CN116993636A - Image enhancement method and device for underground low-illumination deep stratum empty area - Google Patents
Image enhancement method and device for underground low-illumination deep stratum empty area Download PDFInfo
- Publication number
- CN116993636A CN116993636A CN202310843877.6A CN202310843877A CN116993636A CN 116993636 A CN116993636 A CN 116993636A CN 202310843877 A CN202310843877 A CN 202310843877A CN 116993636 A CN116993636 A CN 116993636A
- Authority
- CN
- China
- Prior art keywords
- image
- enhanced
- enhancement
- images
- enhancing
- 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 54
- 238000005286 illumination Methods 0.000 title claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 19
- 230000002708 enhancing effect Effects 0.000 claims abstract description 16
- 238000005516 engineering process Methods 0.000 claims abstract description 10
- 238000013135 deep learning Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 230000002146 bilateral effect Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims 1
- 239000011800 void material Substances 0.000 claims 1
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003595 spectral effect Effects 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
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/10—Image enhancement or restoration using non-spatial domain filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20028—Bilateral filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an image enhancement method for an underground low-illumination deep stratum empty area, which comprises the following steps: processing the image by utilizing a multi-frame stacking technology to obtain a high-resolution image, converting the image from a space domain to a frequency domain, and reconstructing and enhancing the image by CNN to obtain an enhanced image M1; decomposing the high-resolution image to obtain red, green and blue RGB component images, converting the image from an RGB space to an HSV space, and carrying out contrast enhancement on the HSV space image to obtain an enhanced image M2; enhancing the HSV space image through CNN to obtain an enhanced image M3; enhancing the RGB component image through CNN to obtain an enhanced image M4; and merging the enhanced images M1, M2, M3 and M4, and obtaining weighted average coefficients of the enhanced images M1, M2, M3 and M4 by using a deep learning method to obtain a final enhanced image. The weighted and combined image covers the advantages of various enhancement methods, can effectively improve the contrast and quality of the image, and comprehensively displays the characteristics of the image.
Description
Technical Field
The invention relates to the technical field of image enhancement, in particular to an image enhancement method and device for an underground low-illumination deep stratum empty area.
Background
Today, the technology is developing at a high speed, various devices are being used more and more, and video images are being applied more and more widely. Because of the complexity of the conditions, especially the video image formed under night conditions, has low brightness, high noise and low contrast, it is difficult to achieve the ideal acquisition effect and acquire the desired information. It is therefore necessary to enhance the image formed under these low light conditions. The purpose of low-light image enhancement is to highlight critical information, exclude interference information as much as possible, and sharpen or enhance the brightness of an image that is originally unclear or has lower brightness. Under low light conditions, the captured image is poor in quality due to uncertainty of light conditions, and noise is mixed in the captured image to cause serious reduction of contrast and brightness, so that details of dark areas of the image are affected, and color deviation occurs.
According to different enhancement algorithm designs, the current low-light image enhancement algorithm is mainly divided into a traditional low-light image enhancement algorithm and a low-light image enhancement algorithm based on deep learning. The conventional enhancement method mainly processes pixels of an image, so as to improve contrast, brightness and noise of the image. However, the method cannot pay attention to the demand relation of the low-illumination image on illumination, and meanwhile ignores the internal context information, so that the phenomena of image color distortion and high noise are generated.
Disclosure of Invention
In order to solve the problems, the invention provides an image enhancement method for a subsurface low-illumination deep stratum empty area, which comprises the following steps:
s1, acquiring an original image by using a multifunctional camera;
s2, processing the obtained original image by utilizing a multi-frame stacking technology to obtain a high-resolution image;
s3, carrying out Fourier transformation on the high-resolution image in the S2, converting the image from a space domain to a frequency domain, carrying out enhancement pretreatment on the image converted to the frequency domain, and carrying out image reconstruction and enhancement on the image subjected to the enhancement pretreatment through CNN to obtain an enhanced image M1; decomposing the high-resolution image in the step S2 to obtain red, green and blue RGB component images, enhancing the details of the RGB component images by using filters with different scales, reconstructing the images, converting the reconstructed images from the RGB space to the HSV space, and carrying out contrast enhancement processing on the HSV space images to obtain an enhanced image M2; performing image enhancement on the HSV space image through CNN to obtain an enhanced image M3; performing image enhancement on the RGB component image through CNN to obtain an enhanced image M4;
s4, obtaining weighted average coefficients of the enhanced images M1, M2, M3 and M4 by using a deep learning method, and combining the enhanced images M1, M2, M3 and M4 to obtain a final enhanced image.
Further, in step S2, noise and jitter are eliminated by calculating the average value of the images of the multi-frame stack in the process of processing the acquired original image by the multi-frame stack technique.
Further, in step S3, the specific steps of performing the enhancement preprocessing on the image converted into the frequency domain are as follows:
(1) Performing self-adaptive histogram equalization on the image converted into the frequency domain to obtain an equalized image;
(2) Processing edges and textures of the equalized image through bilateral filtering to obtain a detail-preserved image;
(3) And decomposing the image with the reserved details into a plurality of areas, independently executing histogram equalization on each area, limiting the gray value distribution after equalization to balance the brightness and the contrast of the image for global contrast enhancement, and obtaining the image after enhancement preprocessing.
Further, in step S3, the contrast enhancement of the HSV spatial image is specifically:
in HSV color space, hue, saturation and brightness are independent from each other, and under the condition of keeping the hue unchanged, the brightness component is enhanced by using a histogram equalization method, and meanwhile, the saturation is adaptively contrast enhanced.
Further, in step S4, the weighted average coefficients of the enhanced images M1, M2, M3, M4 obtained by using the deep learning method are specifically:
(1) Taking the image processed by the original image through a multi-frame stacking technology and the original image before processing as a training set of a model;
(2) Constructing a CNN model, and training and optimizing by using a training data set to obtain a trained CNN model;
(3) Predicting weighted average coefficients of the enhanced images M1, M2, M3 and M4 by using the trained CNN model;
(4) From the predicted weighted average coefficients, weighted averages of the enhanced images M1, M2, M3, M4 are calculated.
Also provided is an image enhancement device for an underground low-illuminance deep stratum empty region, comprising:
a processor;
a memory having stored thereon a computer program executable on the processor;
the computer program, when executed by the processor, realizes a subsurface low-illumination deep stratum empty area image enhancement method.
The technical scheme provided by the invention has the beneficial effects that:
the technical scheme of the invention is that an image is processed by utilizing a multi-frame stacking technology to obtain a high-resolution image, the image is converted into a frequency domain from a space domain, and the image is reconstructed and enhanced by CNN to obtain an enhanced image M1; decomposing the high-resolution image to obtain red, green and blue RGB component images, converting the image from an RGB space to an HSV space, and carrying out contrast enhancement on the HSV space image to obtain an enhanced image M2; enhancing the HSV space image through CNN to obtain an enhanced image M3; the RGB component images are enhanced by CNN to obtain an enhanced image M4, the enhanced images obtained by processing the RGB component images by a plurality of methods are weighted and combined, and the images obtained by processing the RGB component images by the plurality of enhancement methods can be comprehensively considered, so that the final image has better performance in the aspects of color, contrast, definition, detail and the like. The various defects and weaknesses caused by the treatment of various enhancement methods can be better compensated by adopting various enhancement methods. The weighted and combined image covers the advantages of various enhancement methods, can effectively improve the contrast and quality of the image, and can comprehensively display the image information. The images are weighted and combined by adopting a plurality of enhancement methods, the information of the images can be presented from different angles, the characteristics of the images are comprehensively displayed, and the information deficiency and limitation possibly caused by a single enhancement method are avoided.
Drawings
FIG. 1 is a flow chart of a method for enhancing an image of a subsurface low-illumination deep strata empty region according to an embodiment of the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be further described with reference to the accompanying drawings.
A flow chart of an image enhancement method of an underground low-illumination deep stratum empty area in the embodiment is shown in fig. 1, and the method comprises the following steps:
s1, acquiring an original image by using a multifunctional camera;
s2, processing the obtained original image by using a multi-frame stacking technology, wherein the multi-frame stacking is used for enhancing the definition and stability of the image by superposing the multi-frame images together, and eliminating noise and jitter by calculating the average value of the images of the multi-frame stacking in the process of processing the obtained original image by using the multi-frame stacking technology. Obtaining a high-resolution image;
s3, carrying out Fourier transformation on the high-resolution image in the S2, converting the image from a space domain to a frequency domain, carrying out enhancement pretreatment on the image converted to the frequency domain, and carrying out image reconstruction and enhancement on the image subjected to the enhancement pretreatment through CNN to obtain an enhanced image M1.
The fourier transform converts an image from the spatial domain to the frequency domain, aims to decompose a periodic basis function consisting of sine and cosine waves, and decomposes a time domain signal (i.e. image) into the sum of several spectral components of positive and negative frequencies. The implementation of the fourier transform requires converting the image into a digital signal and then calculating using a Fast Fourier Transform (FFT) algorithm. After fourier transformation, the composition of the image in the frequency domain can be adjusted by changing the different frequencies (or phases).
The specific steps of the enhancement pretreatment of the image converted into the frequency domain are as follows:
(1) Performing self-adaptive histogram equalization on the image converted into the frequency domain to obtain an equalized image; adaptive histogram equalization is a method of constructing an objective function by enhancing low contrast or dark regions using local statistics to calculate the pixel brightness mean and variance for each pixel, in combination with local contrast rules.
(2) The balanced image is subjected to bilateral filtering treatment, so that detail information such as edges, textures and the like are better reserved, and a detail reserved image is obtained;
(3) And decomposing the image with the reserved details into a plurality of areas, independently executing histogram equalization on each area, limiting the gray value distribution after equalization to balance the brightness and the contrast of the image for global contrast enhancement, and obtaining the image after enhancement preprocessing.
And (3) decomposing the high-resolution image in the step (S2) to obtain red, green and blue RGB component images, applying filters with different scales to strengthen details of the RGB component images, reconstructing the images, converting the reconstructed images from the RGB space to the HSV space, and carrying out contrast enhancement processing on the HSV space images to obtain an enhanced image M2.
The conversion from RGB color space to HSV color space is from unit cube based on Cartesian coordinate system to bi-cone based on cylindrical polar coordinate, and the basic principle of the conversion is to separate brightness components in RGB, and to decompose chromaticity into hue and saturation components, and to express hue by angular vector.
The contrast enhancement of HSV space images is specifically as follows:
under the HSV color space, the hue, the saturation and the brightness are mutually independent, under the condition that the hue is kept unchanged, the brightness component is enhanced by using a histogram equalization method, the brightness and the contrast of an image can be enhanced by using the histogram equalization, and meanwhile, the saturation is adaptively contrast enhanced. The adaptive contrast enhancement method may adjust the contrast according to the local area of the image. By adaptively contrast enhancing the saturation component of the image, the visibility of details in the image can be enhanced while maintaining color fullness.
Performing image enhancement on the HSV space image through CNN to obtain an enhanced image M3;
performing image enhancement on the RGB component image through CNN to obtain an enhanced image M4;
and S4, learning and predicting by using a deep learning method to obtain weighted average coefficients of the enhanced images M1, M2, M3 and M4, and combining the enhanced images M1, M2, M3 and M4 to obtain a final enhanced image.
The weighted average coefficients of the enhanced images M1, M2, M3, M4 obtained using the deep learning method are specifically:
(1) Taking the image processed by the original image through a multi-frame stacking technology and the original image before processing as a training set of a model;
(2) Constructing a CNN model, and training and optimizing by using a training data set to obtain a trained CNN model;
(3) Predicting weighted average coefficients of the enhanced images M1, M2, M3 and M4 by using the trained CNN model;
(4) From the predicted weighted average coefficients, weighted averages of the enhanced images M1, M2, M3, M4 are calculated.
The embodiment also includes an image enhancement device for the subsurface low-illuminance deep stratum empty area, including:
a processor;
a memory having stored thereon a computer program executable on the processor;
the computer program when executed by the processor realizes a method for enhancing the image of the empty region of the underground low-illumination deep stratum.
The enhanced images obtained through processing by a plurality of methods are combined, so that the image quality can be comprehensively optimized. The advantages of various methods can be comprehensively considered by weighting and combining the images obtained by processing the various enhancement methods, so that the final image has better performance in the aspects of color, contrast, definition, detail and the like. And at the same time, the contrast and quality of the image can be improved. The various defects and weaknesses caused by the treatment of various enhancement methods can be better compensated by adopting various enhancement methods. The weighted and combined image covers the advantages of various enhancement methods, and can effectively improve the contrast and quality of the image. In addition, the image information can be comprehensively displayed. The images are weighted and combined by adopting a plurality of enhancement methods, the information of the images can be presented from different angles, the characteristics of the images are comprehensively displayed, and the information deficiency and limitation possibly caused by a single enhancement method are avoided.
Meanwhile, compared with the traditional artificial experience method, the method for acquiring the weighted average coefficient by adopting the deep learning algorithm uses the deep learning model for learning and optimizing, has better automation, robustness and reliability, can use a large amount of data for training, improves the prediction accuracy and robustness, is suitable for the problem of weighted average of different types of images, and can be expanded to wider application fields.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. The image enhancement method for the underground low-illumination deep stratum empty area is characterized by comprising the following steps of:
s1, acquiring an original image by using a multifunctional camera;
s2, processing the obtained original image by utilizing a multi-frame stacking technology to obtain a high-resolution image;
s3, carrying out Fourier transformation on the high-resolution image in the S2, converting the image from a space domain to a frequency domain, carrying out enhancement pretreatment on the image converted to the frequency domain, and carrying out image reconstruction and enhancement on the image subjected to the enhancement pretreatment through CNN to obtain an enhanced image M1; decomposing the high-resolution image in the step S2 to obtain red, green and blue RGB component images, enhancing the details of the RGB component images by using filters with different scales, reconstructing the images, converting the reconstructed images from the RGB space to the HSV space, and carrying out contrast enhancement processing on the HSV space images to obtain an enhanced image M2; performing image enhancement on the HSV space image through CNN to obtain an enhanced image M3; performing image enhancement on the RGB component image through CNN to obtain an enhanced image M4;
s4, obtaining weighted average coefficients of the enhanced images M1, M2, M3 and M4 by using a deep learning method, and combining the enhanced images M1, M2, M3 and M4 to obtain a final enhanced image.
2. The method for enhancing an image of a subsurface low-illuminance deep ground empty region according to claim 1, wherein in step S2, noise and jitter are eliminated by calculating an average value of images of a plurality of frames stacked in a process of processing the acquired original image using a plurality of frames stacked technique.
3. The method for enhancing an image of a subsurface low-illuminance deep strata empty region according to claim 1, wherein in step S3, the specific step of enhancing the image converted into the frequency domain is as follows:
(1) Performing self-adaptive histogram equalization on the image converted into the frequency domain to obtain an equalized image;
(2) Processing edges and textures of the equalized image through bilateral filtering to obtain a detail-preserved image;
(3) And decomposing the image with the reserved details into a plurality of areas, independently executing histogram equalization on each area, limiting the gray value distribution after equalization to balance the brightness and the contrast of the image for global contrast enhancement, and obtaining the image after enhancement preprocessing.
4. The method for enhancing an image of an underground low-illuminance deep stratum empty region according to claim 1, wherein in step S3, contrast enhancement is specifically performed on an HSV space image:
in HSV color space, hue, saturation and brightness are independent from each other, and under the condition of keeping the hue unchanged, the brightness component is enhanced by using a histogram equalization method, and meanwhile, the saturation is adaptively contrast enhanced.
5. The method for enhancing an image of a subsurface low-illuminance deep ground empty region according to claim 1, wherein in step S4, the weighted average coefficients of the enhanced images M1, M2, M3, M4 obtained by using the deep learning method are specifically:
(1) Taking the image processed by the original image through a multi-frame stacking technology and the original image before processing as a training set of a model;
(2) Constructing a CNN model, and training and optimizing by using a training data set to obtain a trained CNN model;
(3) Predicting weighted average coefficients of the enhanced images M1, M2, M3 and M4 by using the trained CNN model;
(4) From the predicted weighted average coefficients, weighted averages of the enhanced images M1, M2, M3, M4 are calculated.
6. An image enhancement device for an underground low-illumination deep stratum empty area, which is characterized by comprising:
a processor;
a memory having stored thereon a computer program executable on the processor;
wherein the computer program when executed by the processor implements a subsurface low-light deep formation void image enhancement method as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310843877.6A CN116993636B (en) | 2023-07-10 | 2023-07-10 | Image enhancement method and device for underground low-illumination deep stratum empty area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310843877.6A CN116993636B (en) | 2023-07-10 | 2023-07-10 | Image enhancement method and device for underground low-illumination deep stratum empty area |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116993636A true CN116993636A (en) | 2023-11-03 |
| CN116993636B CN116993636B (en) | 2024-02-13 |
Family
ID=88522307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310843877.6A Active CN116993636B (en) | 2023-07-10 | 2023-07-10 | Image enhancement method and device for underground low-illumination deep stratum empty area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116993636B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106504212A (en) * | 2016-11-07 | 2017-03-15 | 湖南源信光电科技有限公司 | A kind of improved HSI spatial informations low-luminance color algorithm for image enhancement |
| CN110443807A (en) * | 2019-06-27 | 2019-11-12 | 中国地质大学（武汉） | A kind of even carrying out image threshold segmentation method of uneven illumination based on luminance proportion |
| CN111626967A (en) * | 2019-02-28 | 2020-09-04 | 富华科精密工业（深圳）有限公司 | Image enhancement method, image enhancement device, computer device and readable storage medium |
| KR102277005B1 (en) * | 2020-03-13 | 2021-07-14 | 이화여자대학교 산학협력단 | Low-Light Image Processing Method and Device Using Unsupervised Learning |
| CN113129236A (en) * | 2021-04-25 | 2021-07-16 | 中国石油大学(华东) | Single low-light image enhancement method and system based on Retinex and convolutional neural network |
| CN115272115A (en) * | 2022-07-25 | 2022-11-01 | 贵州杰源水务管理技术科技有限公司 | Underwater image enhancement network and method based on dual guidance of physics and deep learning |
| CN115526803A (en) * | 2022-10-14 | 2022-12-27 | 中国石油大学(华东) | Non-uniform illumination image enhancement method, system, storage medium and device |
| CN116363001A (en) * | 2023-03-08 | 2023-06-30 | 江苏科技大学 | Underwater image enhancement method combining RGB and HSV color spaces |
-
2023
- 2023-07-10 CN CN202310843877.6A patent/CN116993636B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106504212A (en) * | 2016-11-07 | 2017-03-15 | 湖南源信光电科技有限公司 | A kind of improved HSI spatial informations low-luminance color algorithm for image enhancement |
| CN111626967A (en) * | 2019-02-28 | 2020-09-04 | 富华科精密工业（深圳）有限公司 | Image enhancement method, image enhancement device, computer device and readable storage medium |
| CN110443807A (en) * | 2019-06-27 | 2019-11-12 | 中国地质大学（武汉） | A kind of even carrying out image threshold segmentation method of uneven illumination based on luminance proportion |
| KR102277005B1 (en) * | 2020-03-13 | 2021-07-14 | 이화여자대학교 산학협력단 | Low-Light Image Processing Method and Device Using Unsupervised Learning |
| CN113129236A (en) * | 2021-04-25 | 2021-07-16 | 中国石油大学(华东) | Single low-light image enhancement method and system based on Retinex and convolutional neural network |
| CN115272115A (en) * | 2022-07-25 | 2022-11-01 | 贵州杰源水务管理技术科技有限公司 | Underwater image enhancement network and method based on dual guidance of physics and deep learning |
| CN115526803A (en) * | 2022-10-14 | 2022-12-27 | 中国石油大学(华东) | Non-uniform illumination image enhancement method, system, storage medium and device |
| CN116363001A (en) * | 2023-03-08 | 2023-06-30 | 江苏科技大学 | Underwater image enhancement method combining RGB and HSV color spaces |
Non-Patent Citations (2)
| Title |
|---|
| PRIYANKA HANDA ET AL.: "Image Quality Enhancement using CLAHlet RetiGaussian Filter for Maize Leaf Images", 《RESEARCH SQUARE》, 10 February 2023 (2023-02-10) * |
| 宋宇康 等: "基于双颜色空间与多网络融合的水下图像增强", 《南京邮电大学学报》, 30 June 2023 (2023-06-30) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116993636B (en) | 2024-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9135681B2 (en) | Image chroma noise reduction | |
| CN111583123A (en) | Wavelet transform-based image enhancement algorithm for fusing high-frequency and low-frequency information | |
| Suganya et al. | Survey on image enhancement techniques | |
| CN108564597B (en) | Video foreground object extraction method fusing Gaussian mixture model and H-S optical flow method | |
| CN111260580B (en) | Image denoising method, computer device and computer readable storage medium | |
| CN111429370B (en) | Underground coal mine image enhancement method, system and computer storage medium | |
| CN112801925B (en) | Underwater image enhancement method for maximally eliminating influence of water ripple based on information entropy | |
| CN111696052B (en) | Underwater image enhancement method and system based on red channel weakness | |
| US7903900B2 (en) | Low complexity color de-noising filter | |
| CN107862672B (en) | Image defogging method and device | |
| CN113850741B (en) | Image noise reduction method and device, electronic equipment and storage medium | |
| CN113781320A (en) | Image processing method and device, terminal equipment and storage medium | |
| CN115984134A (en) | Intelligent enhancing method for remote sensing mapping image | |
| Gao et al. | Sandstorm image enhancement based on YUV space | |
| CN116188325A (en) | Image denoising method based on deep learning and image color space characteristics | |
| CN112435184A (en) | Haze sky image identification method based on Retinex and quaternion | |
| CN117252773A (en) | Image enhancement method and system based on self-adaptive color correction and guided filtering | |
| CN111311503A (en) | Night low-brightness image enhancement system | |
| CN112200719B (en) | Image processing method, electronic device, and readable storage medium | |
| CN116993636B (en) | Image enhancement method and device for underground low-illumination deep stratum empty area | |
| Sun et al. | Readability enhancement of low light videos based on discrete wavelet transform | |
| CN111161189A (en) | Single image re-enhancement method based on detail compensation network | |
| CN108492264B (en) | Single-frame image fast super-resolution method based on sigmoid transformation | |
| CN115082296B (en) | Image generation method based on wavelet domain image generation frame | |
| Sadia et al. | Color image enhancement using multiscale retinex with guided filter |
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 |