CN108550124B - Illumination compensation and image enhancement method based on bionic spiral - Google Patents
Illumination compensation and image enhancement method based on bionic spiral Download PDFInfo
- Publication number
- CN108550124B CN108550124B CN201810342902.1A CN201810342902A CN108550124B CN 108550124 B CN108550124 B CN 108550124B CN 201810342902 A CN201810342902 A CN 201810342902A CN 108550124 B CN108550124 B CN 108550124B
- Authority
- CN
- China
- Prior art keywords
- image
- brightness
- layer
- path
- spiral
- 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 38
- 238000000034 method Methods 0.000 title claims abstract description 36
- 239000011664 nicotinic acid Substances 0.000 title claims abstract description 13
- 238000009499 grossing Methods 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims abstract description 5
- 230000014759 maintenance of location Effects 0.000 claims abstract description 4
- 238000000926 separation method Methods 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 125000001475 halogen functional group Chemical group 0.000 description 6
- 241000196324 Embryophyta Species 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000009194 climbing Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 240000001549 Ipomoea eriocarpa Species 0.000 description 1
- 235000005146 Ipomoea eriocarpa Nutrition 0.000 description 1
- 244000061176 Nicotiana tabacum Species 0.000 description 1
- 235000002637 Nicotiana tabacum Nutrition 0.000 description 1
- 241000219995 Wisteria Species 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000007769 metal material Substances 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000029553 photosynthesis Effects 0.000 description 1
- 238000010672 photosynthesis Methods 0.000 description 1
- 230000005855 radiation 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
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/50—Lighting effects
- G06T15/506—Illumination models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention provides an illumination compensation and image enhancement method based on a bionic spiral, which comprises the following steps: step S1, acquiring an original image to be processed; step S2, separating a brightness layer and a color layer of the image, wherein the color layer is the original attribute retention of the object; the brightness layer contains illumination information to be processed independently; step S3, performing bionic spiral illumination analysis on the brightness layer, and obtaining a new brightness layer according to a self-adaptive smoothing algorithm; step S4, combine the new luminance layer with the original color layer to obtain the enhanced image. The method of the invention reduces the brightness of the bright part of the image, increases the brightness of the shadow part, and ensures that the brightness of the whole image is relatively uniform, and the details of the parts with over-high brightness and over-low brightness are displayed, thereby improving the operation efficiency.
Description
Technical Field
The invention relates to an image enhancement method, in particular to an image enhancement method capable of processing a spatial high-dynamic-range uneven illumination image, and belongs to the technical field of image processing.
Background
For robot astronauts, the variable illumination environment has great challenge to intelligent identification. The dynamic range of the space illumination intensity is high, and because the atmospheric layer does not attenuate and scatter the illumination, the illumination intensity entering the visual system is very high, and the area without direct illumination is a dark background, and the brightness contrast of the two areas is strong. The space in the space station cabin is narrow, the surface of the device is mostly made of metal materials, and strong reflection of light exists; moreover, due to the shadow of the direct illumination in the vicinity of the porthole, a part of highlight areas and shadows are generated, which causes very strong nonlinearity of the illumination environment in the cabin.
Image enhancement techniques have been a very important basic processing foundation in the field of robot vision. The image enhancement technology is to enhance the information useful for observers in the image, so that the contrast of the image is higher and the visual effect is better.
The McCann Retinex algorithm is proposed by McCann and Frankle based on Retinec theory, and is suitable for the situation of calculating objects in human vision in a natural environment with large dynamic range of radiation intensity. When an image with shadow occlusion and an image with uneven illumination are enhanced, the McCann Retinex algorithm has a better enhancement effect, but still has some defects.
A. Halo phenomenon (halo) generation: this phenomenon is caused because conventional Retinex assumes that the illumination is changing smoothly in the scene, and therefore tends to produce a halo phenomenon in contrast when processing high dynamic range images. In a spatial environment, the image is mostly in a nonlinear high dynamic state, and therefore, the retinex method of the conventional MSR is not suitable.
B. The treatment effect and the treatment time cannot be balanced: in order to obtain a good dynamic compression and smooth image, a larger area of the image is often traversed, and the iteration is carried out for more times; but this also slows down the processing speed significantly, affecting algorithm execution efficiency. And if the iteration times are too few, the illumination characteristic of the whole image cannot be represented, and the enhancement effect is not obvious.
C. Part of the color is distorted, producing a false color effect: this is due to the fact that the conventional Retinex method is processed through RGB channels, Retinex being non-linearly processed on 3 different base bands of RGB, resulting in a direct result of color distortion.
D. The detail information of the overexposed area is not abundant: in an overexposed highlight image, the traditional Retinex mainly senses the structural information of the image through different brightness levels of all pixel points in the neighborhood; for a color image, when the brightness levels at both sides of an overexposed image are the same, the edge cannot be distinguished only by the brightness information.
Disclosure of Invention
The invention aims to provide an illumination compensation and image enhancement method, which can reduce the brightness of a bright part of an image, increase the brightness of a shadow part of the image, ensure that the brightness of the whole image is relatively uniform, and show the details of an overhigh part and an overlow part of the image. Meanwhile, the operation efficiency is improved.
The technical scheme of the invention is as follows.
In one aspect, the invention provides an image enhancement method based on a bionic spiral, which comprises the following steps:
step S1, acquiring an original image to be processed;
step S2, separating a brightness layer and a color layer of the image, wherein the color layer is the original attribute retention of the object; the brightness layer contains illumination information to be processed independently;
step S3, performing bionic spiral illumination analysis on the brightness layer, and obtaining a new brightness layer according to a self-adaptive smoothing algorithm;
step S4, combine the new luminance layer with the original color layer to obtain the enhanced image.
Preferably, the step S2 uses image separation based on the HSI model to combine the separated saturation and hue components into a color layer and the intensity component as a luminance layer.
Preferably, in the image separation using the HSI-based model,
wherein
In the above formula, H, S, I is the component of the HSI color model, and R, G, B is the component of the image in the RGB model.
Preferably, the step S4 further includes converting the HSI model into the RGB model after recombining the new luminance layer and the separated color layer of the original image, so as to obtain the enhanced image.
Preferably, the obtaining of the new luminance layer according to the adaptive smoothing algorithm in the step S2 includes the following steps:
selecting a part of pixel points on the brightness layer separated in the step S2 according to a bionic spiral path to be used as an image for estimating the illumination intensity;
the brightness value of a single point in the final enhanced image depends on the result after comparison with the surrounding pixel points on the specific path, and iteration is carried out for multiple times.
Preferably, the path for selecting a part of the pixel points adopts an archimedean spiral, and the equation of the path points is as follows:
t∈[0,kπ]
in the formula, fix is an integer function, (x, y) are coordinates of pixel points of the image path, w and h are width and height of the image pixels, n represents density degree of the spiral, and k is the number of turns of the spiral.
Preferably, after the comparison of the single point brightness value with the point on the path is completed, the resulting difference is denoted as ri(x,y)；
After one iteration is completed, the following results can be obtained:
in the formula, ri(x, y) is the result of the last iteration, ri' (x, y) is ri(x, y) and the sum of the luminance differences;
wherein Δ f is the brightness difference of a single point on the path, and max is the maximum value of the brightness values of the pixels in the original image; after i iterations, ri+1And (x, y) is the brightness value of the enhanced image.
On the other hand, the invention also provides an illumination compensation method based on the bionic spiral, which comprises the following steps:
step S10, acquiring the brightness value of each pixel point of the original image;
step S20, selecting a part of pixel points according to the path of the Archimedes spiral as an image of estimated illumination;
and step S30, comparing the brightness values of the pixel points selected on the path with the central pixel point, and iterating for multiple times to obtain the brightness value of the final image.
Preferably, the archimedean spiral equation is as follows:
t∈[0,kπ]
in the formula, fix is an integer function, (x, y) are coordinates of pixel points of the image path, w and h are width and height of the image pixels, n represents density degree of the spiral, and k is the number of turns of the spiral.
Preferably, after the comparison of the single point brightness value with the point on the path is completed, the resulting difference is denoted as ri(x,y)；
After one iteration is completed, the following results can be obtained:
in the formula, ri(x, y) is the result of the last iteration, ri' (x, y) is ri(x, y) and the sum of the luminance differences;
wherein Δ f is the brightness difference of a single point on the path, and max is the maximum value of the brightness values of the pixels in the original image; after i iterations, ri+1And (x, y) is the brightness value of the enhanced image.
Through the technical scheme, the pixel extraction path based on the Archimedes spiral can acquire the illumination change of the image as much as possible on the premise of acquiring fewer pixel points.
Drawings
Fig. 1 is a schematic diagram of the illumination compensation step of the image enhancement method of the present invention.
Fig. 2 is an archimedean spiral path diagram for use with the image enhancement method of the invention.
Fig. 3 is the image enhancement result using the conventional Retines algorithm and the image enhancement method of the present invention, respectively.
Fig. 4(a) -4 (b) are low-illuminance image enhancement results using the image enhancement method of the present invention.
Fig. 5(a) is the image gradation histogram of fig. 4 (a).
Fig. 5(b) is the image gradation histogram of fig. 4 (b).
Detailed Description
As shown in fig. 1, the present invention provides an image enhancement method based on retinex theory, which includes the following steps:
step S1, acquiring an original image to be processed;
step S2, separating a brightness layer and a color layer of the image, wherein the color layer is the original attribute retention of the object; the brightness layer contains illumination information to be processed independently;
step S3, performing bionic spiral illumination analysis on the brightness layer, and obtaining a new brightness layer according to a self-adaptive smoothing algorithm;
step S4, combine the new luminance layer with the original color layer to obtain the enhanced image.
Those skilled in the art will understand that the original image to be processed acquired in step S1 is typically a color image, but the present invention is not limited thereto. The original image acquired in step S1 may also be a grayscale image with a large dynamic range.
Preferably, the step S2 uses image separation based on the HSI model to combine the separated saturation and hue components into a color layer and the intensity component as a luminance layer.
Preferably, in the image separation using the HSI-based model,
wherein:
in the above formula, H, S, I is the component of the HSI color model, and R, G, B is the component of the image in the RGB model.
Preferably, the step S4 further includes converting the HIS model into an RGB model after recombining the new luminance layer and the separated color layer of the original image, so as to obtain the enhanced image.
Preferably, the obtaining of the new luminance layer according to the adaptive smoothing algorithm in the step S2 includes the following steps:
selecting a part of pixel points on the brightness layer separated in the step S2 according to a bionic spiral path to be used as an image for estimating the illumination intensity;
the brightness value of a single point in the final enhanced image depends on the result after comparison with the surrounding pixel points on the specific path, and iteration is carried out for multiple times.
Preferably, the path for selecting a part of the pixel points adopts an archimedean spiral.
In nature, archimedean spirals are widely available due to their excellent properties. Photosynthesis is particularly important in climbing plants such as morning glory, wisteria, iris and the like. Therefore, the optimal path for climbing the plants is to utilize the minimum material and the minimum energy consumption so that the stems and the leaves can be maximally irradiated by sunlight in the largest area, and the climbing paths of the plants are all often spiral. Similarly, the wheel-shaped phyllotaxy of plants such as tobacco forms a spiral surface which can obtain the maximum illumination area from a narrow space in the gap of other plants.
Inspired by the widely existing spiral in nature, when image illumination analysis is carried out, the invention adopts Archimedes spiral on the path selection for extracting the image illumination condition, as shown in FIG. 2, the path point equation is as follows:
t∈[0,kπ]
in the formula, fix is an integer function, (x, y) are coordinates of pixel points of the image path, w and h are width and height of the image pixels, n represents density degree of the spiral, and k is the number of turns of the spiral.
Preferably, after the comparison of the single point brightness value with the point on the path is completed, the resulting difference is denoted as ri(x,y)；
After one iteration is completed, the following results can be obtained:
in the formula, ri(x, y) is the result of the last iteration, ri' (x, y) is ri(x, y) and the sum of the luminance differences;
wherein Δ f is the brightness difference of a single point on the path, and max is the maximum value of the brightness values of the pixels in the original image; after i iterations, ri+1And (x, y) is the brightness value of the enhanced image.
Fig. 3 shows the image enhancement results under different illumination conditions proposed for the operation panel by using the conventional Retinex algorithm and the image enhancement method of the present invention. As can be seen from fig. 3, the image quality can be improved to a certain extent by using the conventional Retinex algorithm, but the image enhancement method of the present invention has certain advantages compared with the conventional Retinex algorithm, which is specifically represented as follows:
a) under the conditions of uniform illumination and moderate intensity, the results of the traditional Retinex algorithm and the image enhancement method are approximately the same.
b) When the light is in the reverse direction, the whole original image is dark, and details such as keys on a panel are not clearly displayed; the adoption of the traditional Retinex algorithm can improve the detail presentation conditions of a key knob and the like on an operation panel, but the color distortion is more serious; the method of the invention has the advantages of clear details on the back panel, obvious contrast and improved color fidelity.
c) When local strong light reflection exists in the image, the image details of the original image near the reflection position are not obvious; partial details can be recovered by adopting the traditional Retinex algorithm, but the image can generate halo; after the image enhancement method is adopted, the contrast at the details is more obvious, and the halo is reduced.
d) When there is a shadow in the image, the original image cannot display details at the dark area; however, both the conventional Retinex and the image enhancement method of the present invention can highlight the information of the dark area, and the two image enhancement results are similar.
The processing time statistics is performed on 8 pictures by using the conventional Retinex algorithm and the image enhancement method of the present invention, respectively, as shown in Table 1. By comparing the processing time of the two methods, the processing time is shortened by 24.81% by adopting the improved Retinex algorithm compared with the traditional Retinex algorithm.
TABLE 1
Therefore, the traditional Retinex algorithm and the image enhancement method have certain effects on removing the illumination influence in the image, the contrast of the image is enhanced, the details are more obvious, and the brightness is more uniform. However, in some cases, color distortion and halo generation may occur by using the conventional Retinex algorithm, and the image enhancement method of the present invention can reduce the color distortion and halo generation. Moreover, the image enhancement method of the invention has shorter processing time compared with the traditional algorithm.
As shown in fig. 4(a) -4 (b), fig. 4(a) is an image acquired when the illumination intensity is too low, and fig. 4(b) is a picture enhanced by the image enhancement method of the present invention. Each picture is divided into two parts, and the upper left corner part is local amplification in a dotted line identification area of the right complete image. The image is integrally seen, after the image enhancement method is used, the color information of an object is enhanced, the contrast and the brightness are obviously improved, and the color is rich and natural; as can be seen from the local enlargement of the upper left corner of the image, the image enhancement method can enable the image to express more information quantity and the detail texture to be clearer.
The gradation histograms of the images before and after the above processing are shown in fig. 5(a) -5 (b). Fig. 5(a) is a gray level histogram of the original image, in which the gray levels of most of the pixels are concentrated within a range of gray levels less than 90, and the image is dark as a whole. And fig. 5(b) is an image processed by the image enhancement method of the present invention, the distribution of the gray values is relatively even, and the contrast between the object and the background in the image is enhanced, which is beneficial to the identification of the specific object.
Claims (4)
1. An image enhancement method based on retinex theory comprises the following steps:
step S1, acquiring an original image to be processed;
step S2, separating a brightness layer and a color layer of the image, wherein the color layer is the original attribute retention of the object; the brightness layer contains illumination information to be processed independently;
step S3, performing bionic spiral illumination analysis on the brightness layer, and obtaining a new brightness layer according to a self-adaptive smoothing algorithm;
step S4, combining the new brightness layer and the original color layer to obtain the enhanced image;
the step S2 combines the separated saturation and hue components into a color layer using image separation based on the HSI model, and takes the intensity component as a luminance layer;
the obtaining of the new luminance layer according to the adaptive smoothing algorithm in the step S3 includes the following steps:
on the brightness layer separated in the step S2, selecting a part of pixel points according to the bionic spiral path as an image for estimating illuminance, thereby improving the operation efficiency;
the brightness value of a single point in the final enhanced image depends on the result after comparison with the surrounding pixel points on the specific path, and iteration is carried out for multiple times, so that the brightness of the bright part of the image is reduced, and the brightness of the shadow part of the image is increased;
the path for selecting a part of pixel points adopts Archimedes spiral, and the path point equation is as follows:
t∈[0,kπ]
in the formula, fix is an integer function, (x, y) are coordinates of pixel points of an image path, w and h are width and height of the image pixel, n represents density degree of a spiral, and k is the number of turns of spiral rotation;
after the comparison of the single point brightness values with the points on the path is completed, the resulting difference is denoted ri(x,y)；
After one iteration is completed, the following results can be obtained:
in the formula, ri(x, y) is the result of the last iteration, ri' (x, y) is ri(x, y) and the sum of the luminance differences;
wherein Δ f is the brightness difference of a single point on the path, and max is the maximum value of the brightness values of the pixels in the original image; after i iterations, ri+1And (x, y) is the brightness value of the enhanced image.
2. The method of claim 1, wherein in the image separation using HSI-based model,
wherein
In the above formula, H, S, I is the component of the HSI color model, and R, G, B is the component of the image in the RGB model.
3. The method of claim 1 or 2, wherein the step S4 further includes converting the HIS model into an RGB model after recombining the new luminance layer and the color layer separated from the original image, so as to obtain the enhanced image.
4. An illumination compensation method based on a bionic spiral comprises the following steps:
step S10, acquiring the brightness value of each pixel point of the original image;
step S20, selecting a part of pixel points according to the path of the Archimedes spiral as an image for estimating the illumination intensity, thereby improving the operation efficiency;
step S30, comparing the brightness value of the pixel point selected on the path with the brightness value of the central pixel point, and iterating for multiple times to obtain the brightness value of the final image, so that the brightness of the bright part of the image is reduced, and the brightness of the shadow part is increased;
the Archimedes' spiral equation is as follows:
t∈[0,kπ]
in the formula, fix is an integer function, (x, y) are coordinates of pixel points of an image path, w and h are width and height of the image pixel, n represents density degree of a spiral, and k is the number of turns of spiral rotation;
after the comparison of the single point brightness values with the points on the path is completed, the resulting difference is denoted ri(x,y)；
After one iteration is completed, the following results can be obtained:
in the formula, ri(x, y) is the result of the last iteration, ri' (x, y) is ri(x, y) and the sum of the luminance differences;
wherein Δ f is the brightness difference of a single point on the path, and max is the maximum value of the brightness values of the pixels in the original image; after i iterations, ri+1And (x, y) is the brightness value of the enhanced image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810342902.1A CN108550124B (en) | 2018-04-17 | 2018-04-17 | Illumination compensation and image enhancement method based on bionic spiral |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810342902.1A CN108550124B (en) | 2018-04-17 | 2018-04-17 | Illumination compensation and image enhancement method based on bionic spiral |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108550124A CN108550124A (en) | 2018-09-18 |
| CN108550124B true CN108550124B (en) | 2021-03-02 |
Family
ID=63515353
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810342902.1A Active CN108550124B (en) | 2018-04-17 | 2018-04-17 | Illumination compensation and image enhancement method based on bionic spiral |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108550124B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109567849B (en) * | 2018-12-07 | 2022-09-23 | 余姚市恒正金属制品有限公司 | Positron emission CT imager |
| CN109785263B (en) * | 2019-01-14 | 2022-09-16 | 北京大学深圳研究生院 | Retinex-based inverse tone mapping image conversion method |
| CN111291839A (en) * | 2020-05-09 | 2020-06-16 | 创新奇智(南京)科技有限公司 | Sample data generation method, device and equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110062244A (en) * | 2009-12-03 | 2011-06-10 | 인하대학교 산학협력단 | Method for enhancing contrast based on adaptive gamma |
| CN102332154A (en) * | 2011-10-18 | 2012-01-25 | 中国农业大学 | Method and system for enhancing color images of cotton pseudo foreign fibers under non-uniform illumination |
| CN102779330A (en) * | 2012-06-13 | 2012-11-14 | 京东方科技集团股份有限公司 | Image reinforcement method, image reinforcement device and display device |
| CN103593830A (en) * | 2013-11-29 | 2014-02-19 | 大连理工大学 | Low-light video image reinforcing method |
| CN106078748A (en) * | 2016-06-13 | 2016-11-09 | 北京理工大学 | A kind of robot based on hands, eye, arm coordinated manipulation captures the control method of object |
-
2018
- 2018-04-17 CN CN201810342902.1A patent/CN108550124B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110062244A (en) * | 2009-12-03 | 2011-06-10 | 인하대학교 산학협력단 | Method for enhancing contrast based on adaptive gamma |
| CN102332154A (en) * | 2011-10-18 | 2012-01-25 | 中国农业大学 | Method and system for enhancing color images of cotton pseudo foreign fibers under non-uniform illumination |
| CN102779330A (en) * | 2012-06-13 | 2012-11-14 | 京东方科技集团股份有限公司 | Image reinforcement method, image reinforcement device and display device |
| CN103593830A (en) * | 2013-11-29 | 2014-02-19 | 大连理工大学 | Low-light video image reinforcing method |
| CN106078748A (en) * | 2016-06-13 | 2016-11-09 | 北京理工大学 | A kind of robot based on hands, eye, arm coordinated manipulation captures the control method of object |
Non-Patent Citations (1)
| Title |
|---|
| 基于Retinex理论的图像增强算法研究;李莹;《中国优秀硕士学位论文全文数据库信息科技辑》;20140915(第9期);第24-25页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108550124A (en) | 2018-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Veluchamy et al. | Image contrast and color enhancement using adaptive gamma correction and histogram equalization | |
| Huang et al. | Efficient contrast enhancement using adaptive gamma correction with weighting distribution | |
| Lee et al. | Adaptive multiscale retinex for image contrast enhancement | |
| Gupta et al. | Minimum mean brightness error contrast enhancement of color images using adaptive gamma correction with color preserving framework | |
| Singh et al. | Image enhancement via median-mean based sub-image-clipped histogram equalization | |
| Singh et al. | Image enhancement using exposure based sub image histogram equalization | |
| CN102129673B (en) | Color digital image enhancing and denoising method under random illumination | |
| CN104268843B (en) | Image self-adapting enhancement method based on histogram modification | |
| CN102222328B (en) | Edge-preserving self-adaptive weighted filtering method for natural scene images | |
| Wang et al. | Variational single nighttime image haze removal with a gray haze-line prior | |
| US9396526B2 (en) | Method for improving image quality | |
| CN108022223B (en) | Tone mapping method based on logarithm mapping function blocking processing fusion | |
| CN110706172B (en) | Low-illumination color image enhancement method based on adaptive chaotic particle swarm optimization | |
| CN108550124B (en) | Illumination compensation and image enhancement method based on bionic spiral | |
| CN106709504B (en) | High fidelity tone mapping method for detail preservation | |
| CN111968041A (en) | Self-adaptive image enhancement method | |
| CN108898564A (en) | A kind of high dynamic range image tone mapping method based on visual model and WLS filter | |
| CN103839245B (en) | The Retinex colour-image reinforcing method at night of Corpus--based Method rule | |
| CN107256539B (en) | Image sharpening method based on local contrast | |
| Feng et al. | Low-light color image enhancement based on Retinex | |
| CN112308793A (en) | Novel method for enhancing contrast and detail of non-uniform illumination image | |
| JP5327766B2 (en) | Memory color correction in digital images | |
| CN114429426B (en) | Low-illumination image quality improvement method based on Retinex model | |
| Sandeepa et al. | Standard intensity deviation approach based clipped sub image histogram equalization algorithm for image enhancement | |
| Asadi et al. | Improving dark channel prior for single image dehazing |
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 |