CN114429426B - Low-illumination image quality improvement method based on Retinex model - Google Patents
Low-illumination image quality improvement method based on Retinex model Download PDFInfo
- Publication number
- CN114429426B CN114429426B CN202111561917.5A CN202111561917A CN114429426B CN 114429426 B CN114429426 B CN 114429426B CN 202111561917 A CN202111561917 A CN 202111561917A CN 114429426 B CN114429426 B CN 114429426B
- Authority
- CN
- China
- Prior art keywords
- layer image
- image
- illumination
- pixel value
- detail
- 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
- 238000005286 illumination Methods 0.000 title claims abstract description 113
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000013507 mapping Methods 0.000 claims abstract description 53
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000010606 normalization Methods 0.000 claims description 13
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 11
- 230000006870 function Effects 0.000 description 21
- 230000000694 effects Effects 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 101100498818 Arabidopsis thaliana DDR4 gene Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000000007 visual effect Effects 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
A low-illumination image quality improvement method based on a Retinex model belongs to the technical field of image processing. The invention solves the problem of poor quality of the obtained image when the existing low-illumination image quality improvement algorithm is adopted to process the low-illumination image. Firstly, layering a digital image through a Retinex model to obtain a detail layer image and an illumination layer image; secondly, designing a nonlinear global brightness mapping function, and mapping the illumination layer image to obtain an illumination layer enhanced image; designing a nonlinear detail layer image mapping function again, and stretching the detail layer image to obtain a detail layer enhanced image; and finally, multiplying each pixel of the detail layer enhanced image and the illumination layer enhanced image to synthesize the low-illumination enhanced image. The method can be applied to improve the quality of the low-illumination image.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a low-illumination image quality improving method based on a Retinex model.
Background
Because light is easily influenced by the environment in a propagation path, the images shot by the digital camera have uneven brightness distribution, unclear details and textures in low-illumination areas, and poor image quality and human eye visualization effect. Therefore, how to improve the effect of the low illumination effect on the image quality has become a hot issue in the image processing field in recent years.
The classic low-illumination image quality improvement algorithm mainly comprises an image gray scale segmentation mapping algorithm, a histogram equalization algorithm, a Gamma correction algorithm and the like. Although the classic low-illumination image quality improvement algorithm can inhibit the visual problem caused by the low-illumination effect to a certain extent, the image quality of the enhanced image is affected by the problems of selection of free parameters, excessive enhancement of the image, fuzzy details and the like, and therefore, after the low-illumination image is processed by the existing low-illumination image quality improvement algorithm, the quality of the obtained image is still poor.
Disclosure of Invention
The invention aims to solve the problem that when the existing low-illumination image quality improvement algorithm is adopted to process a low-illumination image, the quality of the obtained image is poor, and provides a low-illumination image quality improvement method based on a Retinex model.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a low-illumination image quality improvement method based on a Retinex model specifically comprises the following steps:
step one, after the acquired image is converted from an RGB channel to an HSV channel, data of a V channel, an H channel and an S channel are respectively acquired;
decomposing the V channel data into an illumination layer image and a detail layer image;
step two, carrying out global brightness mapping processing on the illumination layer image to obtain the illumination layer image after global brightness mapping;
then, carrying out pixel value domain expansion on the illumination layer image after global brightness mapping to obtain an illumination layer image after pixel value domain expansion;
stretching the detail layer image by using a detail layer image mapping function to obtain a stretched detail layer image;
step four, synthesizing the illumination layer image with the expanded pixel value domain and the stretched detail layer image into a new image; and converting the synthesized image and the H channel and S channel data obtained in the first step into an output image.
Further, in the first step, the V-channel data is decomposed into an illumination layer image and a detail layer image, and the specific process is as follows:
I(x,y)=c(x,y)×L(x,y) (1)
wherein, I (x, y) represents a pixel value of the V channel data at the pixel point (x, y), L (x, y) represents a pixel value of the illumination layer image at the pixel point (x, y), and c (x, y) represents a pixel value of the detail layer image at the pixel point (x, y).
Further, the illumination layer image is obtained by performing convolution calculation on the V channel data and a Gaussian kernel with the variance of 1.
Further, the specific process of the second step is as follows:
step two, normalization processing is carried out on the illumination layer image to obtain the illumination layer image after normalization processing;
wherein,representing the pixel value of the illumination layer image after normalization processing at the pixel point (x, y), wherein max represents the maximum value operation;
secondly, determining a brightness segmentation threshold T of the illumination layer image after normalization processing by adopting a maximum inter-class variance method;
step two, according to the brightness segmentation threshold value T and a global brightness mapping function, global brightness mapping is carried out on the illumination layer image after normalization processing, and the illumination layer image after global brightness mapping is obtained;
the global luminance mapping function is:
wherein,representing the pixel value of the illumination layer image after global brightness mapping at the pixel point (x, y);
step two, carrying out pixel value domain expansion on the illumination layer image after global brightness mapping:
wherein L is d And (x, y) represents the pixel value of the illumination layer image after the pixel value domain expansion at the pixel point (x, y).
Further, the detail layer image mapping function is:
wherein e is the base of the natural logarithm, A, B, D are coefficients of the detail layer image mapping function, and S (c (x, y)) represents the value of the pixel point (x, y) in the stretched detail layer image.
Further, the coefficients a, B, D of the detail layer image mapping function are:
wherein, [ h ] 0 ,h 1 ]For the domain of pixel values c (x, y) in the detail layer image, c (x, y) is E [ h ] 0 ,h 1 ]I.e. h 0 Is the minimum value of the pixel values c (x, y), h, in the detail layer image 1 Is the maximum value of the pixel value c (x, y) in the detail layer image.
Further, in the fourth step, the illumination layer image after the pixel value domain expansion and the stretched detail layer image are synthesized into a new image, and the specific process is as follows:
and multiplying the pixel values at the same position in the illumination layer image after the pixel value domain expansion and the stretched detail layer image, and taking the multiplication result as the pixel value at the corresponding position in the synthesized new image.
The invention has the beneficial effects that:
the invention provides a low-illumination image quality improving method based on a Retinex model, aiming at improving the overall contrast of a low-illumination image and enhancing the detail and texture characteristics of the low-illumination image. Firstly, layering a digital image through a Retinex model to obtain a detail layer image and an illumination layer image; secondly, designing a nonlinear global brightness mapping function, and mapping the illumination layer image to obtain an illumination layer enhanced image; designing a nonlinear detail layer image mapping function again, and stretching the detail layer image to obtain a detail layer enhanced image; and finally, multiplying each pixel of the detail layer enhanced image and the illumination layer enhanced image to synthesize the low-illumination enhanced image. Experimental results show that the algorithm can effectively improve the image quality of the low-illumination image.
Drawings
FIG. 1 is a flowchart of a method for improving the quality of low-illumination images based on Retinex model according to the present invention;
fig. 2 is a graph of a global luminance mapping function of a corresponding illumination layer when a luminance partition threshold T is 0.2;
fig. 3 is a graph of a global luminance mapping function of a corresponding illumination layer when a luminance partition threshold T is 0.5;
FIG. 4 is a graph of a detail layer image mapping function;
wherein, the intensity value range of the detail layer of the original image is [0.1,3 ];
FIG. 5(a) is a first original image;
FIG. 5(b) is an enhanced image corresponding to FIG. 5 (a);
FIG. 6(a) is the original image two;
fig. 6(b) is an enhanced image corresponding to fig. 6 (a).
Detailed Description
First embodiment this embodiment will be described with reference to fig. 1. The method for improving the quality of a low-illumination image based on a Retinex model in the embodiment specifically includes the following steps:
step one, after the acquired image is converted from an RGB channel to an HSV channel, data of a V channel, an H channel and an S channel are respectively acquired;
decomposing the V channel data into an illumination layer image and a detail layer image;
step two, carrying out global brightness mapping processing on the illumination layer image to obtain the illumination layer image after global brightness mapping;
then, carrying out pixel value domain expansion on the illumination layer image after global brightness mapping to obtain an illumination layer image after pixel value domain expansion, namely an illumination enhancement image;
stretching the detail layer image by using a detail layer image mapping function to obtain a stretched detail layer image, namely a detail enhanced image;
step four, synthesizing the illumination layer image with the expanded pixel value domain and the stretched detail layer image into a new image; and converting the synthesized image and the H channel and S channel data obtained in the step one into an output image.
In the embodiment, firstly, an image is input to the RGB-to-HSV module for color conversion; independently carrying out Retinex layering model shown in the formula (1) on the V channel data to obtain an illumination layer image and a detail layer image; carrying out global brightness mapping shown in the formula (3) on the illumination layer image independently to obtain an illumination layer enhanced image; independently mapping the detail layer image shown in the formula (5) to obtain a detail layer enhanced image; multiplying the detail layer enhanced image and the illumination layer enhanced image one by one to synthesize a new image; by the HSV-RGB conversion module, the synthesized new image, original H channel and S channel data are converted into an output image which can be directly displayed, and the quality of the obtained output image is obviously improved.
The second embodiment is as follows: the difference between this embodiment and the first embodiment is that, in the step one, the V-channel data is decomposed into an illumination layer image and a detail layer image, and the specific process is as follows:
I(x,y)=c(x,y)×L(x,y) (1)
wherein, I (x, y) represents a pixel value of the V channel data at the pixel point (x, y), L (x, y) represents a pixel value of the illumination layer image at the pixel point (x, y), and c (x, y) represents a pixel value of the detail layer image at the pixel point (x, y).
According to the Retinex model, a digital image can be decomposed into an illumination layer image and a detail layer image, the illumination layer image determines the whole brightness and darkness contrast of the image, and the detail layer image determines the details and texture of the image. The pixel point (x, y) is a coordinate in an image coordinate system, and the width direction of the image is taken as an x-axis, and the height direction of the image is taken as a y-axis.
Other steps and parameters are the same as those in the first embodiment.
The third concrete implementation mode: the difference between this embodiment and the first or second embodiment is that the illumination layer image is obtained by performing convolution calculation on V-channel data and a gaussian kernel with a variance of 1.
Other steps and parameters are the same as those in the first or second embodiment.
The fourth concrete implementation mode: the difference between this embodiment and one of the first to third embodiments is that the specific process of the second step is:
step two, normalization processing is carried out on the illumination layer image to obtain the illumination layer image after normalization processing;
wherein,representing the pixel value of the illumination layer image after normalization processing at the pixel point (x, y), wherein max represents the maximum value operation;
secondly, determining the brightness segmentation threshold T of the illumination layer image after normalization processing by adopting a maximum inter-class variance method (OTSU);
step two, according to the brightness segmentation threshold value T and a global brightness mapping function, global brightness mapping is carried out on the illumination layer image after normalization processing, and the illumination layer image after global brightness mapping is obtained;
the global luminance mapping function is:
wherein,representing the pixel value of the illumination layer image after global brightness mapping at the pixel point (x, y);
the overall contrast of the image can be enhanced through the global brightness mapping, and as can be seen from fig. 2 and 3, the global brightness mapping function stretches the brightness smaller than the threshold T, so as to improve the brightness of the portion of pixels, and compresses the brightness larger than the threshold T, so as to reduce the brightness of the portion of pixels.
Step two, pixel (brightness) value domain expansion is carried out on the illumination layer image after the global brightness mapping:
wherein L is d And (x, y) represents the pixel value of the illumination layer image after the pixel value domain expansion at the pixel point (x, y).
By stretching the illumination layer image L by the method of the present embodiment, the overall contrast of the low-illumination image can be enhanced.
Other steps and parameters are the same as those in one of the first to third embodiments.
The fifth concrete implementation mode is as follows: this embodiment will be described with reference to fig. 4. The difference between this embodiment and one of the first to the fourth embodiments is that the detail layer image mapping function is:
wherein e is the base of the natural logarithm, A, B, D are coefficients of the detail layer image mapping function, and S (c (x, y)) represents the value of the pixel point (x, y) in the stretched detail layer image.
The nonlinear detail layer image mapping function designed in the present embodiment is to enhance the detail and texture characteristics of the detail layer image and enrich the detail and texture characteristics of the low-illumination image.
Other steps and parameters are the same as in one of the first to fourth embodiments.
The sixth specific implementation mode: this embodiment is different from one of the first to fifth embodiments in that the coefficients a, B, and D of the detail layer image mapping function are:
wherein, [ h ] 0 ,h 1 ]For the domain of pixel values c (x, y) in the detail layer image, c (x, y) is E [ h ] 0 ,h 1 ]I.e. h 0 Is the minimum value of the pixel values c (x, y), h, in the detail layer image 1 Is the maximum value of the pixel value c (x, y) in the detail layer image.
A, B and D are three undetermined coefficients, and the definition domain, the value domain and the original image detail intensity (namely the pixel value) of the decision function are enhanced image detail intensities corresponding to 1. Since the image is most blurred when the original detail layer image intensity is 1, the detail-enhanced image intensity should also be 1, i.e., S (1) ═ 1. In addition, detail layer image enhancement needs to keep the domain consistent with the value domain, i.e., S (h) 0 )=h 0 、S(h 1 )=h 1 . Therefore, the three corresponding relations are respectively substituted into the function (5), and the values of the three pending coefficients shown in the formula (6) are obtained.
Other steps and parameters are the same as those in one of the first to fifth embodiments.
The seventh embodiment: the difference between this embodiment and one of the first to sixth embodiments is that, in the fourth step, the illumination layer image after the pixel value domain expansion and the detail layer image after the stretching are synthesized into a new image, and the specific process is as follows:
and multiplying the pixel values at the same position in the illumination layer image after the pixel value domain expansion and the stretched detail layer image, and taking the multiplication result as the pixel value at the corresponding position in the synthesized new image.
That is, the pixel value of the pixel point (x, y) in the illumination layer image after the pixel value domain expansion is multiplied by the pixel value of the pixel point (x, y) in the detail layer image after stretching, and the multiplication result is used as the pixel value of the pixel point (x, y) in the synthesized new image.
Other steps and parameters are the same as those in one of the first to sixth embodiments.
Analysis of Experimental results
The simulation software adopted by the invention is Matlab 2018 a. The hardware platform is a desktop computer, and the hardware of the hardware platform comprises the following components: i9-11900H specification CPU, 16GB DDR4 specification memory, RTX 3060 specification display card. The input and output of the simulation program are standard images in the bmp format.
The simulation results of the method of the present invention are shown in fig. 5(a) and 5(b) and in fig. 6(a) and 6 (b).
As can be seen from fig. 5(a) and 5(b) and fig. 6(a) and 6(b), because the illumination intensity is relatively low and the distribution is not uniform, the original image frame shows a darker effect, so that the details and the contour of the scene in the original image cannot be distinguished by human eyes, and thus the image quality is poor; the low-illumination image quality improvement algorithm designed by the invention improves the image brightness of a low-illumination area, and the local details of the enhanced image are clear and rich. Therefore, the algorithm can effectively improve the overall visualization effect of the low-illumination image and enhance the image quality of the image.
The above-described calculation examples of the present invention are merely to explain the calculation model and the calculation flow of the present invention in detail, and are not intended to limit the embodiments of the present invention. It will be apparent to those skilled in the art that other variations and modifications of the present invention can be made based on the above description, and it is not intended to be exhaustive or to limit the invention to the precise form disclosed, and all such modifications and variations are possible and contemplated as falling within the scope of the invention.
Claims (5)
1. A low-illumination image quality improvement method based on a Retinex model is characterized by specifically comprising the following steps of:
step one, after the acquired image is converted from an RGB channel to an HSV channel, data of a V channel, an H channel and an S channel are respectively acquired;
in the first step, the V-channel data is decomposed into an illumination layer image and a detail layer image, and the specific process is as follows:
I(x,y)=c(x,y)×L(x,y) (1)
wherein, I (x, y) represents a pixel value of the V channel data at the pixel point (x, y), L (x, y) represents a pixel value of the illumination layer image at the pixel point (x, y), and c (x, y) represents a pixel value of the detail layer image at the pixel point (x, y);
decomposing the V channel data into an illumination layer image and a detail layer image;
step two, carrying out global brightness mapping processing on the illumination layer image to obtain an illumination layer image after global brightness mapping;
the specific process of the second step is as follows:
step two, normalizing the illumination layer image to obtain a normalized illumination layer image;
wherein,representing the pixel value of the illumination layer image after normalization processing at the pixel point (x, y), wherein max represents the maximum value operation;
secondly, determining a brightness segmentation threshold T of the illumination layer image after normalization processing by adopting a maximum inter-class variance method;
step two, according to the brightness segmentation threshold value T and a global brightness mapping function, global brightness mapping is carried out on the illumination layer image after normalization processing, and the illumination layer image after global brightness mapping is obtained;
the global luminance mapping function is:
wherein,representing a global luminance mapThe pixel value of the subsequent illumination layer image at the pixel point (x, y);
step two, carrying out pixel value domain expansion on the illumination layer image after global brightness mapping:
wherein L is d (x, y) represents the pixel value of the illumination layer image at the pixel point (x, y) after the pixel value domain expansion;
then, carrying out pixel value domain expansion on the illumination layer image after global brightness mapping to obtain an illumination layer image after pixel value domain expansion;
stretching the detail layer image by using a detail layer image mapping function to obtain a stretched detail layer image;
step four, synthesizing the illumination layer image with the expanded pixel value domain and the stretched detail layer image into a new image; and converting the synthesized image and the H channel and S channel data obtained in the first step into an output image.
2. The method as claimed in claim 1, wherein the illumination layer image is obtained by performing convolution calculation on V-channel data and a gaussian kernel with a variance of 1.
3. A method of improving image quality under low illumination based on Retinex model as claimed in claim 2, wherein the detail layer image mapping function is:
wherein e is the base of the natural logarithm, A, B, D are coefficients of the detail layer image mapping function, and S (c (x, y)) represents the value of the pixel point (x, y) in the stretched detail layer image.
4. The method of claim 3, wherein coefficients A, B, and D of the detail layer image mapping function are:
wherein, [ h ] 0 ,h 1 ]For the domain of pixel values c (x, y) in the detail layer image, c (x, y) is E [ h ] 0 ,h 1 ]I.e. h 0 Is the minimum value of the pixel values c (x, y), h, in the detail layer image 1 Is the maximum value of the pixel value c (x, y) in the detail layer image.
5. The method according to claim 4, wherein in the fourth step, the illumination layer image after pixel value domain expansion and the detail layer image after stretching are synthesized into a new image by a specific process:
and multiplying the pixel values at the same position in the illumination layer image after the pixel value domain expansion and the stretched detail layer image, and taking the multiplication result as the pixel value at the corresponding position in the synthesized new image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111561917.5A CN114429426B (en) | 2021-12-20 | 2021-12-20 | Low-illumination image quality improvement method based on Retinex model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111561917.5A CN114429426B (en) | 2021-12-20 | 2021-12-20 | Low-illumination image quality improvement method based on Retinex model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114429426A CN114429426A (en) | 2022-05-03 |
CN114429426B true CN114429426B (en) | 2022-08-16 |
Family
ID=81311806
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111561917.5A Active CN114429426B (en) | 2021-12-20 | 2021-12-20 | Low-illumination image quality improvement method based on Retinex model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114429426B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115660994B (en) * | 2022-10-31 | 2023-06-09 | 哈尔滨理工大学 | Image enhancement method based on regional least square estimation |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105046663A (en) * | 2015-07-10 | 2015-11-11 | 西南科技大学 | Human visual perception simulation-based self-adaptive low-illumination image enhancement method |
CN110163815A (en) * | 2019-04-22 | 2019-08-23 | 桂林电子科技大学 | Low-light (level) restoring method based on multistage variation self-encoding encoder |
CN110298796A (en) * | 2019-05-22 | 2019-10-01 | 中山大学 | Based on the enhancement method of low-illumination image for improving Retinex and Logarithmic image processing |
CN111105359A (en) * | 2019-07-22 | 2020-05-05 | 浙江万里学院 | Tone mapping method for high dynamic range image |
CN112950596A (en) * | 2021-03-09 | 2021-06-11 | 宁波大学 | Tone mapping omnidirectional image quality evaluation method based on multi-region and multi-layer |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7590303B2 (en) * | 2005-09-29 | 2009-09-15 | Samsung Electronics Co., Ltd. | Image enhancement method using local illumination correction |
CN100562067C (en) * | 2007-07-26 | 2009-11-18 | 上海交通大学 | The real time digital image processing and enhancing method that has noise removal function |
EP2187620B1 (en) * | 2007-07-26 | 2014-12-24 | Omron Corporation | Digital image processing and enhancing system and method with function of removing noise |
CN103295225B (en) * | 2013-04-10 | 2016-09-28 | 苏州大学 | Train bogie edge detection method under the conditions of low-light |
JP5907938B2 (en) * | 2013-09-26 | 2016-04-26 | 京セラドキュメントソリューションズ株式会社 | Image forming apparatus and program |
CN105654437B (en) * | 2015-12-24 | 2019-04-19 | 广东迅通科技股份有限公司 | A kind of Enhancement Method of pair of low-light (level) image |
CN107045715B (en) * | 2017-02-22 | 2019-06-07 | 西南科技大学 | A kind of method that single width low dynamic range echograms generate high dynamic range images |
CN112734650B (en) * | 2019-10-14 | 2022-09-30 | 武汉科技大学 | Virtual multi-exposure fusion based uneven illumination image enhancement method |
CN112308793A (en) * | 2020-10-21 | 2021-02-02 | 淮阴工学院 | Novel method for enhancing contrast and detail of non-uniform illumination image |
CN113256533B (en) * | 2021-06-15 | 2022-08-09 | 北方民族大学 | Self-adaptive low-illumination image enhancement method and system based on MSRCR |
-
2021
- 2021-12-20 CN CN202111561917.5A patent/CN114429426B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105046663A (en) * | 2015-07-10 | 2015-11-11 | 西南科技大学 | Human visual perception simulation-based self-adaptive low-illumination image enhancement method |
CN110163815A (en) * | 2019-04-22 | 2019-08-23 | 桂林电子科技大学 | Low-light (level) restoring method based on multistage variation self-encoding encoder |
CN110298796A (en) * | 2019-05-22 | 2019-10-01 | 中山大学 | Based on the enhancement method of low-illumination image for improving Retinex and Logarithmic image processing |
CN111105359A (en) * | 2019-07-22 | 2020-05-05 | 浙江万里学院 | Tone mapping method for high dynamic range image |
CN112950596A (en) * | 2021-03-09 | 2021-06-11 | 宁波大学 | Tone mapping omnidirectional image quality evaluation method based on multi-region and multi-layer |
Also Published As
Publication number | Publication date |
---|---|
CN114429426A (en) | 2022-05-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Gao et al. | Naturalness preserved nonuniform illumination estimation for image enhancement based on retinex | |
Gupta et al. | Minimum mean brightness error contrast enhancement of color images using adaptive gamma correction with color preserving framework | |
CN100568279C (en) | A kind of fast colourful image enchancing method based on the Retinex theory | |
CN109064426B (en) | Method and device for suppressing glare in low-illumination image and enhancing image | |
Zotin | Fast algorithm of image enhancement based on multi-scale retinex | |
CN103578084A (en) | Color image enhancement method based on bright channel filtering | |
Wang et al. | Variational single nighttime image haze removal with a gray haze-line prior | |
CN110298792B (en) | Low-illumination image enhancement and denoising method, system and computer equipment | |
Gupta et al. | New contrast enhancement approach for dark images with non-uniform illumination | |
Shiau et al. | A low-cost hardware architecture for illumination adjustment in real-time applications | |
CN114429426B (en) | Low-illumination image quality improvement method based on Retinex model | |
Jeon et al. | Low-light image enhancement using inverted image normalized by atmospheric light | |
CN113222859B (en) | Low-illumination image enhancement system and method based on logarithmic image processing model | |
CN108550124B (en) | Illumination compensation and image enhancement method based on bionic spiral | |
Tung et al. | ICEBIN: Image contrast enhancement based on induced norm and local patch approaches | |
CN112308793A (en) | Novel method for enhancing contrast and detail of non-uniform illumination image | |
Park et al. | ULBPNet: Low-light image enhancement using U-shaped lightening back-projection | |
CN110807748A (en) | New tone mapping image enhancement method based on high dynamic range | |
CN114862706B (en) | Tone mapping method for keeping gradient direction of image | |
Chen et al. | A novel low-light enhancement via fractional-order and low-rank regularized retinex model | |
CN112767256A (en) | Retinex model-based image enhancement method and terminal | |
Liu et al. | An adaptive tone mapping algorithm based on gaussian filter | |
Trongtirakul et al. | Adaptive single low-light image enhancement by fractional stretching in logarithmic domain | |
Vavilin et al. | Recursive HDR image generation from differently exposed images based on local image properties | |
Lucas et al. | Image enhancement for astronomical scenes |
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 |