CN106485674A - A kind of low light image Enhancement Method based on integration technology - Google Patents
A kind of low light image Enhancement Method based on integration technology Download PDFInfo
- Publication number
- CN106485674A CN106485674A CN201610838870.5A CN201610838870A CN106485674A CN 106485674 A CN106485674 A CN 106485674A CN 201610838870 A CN201610838870 A CN 201610838870A CN 106485674 A CN106485674 A CN 106485674A
- Authority
- CN
- China
- Prior art keywords
- component
- represent
- image
- subgraph
- low light
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000005516 engineering process Methods 0.000 title claims abstract description 13
- 230000010354 integration Effects 0.000 title claims abstract description 6
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 4
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 7
- 238000004040 coloring Methods 0.000 abstract description 2
- 238000005728 strengthening Methods 0.000 abstract description 2
- 238000012545 processing Methods 0.000 description 9
- 238000001914 filtration Methods 0.000 description 4
- 230000002708 enhancing effect Effects 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- KBPHJBAIARWVSC-RGZFRNHPSA-N lutein Chemical compound C([C@H](O)CC=1C)C(C)(C)C=1\C=C\C(\C)=C\C=C\C(\C)=C\C=C\C=C(/C)\C=C\C=C(/C)\C=C\[C@H]1C(C)=C[C@H](O)CC1(C)C KBPHJBAIARWVSC-RGZFRNHPSA-N 0.000 description 3
- 229960005375 lutein Drugs 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- KBPHJBAIARWVSC-XQIHNALSSA-N trans-lutein Natural products CC(=C/C=C/C=C(C)/C=C/C=C(C)/C=C/C1=C(C)CC(O)CC1(C)C)C=CC=C(/C)C=CC2C(=CC(O)CC2(C)C)C KBPHJBAIARWVSC-XQIHNALSSA-N 0.000 description 3
- FJHBOVDFOQMZRV-XQIHNALSSA-N xanthophyll Natural products CC(=C/C=C/C=C(C)/C=C/C=C(C)/C=C/C1=C(C)CC(O)CC1(C)C)C=CC=C(/C)C=CC2C=C(C)C(O)CC2(C)C FJHBOVDFOQMZRV-XQIHNALSSA-N 0.000 description 3
- 235000008210 xanthophylls Nutrition 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000010437 gem Substances 0.000 description 1
- 230000009931 harmful effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—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
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of low light image Enhancement Method based on integration technology, including:Use FCRepresent the colored low light image of input, wherein subscript C represents R, G, B triple channel, calculates and irradiate component L1With reflecting component RC:Using contrast-limited histogram equalizing method CLAHE to L1Processed, obtain contrast and strengthen result figure L2;Stretching L1The low grayscale portion of image, compresses high grade grey level part, result L3Represent;Calculate and irradiate component weighting subgraph, the weighting subgraph of chromatic component;Calculate synthesis weighted graph;Synthesize new irradiation component map;Reconstruct enhanced coloured image.The present invention can effectively strengthen low light image, while strengthening picture contrast, can preferably retain the colouring information of original image, significantly improve the visual quality of image.
Description
Technical field
The present invention relates to color image enhancement technology, more particularly, to it is directed to the enhancement techniques of low light image.
Background technology
Digital camera and the intelligent terminal with camera function, have become as most-often used in people's daily life
One of consumption electronic product.People can shoot all kinds of photos and video record using this kind equipment whenever and wherever possible, and they are given
Our life brings convenient and happy.People are frequently encountered by light weaker situation when shooting, and the intensity of light source is relatively
Weak and block the main cause being to lead to this kind of situation to occur.In digital imaging arts, this kind of situation is referred to as " low light level ".?
The photo photographing under low light condition or the usual visual quality of video be not generally good, such as has that contrast is low, is faint in color, secretly
Region loss in detail etc..
Industry mainly adopts image enhancement technique at present, the initial data obtaining from imageing sensor is strengthened, carries
The visual quality of hi-vision, suppresses low light level effects.The existing low light level is fought for technology and is broadly divided into three classes, that is, be based on histogrammic
Method, the method based on image filtering and the method based on Retinex theory.Straight to original image based on histogrammic method
Square figure enters line translation so that the rectangular histogram after processing has specific shape, such as approaches uniformity distribution.Conventional technology includes
Histogram equalization (HE) [1], contrast limited adaptive histogram equalization (CLAHE) [2] etc..This kind of method amount of calculation is little, can
To effectively improve the contrast of image, but there is also contrast strengthen excessively, noise is exaggerated and the deficiency such as cross-color.Base
Method in image filtering adopts classical spatial domain or frequency domain filtering technology, and input picture is decomposed into general picture (corresponding to low frequency
Composition) and details (corresponding to high fdrequency components) two parts, then as needed, different components are respectively processed.Conventional
Technology includes sharpening [3] and homomorphic filtering [4] etc..This kind of method can be remarkably reinforced the details composition of image, but amount of calculation is relatively
Greatly, contrast raising is inconspicuous.Retinex is theoretical to regard image as irradiate component and reflecting component product, leads to the low light level
The main cause that situation occurs is that exposure rate is uneven.Irradiate component and reflecting component by separating, component is irradiated in adjustment
Realize the purpose of image enhaucament.Single scale Retinex (SSR) [5] and multiple dimensioned Retinex (MSR) [6] be two kinds representational
Retinex method.This kind of method can effectively improve the contrast of image with city, but the image after processing is it sometimes appear that color
Distortion situation.Zhu Hong et al. is in a kind of patent of invention " nighttime image enhancing method with high Xanthophyll cycle " (grant number
CN101783963B, in), disclose a kind of nighttime image enhancing method with high Xanthophyll cycle.The method by input picture from
RGB colorimetric system is transformed in HSV colour system, the H of retaining color information and channel S information, and only luminance channel V is entered with column hisgram broadening
Process, then be transformed into RGB colorimetric system from HSV colour system and shown, obtain enhanced nighttime image.
List of references:
[1].Y.T.Kim,Contrast enhancement using brightness preserving bi-
histogramequalization,IEEE Trans.Consumer Electronics,43(1)(1997)1-8..
[2].Zuiderveld Karel,"Contrast limited adaptive histogram
equalization",Graphics gems IV,Academic Press Professional,Inc.,1994,pp.474–
485
[3].G.Deng,A generalized unsharp masking algorithm,IEEE Transaction
On Image Processing, 2011,20 (5), 1249-1261.
[4].R.C.Gonzalez,R.E.Woods,Digital Image Processing(3rd),Prentice-
Hall,Englewood Cliffs,NJ,USA,2010.
[5].D.J.Jobson,Z.U.Rahman,G.A.Woodell,Properties and performance of a
center/surround Retinex,IEEE Transaction on Image Processing,1996,6(3):451-
462.
[6].D.J.Jobson,Z.U.Rahman,G.A.Woodell,A multi-scale Retinex for
bridging the gap between color images and the human observation of scenes,
IEEE Transaction on Image Processing,1997,6(7),965-976.
[7]. Authorization Notice No.:CN101783963B, a kind of nighttime image enhancing method with high Xanthophyll cycle, invention
People:Zhu Hong, 2012.
Content of the invention
The present invention proposes a kind of low light image Enhancement Method based on integration technology and shoots under low light environment it is therefore an objective to improve
The visual quality of images arriving.Technical scheme is as follows:
A kind of low light image Enhancement Method based on integration technology, including following method:
1) use FCRepresent the colored low light image of input, wherein subscript C represents R, G, B triple channel, calculates and irradiate component L1,
It is called subgraph 1, and reflecting component RC:
RC(x, y)=FC(x,y)/L1(x,y) (2)
Wherein, FRRepresent red component, FGRepresent green component, FBRepresent blue component, FC、L1And RCSpan all
Between [0,1];
2) use contrast-limited histogram equalizing method CLAHE to L1Processed, obtain contrast and strengthen result figure
L2, claim its subgraph 2;
3) use non-linear Signoid function, stretch L1The low grayscale portion of image, compresses high grade grey level part, place
Reason result L3Represent, be called subgraph 3, that is, have:
In formula, parameter lambda is used for controlling the level of stretch to low gray level, calculates λ using following formula:
In formula, LmeanIt is L1Average;
4) use following formula to calculate and irradiate component weighting subgraph, use WL,k(x, y) represents
WL,k(x, y)=exp { -8 (Lk(x,y)-0.5)2} (5)
In formula, k={ 1,2,3 }, represent the sequence number of three described width subgraphs,
5) use following formula to calculate the weighting subgraph of chromatic component, use WC,k(x, y) represents
WC,k(x, y)=Lk(x,y)exp{-6(S(x,y)-1)2} (6)
In formula, S (x, y) is defined as:
6) use WL,k(x, y) and WC,k(x, y), calculates LkCorresponding synthesis weighted graph, uses Wk(x, y) represents, that is, have
Wk(x, y)=WL,k(x,y)+WC,k(x,y) (8)
7) use Wk(x, y) calculates LkCorresponding normalization weighted graph, usesRepresent, that is, have
8) use LkAnd corresponding weighting subgraphSynthesize new irradiation component map, use Lfus(x, y) represents, that is, have
9) use Lfus(x, y) and RC, reconstruct enhanced coloured image, use FenhRepresent, that is, have
Fenh,C(x, y)=RC(x.y)Lfus(x,y) (11)
The present invention can effectively strengthen low light image, while strengthening picture contrast, can preferably retain former
There is the colouring information of image, significantly improve the visual quality of image.In addition, the computation complexity of the method is not high, disclosure satisfy that
The requirement of real-time processing.
Brief description
Fig. 1 is the flow chart of institute's extracting method
Fig. 2 processing procedure exemplary plot (a) artwork (b) L1(c)L2(d)L3 (h)Lfus(i)Fenh
Fig. 3 distinct methods result contrast (a) each figure of row is artwork (b) each figure of row is that CLAHE method (c) each figure of row is
MSRCR method (d) each figure of row is PS method (e) row each figure institute of the present invention extracting method
Specific embodiment
Institute's extracting method includes 4 steps:Estimate to irradiate component, construction sub-irradiation quantum figure, calculate weighted graph, image weight
Structure.What Fig. 1 gave the inventive method realizes block diagram.
1st, estimate to irradiate component
The low-luminance color image (being represented with F) of input can be regarded as irradiating component (being represented with L) and reflecting component (is used
R represents) product form, that is, have F=L × R.Wherein, irradiate component and reflect the illumination condition of image each several part, reflecting component
Reflect the reflection characteristic of each object in image.Illumination condition is not good to be to cause the mainly former of low light image visual quality decline
Cause, can be by being modified suppressing the harmful effect of illumination condition to irradiation component.
Need to be estimated according to input picture to irradiate component.Use FCRepresent input color low light image, wherein subscript C represents
R, G, B triple channel.Institute's extracting method calculates irradiation component using following formula and (uses L1Represent) and reflecting component (use RCRepresent):
RC(x, y)=FC(x,y)/L1(x,y) (2)
Wherein, FC、L1And RCSpan all between [0,1].
2nd, construct sub-irradiation quantum figure
The inventive method needs several to have the sub-irradiation quantum figure of different qualities to synthesize new irradiation component map.From former
Irradiation component map L can be directly obtained in beginning image1.For low light image, L1There is contrast low, dark areas details is inconspicuous
Situations such as.Institute's extracting method improves L by histogram equalization1Contrast, and using nonlinear transformation strengthen L1Middle dark areas details
Part, obtains different sub-irradiation quantum figures.
First, using classical contrast-limited histogram equalization (CLAHE) technology [2] to L1Processed, it is right to obtain
Strengthen result figure than degree, use L2Represent.
Then, using non-linear Signoid function, stretch L1The low grayscale portion of image, compresses high grade grey level part.
Result L3Represent, that is, have:
In formula, parameter lambda is used for controlling the level of stretch to low gray level.Calculate λ using following formula:
In formula, LmeanIt is L1Average.
3rd, calculate weighted graph
When calculating weighted graph, irradiation component and reflecting component two aspect factor to be considered.Calculated using following formula and shine
Penetrate component weighting subgraph, use WL,k(x, y) represents
WL,k(x, y)=exp { -8 (Ik(x,y)-0.5)2} (5)
In formula, k={ 1,2,3 }, represent the sequence number of three width sub-irradiation quantum figures.
Calculate the weighting subgraph of chromatic component using following formula, use WC,k(x, y) represents
WC,k(x, y)=Lk(x,y)exp{-6(S(x,y)-1)2} (6)
In formula, S (x, y) is defined as:
Using WL,k(x, y) and WC,k(x, y), calculates LkCorresponding synthesis weighted graph, uses Wk(x, y) represents, that is, have
Wk(x, y)=WL,k(x,y)+WC,k(x,y) (8)
Using Wk(x, y) calculates LkCorresponding normalization weighted graph, usesRepresent, that is, have
4th, image reconstruction
Using LkAnd corresponding weighting subgraphSynthesize new irradiation component map, use Lfus(x, y) represents, that is, have
Using Lfus(x, y) and RC, reconstruct enhanced coloured image, use FenhRepresent, that is, have
Fenh,C(x, y)=RC(x.y)Lfus(x,y) (11)
Using the matlab2015b under Windows7SP1 system as experiment simulation platform.From patent applicant from mutual
The 80 width low-light (level) images downloaded in networking are as test set.Using method proposed by the present invention, test image is processed,
Obtain good treatment effect.For the image of 800 × 600 sizes, using the process time average out to 15ms of institute's extracting method,
Processing speed disclosure satisfy that the requirement of real-time.Fig. 2 gives more results, is input picture on the left of in figure, right side
It is the result being obtained using the inventive method.Fig. 3 gives the process contrast knot of the inventive method and other three class methods
Really.CLAHE method, MSRCR method and Photoshop (being abbreviated as PS) have been selected in control methods.From comparing result,
The contrast of CLAHE method result is obviously improved, but the situation of enhanced image generally existing tonal distortion;MSRCR
The tone of method result and contrast all increase, but colourity has obvious supersaturation situation, and distortion is obvious;PS side
Method result is similar with CLAHE method, and result is inconspicuous.The inventive method can improve the contrast of image very well,
While prominent dark space information, also preferably maintain the hue information of original image, and supersaturation situation does not occur.
Above-mentioned test result indicate that, using the inventive method, the contrast of low light image can be effectively improved hence it is evident that improve
The visual quality of image, and the requirement of real-time is disclosure satisfy that using the time needed for computer disposal.
Claims (1)
1. a kind of low light image Enhancement Method based on integration technology, including following method:
1) use FCRepresent the colored low light image of input, wherein subscript C represents R, G, B triple channel, calculates and irradiate component L1, claim it
For subgraph 1, and reflecting component RC:
RC(x, y)=FC(x,y)/L1(x,y) (2)
Wherein, FRRepresent red component, FGRepresent green component, FBRepresent blue component, FC、L1And RCSpan all exist
[0,1] between;
2) use contrast-limited histogram equalizing method CLAHE to L1Processed, obtain contrast and strengthen result figure L2, claim
Its subgraph 2;
3) use non-linear Signoid function, stretch L1The low grayscale portion of image, compresses high grade grey level part, result
Use L3Represent, be called subgraph 3, that is, have:
In formula, parameter lambda is used for controlling the level of stretch to low gray level, calculates λ using following formula:
In formula, LmeanIt is L1Average;
4) use following formula to calculate and irradiate component weighting subgraph, use WL,k(x, y) represents
WL,k(x, y)=exp { -8 (Lk(x,y)-0.5)2} (5)
In formula, k={ 1,2,3 }, represent the sequence number of three described width subgraphs,
5) use following formula to calculate the weighting subgraph of chromatic component, use WC,k(x, y) represents
WC,k(x, y)=Lk(x,y)exp{-6(S(x,y)-1)2} (6)
In formula, S (x, y) is defined as:
6) use WL,k(x, y) and WC,k(x, y), calculates LkCorresponding synthesis weighted graph, uses Wk(x, y) represents, that is, have
Wk(x, y)=WL,k(x,y)+WC,k(x,y) (8)
7) use Wk(x, y) calculates LkCorresponding normalization weighted graph, usesRepresent, that is, have
8) use LkAnd corresponding weighting subgraphSynthesize new irradiation component map, use Lfus(x, y) represents, that is, have
9) use Lfus(x, y) and RC, reconstruct enhanced coloured image, use FenhRepresent, that is, have
Fenh,C(x, y)=RC(x.y)Lfus(x,y) (11).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610838870.5A CN106485674A (en) | 2016-09-20 | 2016-09-20 | A kind of low light image Enhancement Method based on integration technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610838870.5A CN106485674A (en) | 2016-09-20 | 2016-09-20 | A kind of low light image Enhancement Method based on integration technology |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106485674A true CN106485674A (en) | 2017-03-08 |
Family
ID=58268703
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610838870.5A Pending CN106485674A (en) | 2016-09-20 | 2016-09-20 | A kind of low light image Enhancement Method based on integration technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106485674A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107424124A (en) * | 2017-03-31 | 2017-12-01 | 北京臻迪科技股份有限公司 | A kind of image enchancing method and device |
CN109345586A (en) * | 2018-11-02 | 2019-02-15 | 国网湖南省电力有限公司 | Electrical equipment discharge characteristic extracting method based on ultraviolet imagery technology |
CN110163818A (en) * | 2019-04-28 | 2019-08-23 | 武汉理工大学 | A kind of low illumination level video image enhancement for maritime affairs unmanned plane |
CN110796607A (en) * | 2018-08-03 | 2020-02-14 | 北京大学 | Deep learning low-illumination image enhancement method based on retina cerebral cortex theory |
WO2020143670A1 (en) * | 2019-01-08 | 2020-07-16 | 电信科学技术研究院有限公司 | Voice dereverberation method and device |
CN113344804A (en) * | 2021-05-11 | 2021-09-03 | 湖北工业大学 | Training method of low-light image enhancement model and low-light image enhancement method |
CN116894793A (en) * | 2023-09-08 | 2023-10-17 | 南京道成网络科技有限公司 | Method and device for enhancing image quality |
US11995808B2 (en) | 2020-09-04 | 2024-05-28 | Abova, Inc | Method for X-ray dental image enhancement |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102750682A (en) * | 2012-07-17 | 2012-10-24 | 中国矿业大学(北京) | Image preprocessing method for processing nonuniform illumination of miner face image and coal surface |
US20150312540A1 (en) * | 2014-04-29 | 2015-10-29 | Uygar Tuna | Automatic white balancing with chromaticity measure of raw image data |
CN105654437A (en) * | 2015-12-24 | 2016-06-08 | 广东迅通科技股份有限公司 | Enhancement method for low-illumination image |
-
2016
- 2016-09-20 CN CN201610838870.5A patent/CN106485674A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102750682A (en) * | 2012-07-17 | 2012-10-24 | 中国矿业大学(北京) | Image preprocessing method for processing nonuniform illumination of miner face image and coal surface |
US20150312540A1 (en) * | 2014-04-29 | 2015-10-29 | Uygar Tuna | Automatic white balancing with chromaticity measure of raw image data |
CN105654437A (en) * | 2015-12-24 | 2016-06-08 | 广东迅通科技股份有限公司 | Enhancement method for low-illumination image |
Non-Patent Citations (3)
Title |
---|
XUEYANG FU 等: "A fusion-based enhancing approach for single sandstorm image", 《2014 IEEE 16TH INTERNATIONAL WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING (MMSP)》 * |
XUEYANG FU 等: "A fusion-based enhancing method for weakly illuminated images", 《SIGNAL PROCESSING》 * |
王建 等: "基于CLAHE的X射线行李图像增强", 《天津大学学报》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107424124A (en) * | 2017-03-31 | 2017-12-01 | 北京臻迪科技股份有限公司 | A kind of image enchancing method and device |
CN107424124B (en) * | 2017-03-31 | 2020-03-17 | 北京臻迪科技股份有限公司 | Image enhancement method and device |
CN110796607A (en) * | 2018-08-03 | 2020-02-14 | 北京大学 | Deep learning low-illumination image enhancement method based on retina cerebral cortex theory |
CN110796607B (en) * | 2018-08-03 | 2022-07-22 | 北京大学 | Deep learning low-illumination image enhancement method based on retina cerebral cortex theory |
CN109345586A (en) * | 2018-11-02 | 2019-02-15 | 国网湖南省电力有限公司 | Electrical equipment discharge characteristic extracting method based on ultraviolet imagery technology |
WO2020143670A1 (en) * | 2019-01-08 | 2020-07-16 | 电信科学技术研究院有限公司 | Voice dereverberation method and device |
CN110163818A (en) * | 2019-04-28 | 2019-08-23 | 武汉理工大学 | A kind of low illumination level video image enhancement for maritime affairs unmanned plane |
US11995808B2 (en) | 2020-09-04 | 2024-05-28 | Abova, Inc | Method for X-ray dental image enhancement |
CN113344804A (en) * | 2021-05-11 | 2021-09-03 | 湖北工业大学 | Training method of low-light image enhancement model and low-light image enhancement method |
CN116894793A (en) * | 2023-09-08 | 2023-10-17 | 南京道成网络科技有限公司 | Method and device for enhancing image quality |
CN116894793B (en) * | 2023-09-08 | 2023-11-28 | 南京道成网络科技有限公司 | Method and device for enhancing image quality |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106485674A (en) | A kind of low light image Enhancement Method based on integration technology | |
Wang et al. | Adaptive image enhancement method for correcting low-illumination images | |
CN105046663B (en) | A kind of adaptive enhancement method of low-illumination image for simulating human visual perception | |
Shi et al. | Let you see in sand dust weather: A method based on halo-reduced dark channel prior dehazing for sand-dust image enhancement | |
CN106846282B (en) | A kind of enhancement method of low-illumination image using adaptively correcting | |
CN103593830B (en) | A kind of low illumination level video image enhancement | |
CN106504212A (en) | A kind of improved HSI spatial informations low-luminance color algorithm for image enhancement | |
CN107798661B (en) | Self-adaptive image enhancement method | |
CN106886985A (en) | A kind of self adaptation enhancement method of low-illumination image for reducing colour cast | |
Vonikakis et al. | Multi-exposure image fusion based on illumination estimation | |
Liu et al. | Low-light video image enhancement based on multiscale retinex-like algorithm | |
CN108416745A (en) | A kind of image adaptive defogging Enhancement Method with color constancy | |
CN102903081A (en) | Low-light image enhancement method based on red green blue (RGB) color model | |
CN106651817A (en) | Non-sampling contourlet-based image enhancement method | |
Fang et al. | A method to improve the image enhancement result based on image fusion | |
Peng et al. | Multi-algorithm fusion of RGB and HSV color spaces for image enhancement | |
Parihar et al. | A comprehensive analysis of fusion-based image enhancement techniques | |
Lal et al. | Automatic method for contrast enhancement of natural color images | |
Wen et al. | A survey of image dehazing algorithm based on retinex theory | |
CN109493289A (en) | One kind having brightness and saturation degree Double Nonlinear image enchancing method | |
Tang et al. | Color image enhancement based on retinex theory with guided filter | |
Yu et al. | Color constancy-based visibility enhancement in low-light conditions | |
Mirza et al. | Enhancement of the underwater images using modified retinex algorithm | |
Singh et al. | Spatial domain color image enhancement based on local processing | |
Toh et al. | Implementation of high dynamic range rendering on acute leukemia slide images using contrast stretching |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170308 |