimization and gamma transformation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112907474B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114119383B (en) * | 2021-09-10 | 2024-04-26 | 大连海事大学 | Underwater image restoration method based on multi-feature fusion |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106780368A (en) * | 2016-11-24 | 2017-05-31 | 天津大学 | A kind of underwater picture Enhancement Method based on foreground model |
CN108537756A (en) * | 2018-04-12 | 2018-09-14 | 大连理工大学 | Single image to the fog method based on image co-registration |
CN108564543A (en) * | 2018-04-11 | 2018-09-21 | 长春理工大学 | A kind of underwater picture color compensation method based on electromagnetic theory |
CN108765342A (en) * | 2018-05-30 | 2018-11-06 | 河海大学常州校区 | A kind of underwater image restoration method based on improvement dark |
CN110782407A (en) * | 2019-10-15 | 2020-02-11 | 北京理工大学 | Single image defogging method based on sky region probability segmentation |
-
2021
- 2021-02-22 CN CN202110199611.3A patent/CN112907474B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106780368A (en) * | 2016-11-24 | 2017-05-31 | 天津大学 | A kind of underwater picture Enhancement Method based on foreground model |
CN108564543A (en) * | 2018-04-11 | 2018-09-21 | 长春理工大学 | A kind of underwater picture color compensation method based on electromagnetic theory |
CN108537756A (en) * | 2018-04-12 | 2018-09-14 | 大连理工大学 | Single image to the fog method based on image co-registration |
CN108765342A (en) * | 2018-05-30 | 2018-11-06 | 河海大学常州校区 | A kind of underwater image restoration method based on improvement dark |
CN110782407A (en) * | 2019-10-15 | 2020-02-11 | 北京理工大学 | Single image defogging method based on sky region probability segmentation |
Non-Patent Citations (2)
Title |
---|
何笑 ; 吐尔洪江・阿布都克力木 * |
融合伽马变换与Retinex的彩色水下图像增强算法;何笑;吐尔洪江・阿布都克力木;贺欢;;科技视界(第03期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN112907474A (en) | 2021-06-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Gao et al. | Sand-dust image restoration based on reversing the blue channel prior | |
KR101328741B1 (en) | Apparatus and method for image enhancement using color channel | |
CN110570360B (en) | Retinex-based robust and comprehensive low-quality illumination image enhancement method | |
CN107527325B (en) | Monocular underwater vision enhancement method based on dark channel priority | |
CN107886486A (en) | Based on dark channel prior and variation Retinex underwater picture Enhancement Methods | |
CN110689490A (en) | Underwater image restoration method based on texture color features and optimized transmittance | |
CN107705258B (en) | Underwater image enhancement method based on three-primary-color combined pre-equalization and deblurring | |
WO2009091152A2 (en) | Color recovery method and system | |
CN109658343B (en) | Underwater image enhancement method combining color conversion and adaptive exposure | |
CN108133462B (en) | Single image restoration method based on gradient field region segmentation | |
CN111861896A (en) | UUV-oriented underwater image color compensation and recovery method | |
Peng et al. | Single image restoration using scene ambient light differential | |
Mathur et al. | Enhancement of underwater images using white balancing and Rayleigh-stretching | |
CN112488948A (en) | Underwater image restoration method based on black pixel point estimation backscattering | |
CN112907474B (en) | Underwater image enhancement method based on background light optimization and gamma transformation | |
CN110782400B (en) | Self-adaptive illumination uniformity realization method and device | |
Pei et al. | Underwater images enhancement by revised underwater images formation model | |
CN112825189B (en) | Image defogging method and related equipment | |
CN110852971A (en) | Video defogging method based on dark channel prior and Retinex and computer program product | |
CN116757949A (en) | Atmosphere-ocean scattering environment degradation image restoration method and system | |
Zhang et al. | A two-stage underwater image enhancement method | |
CN113379631B (en) | Image defogging method and device | |
CN110852957A (en) | Rapid image defogging method based on retina characteristics | |
CN112529802B (en) | Atmospheric scattering degraded image recovery method based on scattering coefficient ratio estimation | |
Deluxni et al. | Underwater Image Enhancement based on White Patch of Color Correction with Dark Channel Prior |
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 |