CN111325690A - Self-adaptive underwater image enhancement method based on differential evolution algorithm - Google Patents
Self-adaptive underwater image enhancement method based on differential evolution algorithm Download PDFInfo
- Publication number
- CN111325690A CN111325690A CN202010104677.5A CN202010104677A CN111325690A CN 111325690 A CN111325690 A CN 111325690A CN 202010104677 A CN202010104677 A CN 202010104677A CN 111325690 A CN111325690 A CN 111325690A
- Authority
- CN
- China
- Prior art keywords
- image
- underwater
- enhancement
- detail
- adjusted
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000005457 optimization Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000011156 evaluation Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000006870 function Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000010420 art technique Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a self-adaptive underwater image enhancement method based on a differential evolution algorithm, which comprises the steps of carrying out histogram equalization operation on an underwater original image to obtain a color adjustment image, carrying out detail sharpening processing on the color adjustment image to obtain a detail enhancement image, carrying out brightness enhancement on the detail enhancement image based on a dark channel prior method, and carrying out defogging operation on a reverse image of the detail enhancement image to obtain an underwater image with enhanced brightness; taking the underwater image evaluation index as a fitness function of an optimization algorithm, selecting parameters to be adjusted, carrying out feedback adjustment on the parameters to be adjusted in the processes of color adjustment, detail enhancement and brightness enhancement of the original underwater image through the fitness function of the optimization algorithm, and circularly executing an image processing process until the stopping condition of the optimization algorithm is reached, thereby obtaining the underwater enhanced image according to the optimal parameters to be adjusted.
Description
Technical Field
The invention relates to the technical field of underwater image restoration, in particular to a self-adaptive underwater image enhancement method based on a differential evolution algorithm.
Background
With the continuous development of marine research, underwater image processing has become a relevant research in a wide range of fields, such as underwater telemetry, deep sea exploration, and the like. However, underwater images are susceptible to blurring due to absorption and scattering effects in water, resulting in decreased contrast and graying of the color. This can compromise computer vision applications, especially those that are critical to safety. Researchers have investigated ways to convert images into a better representation or to improve their visual appearance in order to benefit from subsequent image processing. Some prior art techniques utilize multiple images or depth information to improve image quality. Still other techniques use histogram equalization-based or tone mapping-based techniques to modify an image to be visually acceptable. These techniques have proven their effectiveness in improving medical images, satellite images, aerial images, and even real-life photographs, which are poor in contrast and noise. As for the enhancement of underwater images, several model-based methods have been studied based on methods such as transfer function, dictionary learning, depth estimation, and wavelength compensation. Multiple scattering is unavoidable due to the turbid nature of water. Thus, the prior art generally lacks the requirement to provide sufficient robustness and imperceptibility. Although the deep neural network performs well on the image enhancement problem, it is very sensitive to the setting of its hyper-parameters. Finally, the performance of the enhancement algorithm is often affected by many hyper-parameters, which are unknown and difficult to select in practice. Despite the large number of advanced enhancement methods that have been studied using empirical rules, it is difficult to find excellent agreement of experience between good enhancement performance and hyper-parameter settings.
Disclosure of Invention
According to the problems in the prior art, the invention discloses a self-adaptive underwater image enhancement method based on a differential evolution algorithm, which comprises the following steps:
performing histogram equalization operation on an underwater original image to obtain a color adjustment image, performing detail sharpening processing on the color adjustment image to obtain a detail enhancement image, performing brightness enhancement on the detail enhancement image based on a dark channel prior method, and performing defogging operation on a reverse image of the detail enhancement image to obtain an underwater image with enhanced brightness;
taking the underwater image evaluation index as a fitness function of an optimization algorithm, selecting parameters to be adjusted, carrying out feedback adjustment on the parameters to be adjusted in the processes of color adjustment, detail enhancement and brightness enhancement of the original underwater image through the fitness function of the optimization algorithm, and circularly executing an image processing process until the stopping condition of the optimization algorithm is reached, thereby obtaining the underwater enhanced image according to the optimal parameters to be adjusted.
Further, when the detail sharpening process is performed on the color adjustment image, the detail enhanced image is defined as:
Dmaxis an enhanced upper limit, U is the high frequency of J greater than the threshold, JcRepresenting a color-adjusted image, J representing a detail-enhanced image, the detail enhancement matrix being:
dis (p) and vis (p) represent atmospheric light constraints and visibility constraints respectively,
representing element-by-element multiplication.
Wherein S and
respectively representing the weber luminous contrast and its average,
l is the brightness of the image, LB is the background brightness of the image,
is the average value of C, k1And k2Representing a weighting factor.
Further, a minimum threshold V of the image pixel is selectedminMaximum threshold value VmaxA weight factor k1And k2And as a parameter to be adjusted of the optimization algorithm, the cutoff condition of the optimization algorithm is the maximum iteration number.
Due to the adoption of the technical scheme, the self-adaptive underwater image enhancement method based on the differential evolution algorithm provided by the invention provides a more comprehensive image enhancement framework, and can meet the requirements of underwater image enhancement. The color and brightness of the underwater original image are adjusted by an image depth-based method, and meanwhile, the detail information of the image is enhanced, so that the observability of the image can be improved, and the low-quality underwater image is obviously improved; meanwhile, in order to reduce the intervention of manual parameter setting, an optimization algorithm is adopted to carry out self-adaptive parameter adjustment so as to achieve the optimal effect of the image and obtain better visual appearance; compared with a deep learning-based method, the method does not need paired training data, and programming implementation is easy and is worthy of popularization and application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
In order to make the technical solutions and advantages of the present invention clearer, the following describes the technical solutions in the embodiments of the present invention clearly and completely with reference to the drawings in the embodiments of the present invention:
as shown in fig. 1, a self-adaptive underwater image enhancement method based on a differential evolution algorithm specifically includes the following steps:
s1, carrying out histogram equalization operation on the underwater original image to obtain a color adjustment image: firstly, counting the minimum value J of each channel of an underwater original image Jc minAnd maximum value
Then all pixels of the image are sorted, and a minimum threshold value V is setminAnd a maximum threshold value VmaxPixels that are smaller or larger than the threshold are adjusted.
End use formula
A color adjusted image can be obtained.
S2, processing the color adjustment image by a detail sharpening method to obtain a detail enhanced image, which comprises the following specific steps: the detail-enhanced image is defined as:
Dmaxis an enhanced upper limit, U is the high frequency of J greater than the threshold, JcRepresenting a color-adjusted image, J representing a detail-enhanced image, the detail enhancement matrix being:
dis (p) and vis (p) represent atmospheric light constraints and visibility constraints respectively,
wherein S and
respectively representing the weber luminous contrast and its average,
l is the brightness of the image, LB is the background brightness of the image,
is the average value of C, k1And k2Representing a weighting factor.
And S3, brightness enhancement is carried out on the detail enhanced image based on the Dark Channel Prior (DCP), and the underwater image after brightness enhancement can be obtained by carrying out defogging operation on the reverse image of the detail enhanced image. We use Dark Channel Prior (DCP) to improve low light. By inputting the inverted image, wherein the high-brightness area corresponds to the dark channel in J (p), since the inverted image also satisfies the physical model, the high brightness can be weakened through the defogging method, and the underwater enhanced image with enhanced brightness is obtained.
S4: taking the underwater image evaluation index as a fitness function of an optimization algorithm, selecting parameters to be adjusted, carrying out feedback adjustment on the parameters to be adjusted in the processes of color adjustment, detail enhancement and brightness enhancement of the original underwater image through the fitness function of the optimization algorithm, and circularly executing an image processing process until the stopping condition of the optimization algorithm is reached, thereby obtaining the underwater enhanced image according to the optimal parameters to be adjusted.
Wherein the parameter to be adjusted is the minimum threshold value V of the image pixelminMaximum threshold value VmaxA weight factor k1And k2(ii) a The cutoff condition of the optimization algorithm is the maximum iteration number.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (4)
1. A self-adaptive underwater image enhancement method based on a differential evolution algorithm is characterized by comprising the following steps:
performing histogram equalization operation on an underwater original image to obtain a color adjustment image, performing detail sharpening processing on the color adjustment image to obtain a detail enhancement image, performing brightness enhancement on the detail enhancement image based on a dark channel prior method, and performing defogging operation on a reverse image of the detail enhancement image to obtain an underwater image with enhanced brightness;
taking the underwater image evaluation index as a fitness function of an optimization algorithm, selecting parameters to be adjusted, carrying out feedback adjustment on the parameters to be adjusted in the processes of color adjustment, detail enhancement and brightness enhancement of the original underwater image through the fitness function of the optimization algorithm, and circularly executing an image processing process until the stopping condition of the optimization algorithm is reached, thereby obtaining the underwater enhanced image according to the optimal parameters to be adjusted.
2. The underwater image enhancement method of claim 1, further characterized by: when detail sharpening is carried out on the color adjustment image, the detail enhanced image is defined as:
Dmaxis an enhanced upper limit, U is the high frequency of J greater than the threshold, JcRepresenting a color-adjusted image, J representing a detail-enhanced image, the detail enhancement matrix being: q (p) ═ dis (p). Vis (p), Dis (p) and Vis (p) represent atmospheric light constraints and visibility constraints, respectively,
representing element-by-element multiplication.
Wherein S and
respectively representing the weber luminous contrast and its average,
l is the brightness of the image, LB is the background brightness of the image,
is the average value of C, k1And k2Representing a weighting factor.
3. The underwater image enhancement method according to claim 2, further characterized by: selecting minimum threshold V of image pixelminMaximum threshold value VmaxA weight factor k1And k2As the parameter to be adjusted of the optimization algorithm.
4. The underwater image enhancement method of claim 3, further characterized by: the cutoff condition of the optimization algorithm is the maximum iteration number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010104677.5A CN111325690B (en) | 2020-02-20 | 2020-02-20 | Self-adaptive underwater image enhancement method based on differential evolution algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010104677.5A CN111325690B (en) | 2020-02-20 | 2020-02-20 | Self-adaptive underwater image enhancement method based on differential evolution algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111325690A true CN111325690A (en) | 2020-06-23 |
| CN111325690B CN111325690B (en) | 2023-08-22 |
Family
ID=71168814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010104677.5A Active CN111325690B (en) | 2020-02-20 | 2020-02-20 | Self-adaptive underwater image enhancement method based on differential evolution algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111325690B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022027197A1 (en) * | 2020-08-03 | 2022-02-10 | SZ DJI Technology Co., Ltd. | Systems and methods for processing image |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104240194A (en) * | 2014-04-29 | 2014-12-24 | 西南科技大学 | Low-light-level image enhancement algorithm based on parabolic function |
| CN104376543A (en) * | 2014-11-28 | 2015-02-25 | 湖北工业大学 | Method for adaptively enhancing images on basis of cuckoo search algorithm |
| 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 |
| CN110689587A (en) * | 2019-10-11 | 2020-01-14 | 大连海事大学 | Underwater image enhancement method based on color correction and detail enhancement |
-
2020
- 2020-02-20 CN CN202010104677.5A patent/CN111325690B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104240194A (en) * | 2014-04-29 | 2014-12-24 | 西南科技大学 | Low-light-level image enhancement algorithm based on parabolic function |
| CN104376543A (en) * | 2014-11-28 | 2015-02-25 | 湖北工业大学 | Method for adaptively enhancing images on basis of cuckoo search algorithm |
| 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 |
| CN110689587A (en) * | 2019-10-11 | 2020-01-14 | 大连海事大学 | Underwater image enhancement method based on color correction and detail enhancement |
Non-Patent Citations (5)
| Title |
|---|
| QIAN WANG 等: ""A Novel Algorithm for Automatic Dendritic Spine Detection in Microscope Images"", 《2014 INTERNATIONAL CONFERENCE ON ELECTRICAL AND ELECTRONIC ENGINEERING(EEE 2014)》 * |
| 张永萍: ""基于光照过强过弱条件下的图像增强研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 李阳: ""水下目标探测中的侧扫声纳图像处理技术研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 王明威 等: ""基于差分进化的图像自适应增强方法"", 《湖北民族学院学报( 自然科学版)》 * |
| 赵宏宇: ""雾天图像清晰化技术的研究"", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022027197A1 (en) * | 2020-08-03 | 2022-02-10 | SZ DJI Technology Co., Ltd. | Systems and methods for processing image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111325690B (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112288658B (en) | Underwater image enhancement method based on multi-residual joint learning | |
| Zhang et al. | Enhancing underwater image via color correction and bi-interval contrast enhancement | |
| CN110599409B (en) | Convolutional neural network image denoising method based on multi-scale convolutional groups and parallel | |
| CN109493303B (en) | Image defogging method based on generation countermeasure network | |
| CN110232661B (en) | Low-illumination color image enhancement method based on Retinex and convolutional neural network | |
| CN109872285B (en) | Retinex low-illumination color image enhancement method based on variational constraint | |
| CN108416745B (en) | Image self-adaptive defogging enhancement method with color constancy | |
| CN107798661B (en) | Self-adaptive image enhancement method | |
| CN110288550B (en) | Single-image defogging method for generating countermeasure network based on priori knowledge guiding condition | |
| CN112767279B (en) | Underwater image enhancement method for generating countermeasure network based on discrete wavelet integration | |
| CN110136075A (en) | It is a kind of to recycle the remote sensing image defogging method for generating confrontation network based on edge sharpening | |
| CN116188325A (en) | Image denoising method based on deep learning and image color space characteristics | |
| CN114511480A (en) | Underwater image enhancement method based on fractional order convolution neural network | |
| Zhao et al. | Enhancing underwater imagery via latent low-rank decomposition and image fusion | |
| CN111325690A (en) | Self-adaptive underwater image enhancement method based on differential evolution algorithm | |
| CN111563854B (en) | Particle swarm optimization method for underwater image enhancement processing | |
| CN117351340A (en) | Underwater image enhancement algorithm based on double-color space | |
| Park et al. | Enhancing underwater color images via optical imaging model and non-local means denoising | |
| CN108133467B (en) | Underwater image enhancement system and method based on particle calculation | |
| Marasakatla et al. | Under Water Image Enhancement Using CNN | |
| Zhou et al. | Underwater image enhancement via complementary advantage fusion of global and local contrast | |
| Du et al. | RRANet: low-light image enhancement based on Retinex theory and residual attention | |
| Hong et al. | Multi-scale iterative network for underwater image restoration | |
| Xu et al. | Quaternion Quasi-Chebyshev Non-local Means for Color Image Denoising | |
| Qian et al. | Underwater image enhancement via efficient generative adversarial network |
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 |