CN106127694A - The self adaptation two-way guarantor bandwidth logarithmic transformation method of uneven illumination image enhaucament - Google Patents
The self adaptation two-way guarantor bandwidth logarithmic transformation method of uneven illumination image enhaucament Download PDFInfo
- Publication number
- CN106127694A CN106127694A CN201610340343.1A CN201610340343A CN106127694A CN 106127694 A CN106127694 A CN 106127694A CN 201610340343 A CN201610340343 A CN 201610340343A CN 106127694 A CN106127694 A CN 106127694A
- Authority
- CN
- China
- Prior art keywords
- image
- logarithmic transformation
- conversion
- bandwidth
- guarantor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000005286 illumination Methods 0.000 title claims abstract description 17
- 230000006978 adaptation Effects 0.000 title claims abstract description 13
- 238000011426 transformation method Methods 0.000 title claims abstract description 10
- 230000009466 transformation Effects 0.000 claims abstract description 91
- 238000006243 chemical reaction Methods 0.000 claims abstract description 63
- 230000008901 benefit Effects 0.000 claims abstract description 5
- 230000000295 complement effect Effects 0.000 claims description 12
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 abstract description 5
- 230000000694 effects Effects 0.000 abstract description 4
- 238000000034 method Methods 0.000 description 29
- 238000001228 spectrum Methods 0.000 description 7
- 230000000007 visual effect Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000007812 deficiency Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013441 quality evaluation Methods 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G06T5/73—Deblurring; Sharpening
-
- 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
- G06T2207/20048—Transform domain processing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
A kind of self adaptation two-way guarantor bandwidth logarithmic transformation method of uneven illumination image enhaucament, it is characterised in that comprise the following steps: step 1: the image that Input illumination is uneven, and this image is standardized conversion;Step 2: mean flow rate AL of image after normalized conversion, and this image carried out two-way guarantor's bandwidth logarithmic transformation according to the value of AL: if AL < 127.5, the most reversely protect bandwidth logarithmic transformation, then carry out forward and protect bandwidth logarithmic transformation;Otherwise, the most first carry out forward and protect bandwidth logarithmic transformation, more reversely protect bandwidth logarithmic transformation;Step 3: round conversion;Step 4: output image.The invention have the characteristics that have enhancing dark space contrast and the advantage of clear zone contrast, reinforced effects is obvious, and background retains good, entirely without halation phenomenon, makes picture quality obtain overall enhancing.
Description
Technical field
The invention belongs to digital image processing field, relate to a kind of quality enhancement method to uneven illumination image.
Background technology
Owing to the contrast sensitivity of too high or too low luminance picture is reduced by human vision, so needing crossing dark or mistake
Bright image (or region) carries out contrast enhancing, in order to its details of perception.And the image of uneven illumination, existing highlight bar of crossing has again
Too low dark space, general method effect is bad, and have there is also halation phenomenon.
At present, use and counting method is strengthened picture quality, be widely used in image procossing every field and ground
Study carefully.In disclosed patent, such as: keep the defogging method (application number: CN101754032A) of color, a kind of reduction synthetic aperture thunder
Reach the method (application number: CN101398487A) of smudges noise, the self-adapting enhancement method of a kind of degraded image under water
(CN104766285A), etc..These methods be all use unidirectional (forward) logarithmic transformation as image pre-processing method, in conjunction with
Mist elimination, denoising, the additive method such as anhydrate are for image enhaucament, and computational methods are complicated, process the time long, can strengthen non-primary image
Information contained by.
In the document delivered, the document relating to image log conversion is more, mainly has LIP (logarithmic
Image processing) family's (referring to various deformation and improvement based on LIP) method and RETINEX family (refer to
Various deformation and improvement based on RETINEX) method.The unidirectional logarithmic transformation that these methods are the most only by, can only pull open
Distance between the spectral line of gray/color spectrum (or referred to as rectangular histogram) low side (dark space), thus image low side (dark space) can only be improved
Contrast, reach the purpose of picture superposition.Meanwhile, they also comprise the calculating of two image subtractions, it is possible to create negative
Data, destroy the positive definite feature of image, and may introduce in source images and non-existent additional information, destroy fidelity
Property, cause composition distortion.
Therefore, the defect that counting method carries out image enhaucament used at present is without reference to how improving high-end (clear zone)
Contrast, and do not increase information contained in artwork (emphasizing fidelity).
Summary of the invention
It is an object of the invention to provide a kind of two-way guarantor of self adaptation for the visual quality of images enhancing of uneven illumination to carry
Wide logarithmic transformation method, can not only improve the contrast of dark space, moreover it is possible to improves the contrast in clear zone, does not produce halation phenomenon,
Reach preferably and do not increase the effect of image information image enhaucament.
To achieve the object of the present invention, the present invention proposes the self adaptation two-way guarantor bandwidth pair of a kind of uneven illumination image enhaucament
Transformation of variables method, it it is critical only that and comprises the following steps:
Step 1: the image that Input illumination is uneven, and this image is standardized conversion, scheme after obtaining standardized transformation
Picture;
The method of standardized transformation sees " the generation method of standardized images " (publication number: CN102800062A).Standard
After changing conversion, image becomes the image with full bandwidth characteristic.This is the basis that the present invention implements.
Step 2: mean flow rate AL of image after normalized conversion, and according to the value of AL, this image is carried out two-way guarantor
Bandwidth logarithmic transformation:
Mean flow rate AL is the auto-adaptive parameter of the present invention, different with image difference, it is not necessary to manually to set.
Described two-way guarantor's bandwidth logarithmic transformation, is protected bandwidth logarithmic transformation by forward and reverse bandwidth logarithmic transformation of protecting forms,
The truth of a matter of described logarithmic transformation is 1.02198395689;
If AL < 127.5, the most reversely protect bandwidth logarithmic transformation, then carry out forward guarantor's bandwidth logarithmic transformation;
Otherwise, the most first carry out forward and protect bandwidth logarithmic transformation, more reversely protect bandwidth logarithmic transformation;
Step 3: the image after two-way guarantor's bandwidth logarithmic transformation is rounded conversion;
After image carries out two-way guarantor's bandwidth logarithmic transformation, the gray/color value of image becomes real number, it is impossible to meets image and shows
The requirement shown, it is therefore desirable to carry out rounding conversion, becomes integer by the gray/color value of image.Round conversion and use four houses five
The mode entered.
Step 4: output image.
Described forward is protected bandwidth logarithmic transformation and is carried out in the following manner:
Step one: to need to convert image f (x, y) carries out moving to right conversion, obtain the image F after moving to right conversion (x, y);
Described move to right conversion carry out as the following formula:
F (x, y)=SHIFTR1 [f (x, y)] and=f (x, y)+1
Wherein, SHIFTR1 [] represents the displacement operator moving to right 1 along x-axis;(x, y), (x y) is INTEGER MATRICES to f to F;f
(x, y) in the codomain of element be 0~255, F (x, y) in the codomain of element become 1~256;
Step 2: (x, y) carries out forward logarithmic transformation, after obtaining forward logarithmic transformation by moving to right the image F after conversion
Image
Described forward logarithmic transformation is carried out as the following formula:
Wherein, LOGa[] represents the operator taking the logarithm with a as the end;It it is real number matrix;A=
1.02198395689。
Described reverse guarantor's bandwidth logarithmic transformation is carried out in the following manner:
Step one: to need to convert image f (x, y) carry out mend conversion, it is thus achieved that complement as Ψ (x, y);
Described benefit conversion is carried out as the following formula:
Ψ (x, y)=255-f (x, y)
Wherein, (x, y), (x, y) is INTEGER MATRICES to f to Ψ, and in two INTEGER MATRICES, the codomain of element is 0~255;
Step 2: to complement as Ψ (x, y) carries out moving to right conversion, obtain the image F1 after moving to right conversion (x, y);
Described move to right conversion carry out as the following formula:
F1 (x, y)=SHIFTR1 [Ψ (x, y)] and=Ψ (x, y)+1
Wherein, SHIFTR1 [] represents the displacement operator moving to right 1 along x-axis;(x, y) is INTEGER MATRICES to F1, the value of element
Territory becomes 1~256;
Step 3: (x, y) carries out forward logarithmic transformation, after obtaining forward logarithmic transformation by moving to right the image F1 after conversion
Image
Described forward logarithmic transformation is carried out as the following formula:
Wherein, LOGa[] represents the operator taking the logarithm with a as the end;It it is real number matrix;A=
1.02198395689;
Step 4 is rightCarry out mending conversion by step one, obtain positive image.
Described positive image is for complement picture.Without the image mending conversion, it is believed that be positive image, to complement picture
Again carrying out mending conversion, obtain is also positive image.
The gray/color of the pixel of general digital picture is at 0~255 value (so-called 8 systems), the table of logarithm of 0
Show uncertainty, so needing gradation of image/colourity spectrum is moved to right conversion, to eliminate logarithmic transformation before doing logarithmic transformation
Uncertain.After moving to right conversion, the span of the gray/color value of image becomes 1~256 from 0~255.
Logarithmic transformation along the forward of x-axis is referred to as forward logarithmic transformation.Forward logarithmic transformation has increase gray/color spectrum low
The function of end (dark picture areas) contrast.
Logarithmic transformation along the negative sense of x-axis is referred to as reverse logarithmic transformation.Reversely logarithmic transformation has increase gray/color spectrum high
The function of end (image clear zone) contrast.Owing to the forward logarithmic transformation of complement picture is equivalent to the reverse logarithmic transformation of original image,
Therefore, the reverse logarithmic transformation of image can realize by the forward logarithmic transformation of its complement picture, high-end to improve gray/color spectrum
The contrast in (image clear zone).
The bandwidth of the gray/color spectrum of the image after logarithmic transformation changes with the change of logarithm truth of a matter a.Making logarithmic transformation
Time, take truth of a matter a=1.02198395689, be the determiner realizing protecting bandwidth.
When following table gives a value difference, M=Loga256 and the Different Results of bandwidth:
As can be seen from the above table, a=1.02198395689 is a special logarithm truth of a matter, moves to right image after conversion
After as the logarithmic transformation at the end, low side contrast promotes, and has automatically generated the operation moving to left, and gray/color spectrum is also
Former one-tenth original tape wide 0~255.
The special logarithmic transformation with a=1.02198395689 as the end of image, is referred to as protecting bandwidth logarithmic transformation.Keep 0~
The maximum bandwidth of 255 provides for the probability with maximum-contrast.
The remarkable result of the present invention is: utilize standardized transformation, mean flow rate to calculate, move to right conversion, become by forward logarithm
The guarantor's bandwidth change the two-way logarithmic transformation formed with reverse logarithmic transformation, being realized by the truth of a matter selecting logarithm converts this several sides
Method, has carried out good potentiation to the image of uneven illumination.The method not only has enhancing dark space contrast and clear zone pair
The ratio advantage of degree, reinforced effects is obvious, and background retains good, entirely without halation phenomenon, makes picture quality obtain overall increasing
By force.
Accompanying drawing explanation
The flow chart of Fig. 1 present invention;
Fig. 2 (a-1), (b-1), (c-1) are the source images in embodiment 1;
Fig. 2 (a-2), (b-2), (c-2) are that Fig. 2 (a-1), (b-1), (c-1) are through self adaptation two-way guarantor bandwidth logarithm respectively
Image after alternative approach conversion;
Fig. 2 (a-3), (b-3), (c-3) be Fig. 2 (a-1), (b-1), (c-1) through Zadeh-X (see the Chinese invention patent " end
Tomographic image obtains the method for best quality image in excavating ", publication number: CN101419707) the enhanced image of method.
Detailed description of the invention
With specific embodiment, the present invention is described in further detail below in conjunction with the accompanying drawings.
Embodiment 1: flow process as shown in Figure 1: the self adaptation two-way guarantor bandwidth logarithm of a kind of uneven illumination image enhaucament becomes
Change method, comprise the following steps:
Step 1: the image that Input illumination is uneven, and this image is standardized conversion, scheme after obtaining standardized transformation
Picture;
The method of standardized transformation sees " the generation method of standardized images " (publication number: CN102800062A).
Step 2: mean flow rate AL of image after normalized conversion, and according to the value of AL, this image is carried out two-way guarantor
Bandwidth logarithmic transformation:
Mean flow rate AL is the auto-adaptive parameter of the present invention;
Described two-way guarantor's bandwidth logarithmic transformation, is protected bandwidth logarithmic transformation by forward and reverse bandwidth logarithmic transformation of protecting forms,
The truth of a matter of described logarithmic transformation is 1.02198395689;
If AL < 127.5, the most reversely protect bandwidth logarithmic transformation, then carry out forward guarantor's bandwidth logarithmic transformation;
Otherwise, the most first carry out forward and protect bandwidth logarithmic transformation, more reversely protect bandwidth logarithmic transformation.
Described forward is protected bandwidth logarithmic transformation and is carried out in the following manner:
Step one: to need to convert image f (x, y) carries out moving to right conversion, obtain the image F after moving to right conversion (x, y);
Described move to right conversion carry out as the following formula:
F (x, y)=SHIFTR1 [f (x, y)] and=f (x, y)+1
Wherein, SHIFTR1 [] represents the displacement operator moving to right 1 along x-axis;(x, y), (x y) is INTEGER MATRICES to f to F;f
(x, y) in the codomain of element be 0~255, F (x, y) in the codomain of element become 1~256;
Step 2: (x, y) carries out forward logarithmic transformation, after obtaining forward logarithmic transformation by moving to right the image F after conversion
Image
Described forward logarithmic transformation is carried out as the following formula:
Wherein, LOGa[] represents the operator taking the logarithm with a as the end;It it is real number matrix;A=
1.02198395689。
Described reverse guarantor's bandwidth logarithmic transformation is carried out in the following manner:
Step one: to need to convert image f (x, y) carry out mend conversion, it is thus achieved that complement as Ψ (x, y);
Described benefit conversion is carried out as the following formula:
Ψ (x, y)=255-f (x, y)
Wherein, (x, y), (x, y) is INTEGER MATRICES to f to Ψ, and in two INTEGER MATRICES, the codomain of element is 0~255;
Step 2: to complement as Ψ (x, y) carries out moving to right conversion, obtain the image F1 after moving to right conversion (x, y);
Described move to right conversion carry out as the following formula:
F1 (x, y)=SHIFTR1 [Ψ (x, y)] and=Ψ (x, y)+1
Wherein, SHIFTR1 [] represents the displacement operator moving to right 1 along x-axis;(x, y) is INTEGER MATRICES to F1, the value of element
Territory becomes 1~256;
Step 3: (x, y) carries out forward logarithmic transformation, after obtaining forward logarithmic transformation by moving to right the image F1 after conversion
Image
Described forward logarithmic transformation is carried out as the following formula:
Wherein, LOGa[] represents the operator taking the logarithm with a as the end;It it is real number matrix;A=
1.02198395689;
Step 4 is rightCarry out mending conversion by step one, obtain positive image.
Described positive image be relative to complement picture (or referred to as negative image, negative-appearing image, negative film) for.Without the figure mending conversion
Picture, it is believed that be positive image, carries out complement picture mending conversion again, and obtain is also positive image.
Step 3: the image after two-way guarantor's bandwidth logarithmic transformation is rounded conversion;Round what conversion employing rounded up
Mode.
Step 4: output image.
Following table lists figure (a-1), (b-1), (c-1) and they are through the change of self adaptation two-way guarantor bandwidth logarithmic transformation method
Change rear image (a-2), (b-2), (c-2) average information entropy AIE, average contrast AC, mean flow rate AL, image quality evaluation letter
Number CAF, the calculating of above parameter may refer to patent of invention " color image quality evaluation method " (publication number:
CN101650833B):
Image Name | AL | AC | AIE | CAF |
Figure (a-1) | 20.9768 | 1.4426 | 5.2593 | 2.2911 |
Figure (a-2) | 125.0448 | 2.7961 | 5.0680 | 9.4114 |
Figure (b-1) | 55.4095 | 2.3309 | 6.1054 | 9.6815 |
Figure (b-2) | 106.4465 | 3.3353 | 5.8744 | 11.9728 |
Figure (c-1) | 198.2702 | 3.9892 | 5.8298 | 15.6336 |
Figure (c-2) | 138.4668 | 4.6323 | 5.2832 | 16.7722 |
From upper table it will be seen that source images (a-1), (b-1) mean flow rate AL all < 127.5, therefore use the most reversely
Guarantor's bandwidth logarithmic transformation of rear forward.After conversion, (AIE) drops in basic parameter two liters (AC, AL).Visual quality of images strengthens,
The inverse process of natural process (deteriroation of image quality, such as sound pollution, fuzzy, make AIE increase), AIE should reduce and can not
Increase.Visual quality of images evaluating (CAF) raises, and points out total visual quality to increase.
It can also be seen that use the enhanced image of Zadeh-X method to have halation phenomenon (figure (a-3) You Ming from Fig. 2
Aobvious), dark space strengthens deficiency, and background disappears (figure (b-3) is the most obvious).Scheme after the conversion of self adaptation two-way guarantor bandwidth logarithmic transformation method
As (figure (a-2) and figure (b-2)) dark space contrast and brightness strengthen substantially, background retains good, entirely without halation phenomenon, overall
Picture quality is remarkably reinforced.
As shown above, mean flow rate AL of source images (c-1) > 127.5, belong to high brightness (AL=198.2702) illumination
Uneven image.It is thus desirable to use the most reverse guarantor's bandwidth logarithmic transformation, after conversion, the information of image is to reduce
(comentropy from the 5.8298 of source images, reduce to after the conversion of self adaptation two-way guarantor bandwidth logarithmic transformation method the 5.2832 of image),
Because this is inverse natural process.Transformation results visual quality of images evaluating (CAF) raises (15.6336/16.7722), carries
Show that total visual quality increases.Brightness is to reduce (198.2702/138.4668), levels off to ideal value 127.5.
Image shown in Fig. 2 (c-3) has obvious halation phenomenon, and clear zone strengthens deficiency, and contrast is low.Fig. 2 (c-2) substantially carries on the back
Scape contrast strengthens, and entirely without halation phenomenon, overall image quality strengthens.
Claims (3)
1. the self adaptation of a uneven illumination image enhaucament two-way guarantor bandwidth logarithmic transformation method, it is characterised in that include following step
Rapid:
Step 1: the image that Input illumination is uneven, and this image is standardized conversion, obtain image after standardized transformation;
Step 2: mean flow rate AL of image after normalized conversion, and according to the value of AL, this image carried out two-way guarantor's bandwidth
Logarithmic transformation:
Described two-way guarantor's bandwidth logarithmic transformation, is protected bandwidth logarithmic transformation by forward and reverse bandwidth logarithmic transformation of protecting forms, described
The truth of a matter of logarithmic transformation is 1.02198395689;
If AL < 127.5, the most reversely protect bandwidth logarithmic transformation, then carry out forward guarantor's bandwidth logarithmic transformation;
Otherwise, the most first carry out forward and protect bandwidth logarithmic transformation, more reversely protect bandwidth logarithmic transformation;
Step 3: the image after two-way guarantor's bandwidth logarithmic transformation is rounded conversion;
Step 4: output image.
The self adaptation two-way guarantor bandwidth logarithmic transformation method of uneven illumination image enhaucament the most according to claim 1, it is special
Levy and be to comprise the following steps: that described forward is protected bandwidth logarithmic transformation and carried out in the following manner:
Step one: to need to convert image f (x, y) carries out moving to right conversion, obtain the image F after moving to right conversion (x, y);
Described move to right conversion carry out as the following formula:
F (x, y)=SHIFTR1 [f (x, y)]
Wherein, SHIFTR1 [] represents the displacement operator moving to right 1 along x-axis;(x, y), (x y) is INTEGER MATRICES to f to F;f(x,y)
The codomain of middle element is 0~255, F (x, y) in the codomain of element become 1~256;
Step 2: (x, y) carries out forward logarithmic transformation, obtains the image after forward logarithmic transformation by moving to right the image F after conversion
Described forward logarithmic transformation is carried out as the following formula:
Wherein, LOGa[] represents the operator taking the logarithm with a as the end;It it is real number matrix;A=1.02198395689.
The self adaptation two-way guarantor bandwidth logarithmic transformation method of uneven illumination image enhaucament the most according to claim 1, it is special
Levy and be to comprise the following steps: that described reverse guarantor's bandwidth logarithmic transformation is carried out in the following manner:
Step one: to need to convert image f (x, y) carry out mend conversion, it is thus achieved that complement as Ψ (x, y);
Described benefit conversion is carried out as the following formula:
Ψ (x, y)=255-f (x, y)
Wherein, (x, y), (x, y) is INTEGER MATRICES to f to Ψ, and in two INTEGER MATRICES, the codomain of element is 0~255;
Step 2: to complement as Ψ (x, y) carries out moving to right conversion, obtain the image F1 after moving to right conversion (x, y);
Described move to right conversion carry out as the following formula:
F1 (x, y)=SHIFTR1 [Ψ (x, y)]
Wherein, SHIFTR1 [] represents the displacement operator moving to right 1 along x-axis;(x, y) is INTEGER MATRICES to F1, and the codomain of element becomes
It is 1~256;
Step 3: (x, y) carries out forward logarithmic transformation, obtains the image after forward logarithmic transformation by moving to right the image F1 after conversion
Described forward logarithmic transformation is carried out as the following formula:
Wherein, LOGa[] represents the operator taking the logarithm with a as the end;It it is real number matrix;A=
1.02198395689;
Step 4 is rightCarry out mending conversion by step one, obtain positive image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610340343.1A CN106127694B (en) | 2016-05-20 | 2016-05-20 | Adaptive two-way guarantor's bandwidth logarithmic transformation method of uneven illumination image enhancement |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610340343.1A CN106127694B (en) | 2016-05-20 | 2016-05-20 | Adaptive two-way guarantor's bandwidth logarithmic transformation method of uneven illumination image enhancement |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106127694A true CN106127694A (en) | 2016-11-16 |
CN106127694B CN106127694B (en) | 2018-11-09 |
Family
ID=57270689
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610340343.1A Expired - Fee Related CN106127694B (en) | 2016-05-20 | 2016-05-20 | Adaptive two-way guarantor's bandwidth logarithmic transformation method of uneven illumination image enhancement |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106127694B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021114564A1 (en) * | 2019-12-10 | 2021-06-17 | 南京莱斯电子设备有限公司 | Enhancement method for low-contrast infrared image |
CN117314795A (en) * | 2023-11-30 | 2023-12-29 | 成都玖锦科技有限公司 | SAR image enhancement method by using background data |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102314673A (en) * | 2011-08-02 | 2012-01-11 | 中国科学院长春光学精密机械与物理研究所 | Self-adapting image enhancement method |
CN102800062A (en) * | 2012-06-26 | 2012-11-28 | 重庆医科大学 | Standard image generation method |
CN102800061A (en) * | 2012-06-26 | 2012-11-28 | 重庆医科大学 | High-illuminance digital image fast adaptive optimization method |
CN102800060A (en) * | 2012-06-26 | 2012-11-28 | 重庆医科大学 | Quick self-adaption optimizing method for digital image at low illumination level |
CN103985097A (en) * | 2014-05-26 | 2014-08-13 | 中国科学院长春光学精密机械与物理研究所 | Non-uniform illuminance image enhancement method |
-
2016
- 2016-05-20 CN CN201610340343.1A patent/CN106127694B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102314673A (en) * | 2011-08-02 | 2012-01-11 | 中国科学院长春光学精密机械与物理研究所 | Self-adapting image enhancement method |
CN102800062A (en) * | 2012-06-26 | 2012-11-28 | 重庆医科大学 | Standard image generation method |
CN102800061A (en) * | 2012-06-26 | 2012-11-28 | 重庆医科大学 | High-illuminance digital image fast adaptive optimization method |
CN102800060A (en) * | 2012-06-26 | 2012-11-28 | 重庆医科大学 | Quick self-adaption optimizing method for digital image at low illumination level |
CN103985097A (en) * | 2014-05-26 | 2014-08-13 | 中国科学院长春光学精密机械与物理研究所 | Non-uniform illuminance image enhancement method |
Non-Patent Citations (5)
Title |
---|
R.NEERAJHA ET AL.: "IMAGE ENHANCEMENT AND QUALITY ANALYSIS USING THE BIOLOG TRANSFORMATION", 《INTERNATIONAL CONFERENCE ON ENGINEERING TRENDS AND SCIENCE & HUMANITIES》 * |
SHUHANG WANG ET AL.: "Naturalness Preserved Enhancement Algorithm for Non-Uniform Illumination Images", 《IEEE TRANSACTIONS ON IMAGE PROCESSING》 * |
李小霞 等: "一种新的低照度彩色图像增强算法", 《计算机应用研究》 * |
谢正祥 等: "基于视觉感知噪声模型的彩色图像质量评价和彩色图像质量最佳化", 《中国图象图形学报》 * |
陈萌梦 等: "1中视网膜眼底图像增强新方法", 《重庆医科大学学报》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021114564A1 (en) * | 2019-12-10 | 2021-06-17 | 南京莱斯电子设备有限公司 | Enhancement method for low-contrast infrared image |
CN117314795A (en) * | 2023-11-30 | 2023-12-29 | 成都玖锦科技有限公司 | SAR image enhancement method by using background data |
CN117314795B (en) * | 2023-11-30 | 2024-02-27 | 成都玖锦科技有限公司 | SAR image enhancement method by using background data |
Also Published As
Publication number | Publication date |
---|---|
CN106127694B (en) | 2018-11-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108876743B (en) | Image rapid defogging method, system, terminal and storage medium | |
CN108053374B (en) | Underwater image enhancement method combining bilateral filtering and Retinex | |
CN108389175B (en) | Image defogging method integrating variation function and color attenuation prior | |
KR101448164B1 (en) | Method for Image Haze Removal Using Parameter Optimization | |
US8842912B2 (en) | Method for processing highlights and saturated regions in a digital image | |
CN103942758A (en) | Dark channel prior image dehazing method based on multiscale fusion | |
CN114331873B (en) | Non-uniform illumination color image correction method based on region division | |
Guo et al. | Automatic image haze removal based on luminance component | |
CN103985097B (en) | A kind of image enchancing method of Nonuniform illumination | |
CN111861896A (en) | UUV-oriented underwater image color compensation and recovery method | |
Sanila et al. | Underwater image enhancement using white balance, USM and CLHE | |
CN108648160B (en) | Underwater sea cucumber image defogging enhancement method and system | |
Ngo et al. | Nonlinear unsharp masking algorithm | |
Hegde et al. | Adaptive cubic spline interpolation in cielab color space for underwater image enhancement | |
CN110111280B (en) | Low-illumination image enhancement method for multi-scale gradient domain guided filtering | |
Yao et al. | Brightness preserving and contrast limited bi-histogram equalization for image enhancement | |
CN111476744A (en) | Underwater image enhancement method based on classification and atmospheric imaging model | |
CN109345479B (en) | Real-time preprocessing method and storage medium for video monitoring data | |
Muniraj et al. | Underwater image enhancement by modified color correction and adaptive Look-Up-Table with edge-preserving filter | |
CN106127694B (en) | Adaptive two-way guarantor's bandwidth logarithmic transformation method of uneven illumination image enhancement | |
CN105608683A (en) | Defogging method of single image | |
CN117611501A (en) | Low-illumination image enhancement method, device, equipment and readable storage medium | |
CN116630198A (en) | Multi-scale fusion underwater image enhancement method combining self-adaptive gamma correction | |
CN116862809A (en) | Image enhancement method under low exposure condition | |
Guo et al. | An adaptive enhancement algorithm for low-illumination image based on hue reserving |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181109 Termination date: 20190520 |