CN109493291A - A kind of method for enhancing color image contrast ratio of adaptive gamma correction - Google Patents
A kind of method for enhancing color image contrast ratio of adaptive gamma correction Download PDFInfo
- Publication number
- CN109493291A CN109493291A CN201811265104.XA CN201811265104A CN109493291A CN 109493291 A CN109493291 A CN 109493291A CN 201811265104 A CN201811265104 A CN 201811265104A CN 109493291 A CN109493291 A CN 109493291A
- Authority
- CN
- China
- Prior art keywords
- image
- adaptive gamma
- lightness
- gamma correction
- distribution function
- 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
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000002708 enhancing effect Effects 0.000 title claims abstract description 21
- 238000005315 distribution function Methods 0.000 claims abstract description 18
- 230000001186 cumulative effect Effects 0.000 claims abstract description 6
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims 1
- 238000001514 detection method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 206010047531 Visual acuity reduced Diseases 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011426 transformation method 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
- G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Processing Of Color Television Signals (AREA)
Abstract
The invention discloses a kind of method for enhancing color image contrast ratio of adaptive gamma correction, method includes the following steps: 1, the calculating of lightness image is done to the image to be reinforced of input;2, probability density function and weight distribution function are calculated using lightness image;3, the cumulative distribution function of weight distribution function is calculated;4, adaptive gamma parameter is constructed, and adaptive Gamma correction is carried out to lightness image;5, enhanced result images are obtained after the image after correction being converted back RGB color space.The present invention can make the enhancing of picture contrast be adaptive to image pixel intensities, and enhanced image is more natural, and can enhance Image Warping.
Description
Technical field
The present invention relates to a kind of method for enhancing picture contrast more particularly to a kind of color images of adaptive Gamma correction
Contrast enhancement process.
Background technique
Undesirable shooting environmental, such as rainy weather, indoor light are inadequate, will lead to the image pair that people take
Decline than degree, scene and some minutias of object all can not be showed clearly in image, generate poor vision effect
Fruit.If directly such image is applied in the application of the view-based access control models such as target detection, target tracking, it will cause detection or chase after
The inaccuracy of track result.
Method for enhancing picture contrast mainly has the method based on transformation and the method based on histogram.Side based on transformation
Method, to adjust the image pixel intensities of output image, reaches raising image by doing certain mathematic(al) manipulation, such as exponential transform to image
The purpose of contrast.Improve picture contrast based on the method for histogram by adjusting the histogram distribution of original image, so
And such methods do integrated regulation to picture contrast, often bring some unnatural pseudomorphisms.Shih-Chia Huang etc.
People propose it is a kind of based on adaptive gamma correction contrast enhancement process (Shih-Chia Huang, Fan-Chieh Cheng,
Yi-Sheng Chiu, Efficient contrast enhancement using adaptive gamma correction
with weighting distribution,IEEE Transactions on Image Processing,vol.22,
No.3, pp.1032-1041,2013), the method based on transformation and the method based on histogram are combined, original image is done
The phenomenon that adaptive gamma correction enhances picture contrast, but bright areas usually will appear excessive enhancing, and have ignored part
The enhancing of region contrast.
Summary of the invention
Goal of the invention: for problem and shortage existing for above-mentioned existing method, the present invention provides a kind of increasing for making image
It is adaptive to image pixel intensities by force and the method for enhancing picture contrast of Image Warping can be enhanced, take full advantage of image slices
The demographic information of plain intensity.
Technical solution: for achieving the above object, a kind of the used following technical scheme of the present invention: adaptive gamma school
Positive method for enhancing color image contrast ratio, by the way that image is transformed into the color space HSV from RGB color space come separate picture
Color information and lightness information, adaptive gamma parameter is constructed by the cumulative distribution function of weight distribution function, makes to compare
Image is more natural after degree enhancing.
Specific step is as follows for the method for enhancing color image contrast ratio of the adaptive Gamma correction:
It (1) is the color image to be reinforced of M × N pixel to the size of inputThe calculating of lightness image is done, it willFrom RGB color
Space is transformed into the color space HSV, and the image pixel intensities of V channel image are all normalized in [0,255] section and obtain lightness figure
As I;
(2) probability density function and weight distribution function are calculated using lightness image, respectively shown in following formula (1) (2):
Wherein, l is lightness image pixel intensity, pdfmaxIt is the largest probability density, pdfminIt is the smallest probability density,α is parameter;
(3) cumulative distribution function for calculating weight distribution function, as shown in formula (3):
Wherein,lmaxIt is the maximum image pixel intensities of lightness image;
(4) adaptive gamma parameter is constructed, shown in following formula (4):
Wherein, a and b is adjustment parameter,I is lightness image, and Ω (x) is to be with pixel x
The size at center is the neighborhood of w × h pixel.
Adaptive Gamma correction is carried out to lightness image based on adaptive gamma parameter, makes lightness image adaptive gamma school
Image pixel intensities after just, image pixel intensities are following formula (5):
Wherein, lmaxIt is maximum image pixel intensities in I;
(5) using the lightness image after correction as the channel V, make itself and original channel S and the channel H together from HSV colour
Space converts back RGB color space, obtains enhanced result images.
The utility model has the advantages that compared with prior art, the invention has the following advantages that the adaptive pixel of 1, contrast enhancing is strong
Degree, so that enhanced image is more natural;It 2, can be according to the ratio processing image office of pixel and its neighborhood territory pixel mean intensity
Portion's contrast.
Detailed description of the invention
Fig. 1 is the implementation flow chart of invention;
Fig. 2 (a) is image 1 to be reinforced in embodiment, and Fig. 2 (b) is in embodiment to the enhanced result images of image 1;
Fig. 3 (a) is the histogram of the lightness image of Fig. 2 (a) in embodiment, and Fig. 3 (b) is the lightness of Fig. 2 (b) in embodiment
The histogram of image;
Fig. 4 (a) is image 2 to be reinforced in embodiment, and Fig. 4 (b) is in embodiment to the enhanced result images of image 2;
Fig. 5 (a) is the histogram of the lightness image of Fig. 4 (a) in embodiment, and Fig. 5 (b) is the lightness of Fig. 4 (b) in embodiment
The histogram of image.
Specific embodiment
Further description of the technical solution of the present invention with reference to the accompanying drawings and examples.
As shown in Figure 1, a kind of method for enhancing color image contrast ratio of adaptive Gamma correction, comprising the following steps:
(1) lightness image is done to the image to be reinforced of input to calculate:
Used in this embodiment size for the color image of 512 × 768 pixels and 360 × 236 pixels respectively as to
Enhancing image 1 and image to be reinforced 2 are tested.2 images to be reinforced are transformed into HSV colour from RGB color space respectively
The image pixel intensities of V channel image are all normalized in [0,255] section and obtain lightness image by space.
(2) probability density function and weight distribution function are calculated using lightness image, function formula difference is as follows:
Probability density function
Weight distribution function
Wherein, l is lightness image pixel intensity, pdfmaxIt is the largest probability density, pdfminIt is the smallest probability density,α is parameter, and the present invention takes α=0.6.
(3) cumulative distribution function for calculating weight distribution function, shown in following formula:
Wherein,lmaxIt is the maximum image pixel intensities of lightness image.
(4) adaptive gamma parameter is constructed, and to lightness image adaptive Gamma correction, is specifically comprised the following steps:
(4.1) it constructs shown in the adaptive following formula of gamma parameter:
Wherein, a and b be adjustment parameter, a=0.5, b=0.3,I is lightness image, Ω (x)
It is the neighborhood of 5 × 5 pixels for the size centered on pixel x.
(4.2) adaptive Gamma correction is carried out to lightness image based on adaptive gamma parameter, makes lightness image adaptive
Image pixel intensities after gamma correction, image pixel intensities are following formula:
Wherein, lmaxIt is maximum image pixel intensities in I;
(5) using the lightness image after adaptive gamma correction as the channel V and original channel S and the channel H together from HSV
Color space conversion returns RGB color space, obtains enhanced result images.
As shown in Fig. 2 (a) and Fig. 4 (a), two image overall contrast ratios to be reinforced are lower, and some darker regions are thin
It saves unintelligible.Fig. 3 (a) and Fig. 5 (a) is respectively the histogram of the lightness image of two images to be reinforced, can from histogram
To find out that pixel distribution compares concentration, and the pixel in low tonal range is more.Fig. 2 (b) is that the method for the present invention handles Fig. 2
(a) result images obtained after, image overall contrast ratio enhances as can be seen from Figure, and prospect is shown clearly with background area.Fig. 4 (b)
The result images obtained after Fig. 4 (a) are handled for the method for the present invention, the image in vehicle window restores presentation well as can be seen from Figure
Out, the details such as personage's hair, leaf are also enhanced.From the histogram of the lightness image of result images, i.e. Fig. 3 (b) and
It can also be seen that pixel distribution is more more balanced than original in Fig. 5 (b).
Claims (6)
1. a kind of method for enhancing color image contrast ratio of adaptive gamma correction, it is characterised in that comprising steps of
(1) lightness image is done to the image to be reinforced of input to calculate;
(2) probability density function and weight distribution function are calculated using lightness image;
(3) cumulative distribution function of weight distribution function is calculated;
(4) adaptive gamma parameter is constructed, and adaptive Gamma correction is carried out to lightness image;
(5) image after correction is converted back into RGB color space, obtains enhanced result images.
2. a kind of method for enhancing color image contrast ratio of adaptive gamma correction according to claim 1, feature exist
In: in step (1), the lightness image is calculated are as follows: is the color image to be reinforced of M × N pixel by a width sizeFrom
RGB color space is transformed into the color space HSV, and the image pixel intensities of V channel image are all normalized in [0,255] section and are obtained
Lightness image I.
3. a kind of method for enhancing color image contrast ratio of adaptive gamma correction according to claim 1, feature exist
In: in step (2), the probability density function and weight distribution function are respectively formula (1) and (2):
Wherein, l is lightness image pixel intensity, pdfmaxIt is the largest probability density, pdfminIt is the smallest probability density,α is parameter.
4. a kind of method for enhancing color image contrast ratio of adaptive gamma correction according to claim 1, feature exist
In: in step (3), the cumulative distribution function of the weight distribution function is following formula:
Wherein,lmaxIt is the maximum image pixel intensities of lightness image.
5. a kind of method for enhancing color image contrast ratio of adaptive gamma correction according to claim 1, feature exist
In: in step (4), the adaptive gamma correction of construction is following formula:
Wherein, a and b is adjustment parameter, and I is lightness image, and Ω (x) is that the size centered on pixel x is w × h pixel
Neighborhood, γ (x) are adaptive gamma parameter, the image pixel intensities after T (x) correction, lmaxIt is maximum image pixel intensities in I.
6. a kind of method for enhancing color image contrast ratio of adaptive gamma correction according to claim 1, feature exist
In: in step (5), the described picture conversion are as follows: using the lightness image after adaptive gamma correction as the channel V, make its with
Original channel S and the channel H returns RGB color space from HSV color space conversion together.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811265104.XA CN109493291A (en) | 2018-10-29 | 2018-10-29 | A kind of method for enhancing color image contrast ratio of adaptive gamma correction |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811265104.XA CN109493291A (en) | 2018-10-29 | 2018-10-29 | A kind of method for enhancing color image contrast ratio of adaptive gamma correction |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109493291A true CN109493291A (en) | 2019-03-19 |
Family
ID=65691749
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811265104.XA Pending CN109493291A (en) | 2018-10-29 | 2018-10-29 | A kind of method for enhancing color image contrast ratio of adaptive gamma correction |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109493291A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110599415A (en) * | 2019-08-29 | 2019-12-20 | 西安电子科技大学 | Image contrast enhancement implementation method based on local adaptive gamma correction |
CN110728718A (en) * | 2019-09-29 | 2020-01-24 | 上海电力大学 | Method for improving calibration parameters of camera |
CN112598607A (en) * | 2021-01-06 | 2021-04-02 | 安徽大学 | Endoscope image blood vessel enhancement algorithm based on improved weighted CLAHE |
CN112785532A (en) * | 2021-01-12 | 2021-05-11 | 安徽大学 | Singular value equalization image enhancement algorithm based on weighted histogram distribution gamma correction |
CN113870141A (en) * | 2021-10-08 | 2021-12-31 | 成都医学院 | Color fundus image enhancement method |
CN114037615A (en) * | 2021-09-03 | 2022-02-11 | 南京泓众电子科技有限公司 | Self-adaptive panoramic image enhancement method and device |
CN115018741A (en) * | 2022-06-07 | 2022-09-06 | 成都微光集电科技有限公司 | Image processing method and device |
CN115131336A (en) * | 2022-07-22 | 2022-09-30 | 电子科技大学 | Dark line defect detection method under four-color background picture of display screen |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103413275A (en) * | 2013-07-26 | 2013-11-27 | 北京工业大学 | Retinex night image enhancement method based on gradient zero norm minimum |
CN103973941A (en) * | 2014-05-14 | 2014-08-06 | 深圳市大疆创新科技有限公司 | Method and system for adjusting dynamic contrast of digital image or video |
CN104268843A (en) * | 2014-10-16 | 2015-01-07 | 桂林电子科技大学 | Image self-adaptation enhancing method based on histogram modification |
CN104700376A (en) * | 2014-11-25 | 2015-06-10 | 桂林电子科技大学 | Gamma correction and smoothing filtering based image histogram equalization enhancing method |
CN107358592A (en) * | 2017-09-08 | 2017-11-17 | 哈尔滨理工大学 | A kind of iterative global method for adaptive image enhancement |
-
2018
- 2018-10-29 CN CN201811265104.XA patent/CN109493291A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103413275A (en) * | 2013-07-26 | 2013-11-27 | 北京工业大学 | Retinex night image enhancement method based on gradient zero norm minimum |
CN103973941A (en) * | 2014-05-14 | 2014-08-06 | 深圳市大疆创新科技有限公司 | Method and system for adjusting dynamic contrast of digital image or video |
CN104268843A (en) * | 2014-10-16 | 2015-01-07 | 桂林电子科技大学 | Image self-adaptation enhancing method based on histogram modification |
CN104700376A (en) * | 2014-11-25 | 2015-06-10 | 桂林电子科技大学 | Gamma correction and smoothing filtering based image histogram equalization enhancing method |
CN107358592A (en) * | 2017-09-08 | 2017-11-17 | 哈尔滨理工大学 | A kind of iterative global method for adaptive image enhancement |
Non-Patent Citations (2)
Title |
---|
WANG, LQ 等: "Video Enhancement Using Temporal-Spatial Total Variation Retinex and Luminance Adaptation", 《5TH IEEE INTERNATIONAL CONFERENCE ON PROGRESS IN INFORMATICS AND COMPUTING (PIC)》 * |
王力谦: "基于变分正则化与统计学习的低质图像质量提升方法", 《中国优秀博士学位论文信息科技辑》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110599415A (en) * | 2019-08-29 | 2019-12-20 | 西安电子科技大学 | Image contrast enhancement implementation method based on local adaptive gamma correction |
CN110599415B (en) * | 2019-08-29 | 2023-11-10 | 西安电子科技大学 | Image contrast enhancement implementation method based on local self-adaptive gamma correction |
CN110728718A (en) * | 2019-09-29 | 2020-01-24 | 上海电力大学 | Method for improving calibration parameters of camera |
CN110728718B (en) * | 2019-09-29 | 2023-08-22 | 上海电力大学 | Method for improving camera calibration parameters |
CN112598607B (en) * | 2021-01-06 | 2022-11-18 | 安徽大学 | Endoscope image blood vessel enhancement algorithm based on improved weighted CLAHE |
CN112598607A (en) * | 2021-01-06 | 2021-04-02 | 安徽大学 | Endoscope image blood vessel enhancement algorithm based on improved weighted CLAHE |
CN112785532A (en) * | 2021-01-12 | 2021-05-11 | 安徽大学 | Singular value equalization image enhancement algorithm based on weighted histogram distribution gamma correction |
CN112785532B (en) * | 2021-01-12 | 2022-11-18 | 安徽大学 | Singular value equalization image enhancement algorithm based on weighted histogram distribution gamma correction |
CN114037615A (en) * | 2021-09-03 | 2022-02-11 | 南京泓众电子科技有限公司 | Self-adaptive panoramic image enhancement method and device |
CN113870141A (en) * | 2021-10-08 | 2021-12-31 | 成都医学院 | Color fundus image enhancement method |
CN115018741A (en) * | 2022-06-07 | 2022-09-06 | 成都微光集电科技有限公司 | Image processing method and device |
CN115131336A (en) * | 2022-07-22 | 2022-09-30 | 电子科技大学 | Dark line defect detection method under four-color background picture of display screen |
CN115131336B (en) * | 2022-07-22 | 2023-11-14 | 电子科技大学 | Dark line defect detection method under four-color background picture of display screen |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109493291A (en) | A kind of method for enhancing color image contrast ratio of adaptive gamma correction | |
CN110599415B (en) | Image contrast enhancement implementation method based on local self-adaptive gamma correction | |
CN104240194B (en) | A kind of enhancement algorithm for low-illumination image based on parabolic function | |
CN108765336B (en) | Image defogging method based on dark and bright primary color prior and adaptive parameter optimization | |
CN106897981A (en) | A kind of enhancement method of low-illumination image based on guiding filtering | |
Wang et al. | Variational single nighttime image haze removal with a gray haze-line prior | |
CN109872285A (en) | A kind of Retinex low-luminance color image enchancing method based on variational methods | |
CN111968065B (en) | Self-adaptive enhancement method for image with uneven brightness | |
CN101930596A (en) | Color constancy method in two steps under a kind of complex illumination | |
CN102682436A (en) | Image enhancement method on basis of improved multi-scale Retinex theory | |
CN109447917B (en) | Remote sensing image haze eliminating method based on content, characteristics and multi-scale model | |
CN103714520A (en) | Digital video image enhancement achieving system and method based on FPGA | |
CN111968041A (en) | Self-adaptive image enhancement method | |
CN109919859A (en) | A kind of Outdoor Scene image defogging Enhancement Method calculates equipment and its storage medium | |
KR101774735B1 (en) | Method for improvement of shadow area around car number plate and car number recognition | |
CN111476725A (en) | Image defogging enhancement algorithm based on gradient domain oriented filtering and multi-scale Retinex theory | |
CN107392879B (en) | A kind of low-light (level) monitoring image Enhancement Method based on reference frame | |
CN106651817A (en) | Non-sampling contourlet-based image enhancement method | |
CN105913400A (en) | Device for obtaining high-quality and real-time beautiful image | |
CN115660964A (en) | Nighttime road image enhancement method based on threshold partition weighted brightness component | |
CN109801233A (en) | A kind of Enhancement Method suitable for true color remote sensing image | |
CN104915933B (en) | A kind of Misty Image Enhancement Method based on APSO-BP coupling algorithm | |
CN110111280B (en) | Low-illumination image enhancement method for multi-scale gradient domain guided filtering | |
CN108550124B (en) | Illumination compensation and image enhancement method based on bionic spiral | |
CN104463806A (en) | Highly adaptive image contrast enhancing method based on data driving technology |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190319 |