CN104463800B - A kind of gradation of image Enhancement Method - Google Patents
A kind of gradation of image Enhancement Method Download PDFInfo
- Publication number
- CN104463800B CN104463800B CN201410738404.0A CN201410738404A CN104463800B CN 104463800 B CN104463800 B CN 104463800B CN 201410738404 A CN201410738404 A CN 201410738404A CN 104463800 B CN104463800 B CN 104463800B
- Authority
- CN
- China
- Prior art keywords
- mrow
- image
- msub
- value
- formula
- 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
Abstract
The present invention discloses a kind of gradation of image Enhancement Method, comprises the following steps：Image preprocessing：Denoising is carried out to image；Calculate the global average image and local mean value image of image；Calculate gray scale weights；Global grey level enhancement figure and local grey level enhancement figure are calculated, it is final to obtain grey level enhancement figure.Gradation of image Enhancement Method flexibility proposed by the present invention is strong, using technical scheme region bright in image can be made brighter, dark region is darker so that image seems to become apparent from.
Description
Technical field
The present invention relates to image enhancement technique field, more particularly to a kind of gradation of image Enhancement Method.
Background technology
It is well known that image is the important channel that the mankind obtain visual information.But, image has during acquisition can
Can be influenceed by factors such as imaging device dynamic range size, ambient light powers, cause image occur contrast it is relatively low,
Image information not substantially, the profile of cross-color, target or boundary information the definition phenomenon such as not enough, give mankind's Visual Observations Observations
Difficulty is brought with equipment analysis processing, thus needs to carry out enhancing processing to image.
The content of the invention
It is an object of the invention to by a kind of gradation of image Enhancement Method, mention solving background section above
Problem.
For up to this purpose, the present invention uses following technical scheme：
A kind of gradation of image Enhancement Method, it comprises the following steps：
A, image preprocessing：Denoising is carried out to image；
B, the global average image and local mean value image for calculating image；
C, calculating gray scale weights；
D, the global grey level enhancement figure of calculating and local grey level enhancement figure, it is final to obtain grey level enhancement figure.
Especially, denoising is carried out to image in the step A, specifically included：Image is gone using two-sided filter
Make an uproar.
Especially, gray scale weights described in the step C and pixel value are transformed into monotonic relationshi, and calculating process is as follows：
Wherein, wi,jIt is, according to image local gray value, to be obtained using special function；The special function and current gray level
Value Ii,jWith the gray value Avg at average image midpoint (i, j)i,jThere is relation, pushed away according to the property of exponential function and inverse proportion function
Calculate and obtain, it is specific as follows：
First, the ratio r atio of gray value and average value is calculated by formula (1), and as calculating weights
The truth of a matter of exponential function used：
2nd, the exponent e xp of gray scale weights is calculated for the function of variable using ratio, shown in such as formula (2)；Choosing
Optimal transformation function formula (3) is taken, w is obtained by formula (4)i,j：
Exp=f (ratio), ratio ∈ [0,255] (2)
wi,j=ratioexp (4)。
Especially, the step D is specifically included：According to the gray scale weight w calculated in step Ci,j, obtained by formula (5)
Obtain enhanced gray value Ii,j'：
Ii,j'=wi,j·Ii,j=ratioexp·Ii,j (5)
Meanwhile, also can be respectively with two different size of window averaged Avgi,j, obtain global enhancing gray value and
Local enhancement gray value Ii,j bAnd Ii,j s, the gray value for finally obtaining the pixel by formula (6) is：
Ii,j'=α Ii,j b+(1-α)·Ii,j s (6)
Wherein, α (0≤α≤1) represents to utilize the enhanced figure proportion of big window.
Gradation of image Enhancement Method flexibility proposed by the present invention is strong, can be made using technical scheme in image
Bright region is brighter, and dark region is darker so that image seems to become apparent from.
Brief description of the drawings
Fig. 1 is gradation of image Enhancement Method flow chart provided in an embodiment of the present invention.
Embodiment
The invention will be further described with reference to the accompanying drawings and examples.It is understood that tool described herein
Body embodiment is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that, for the ease of retouching
State, part related to the present invention rather than full content are illustrate only in accompanying drawing, it is unless otherwise defined, used herein all
Technology and scientific terminology it is identical with the implication that is generally understood that of those skilled in the art for belonging to the present invention.Made herein
Term is intended merely to describe the purpose of specific embodiment, it is not intended that in the limitation present invention.
It refer to shown in Fig. 1, Fig. 1 is gradation of image Enhancement Method flow chart provided in an embodiment of the present invention.
Gradation of image Enhancement Method specifically includes following steps in the present embodiment：
S101, image preprocessing：Denoising is carried out to image.
Denoising is carried out to image using two-sided filter.Wherein, two-sided filter (Bilateral filter) is a kind of
The wave filter of side denoising can be protected.Why two-sided filter can reach this denoising effect, be because wave filter is by two
Function is constituted.One function is to determine filter coefficient by geometric space distance.Another determines wave filter system by pixel value difference
Number, i.e., consider the difference of spatial domain and codomain simultaneously.
S102, the global average image and local mean value image for calculating image.Equal is asked to image with a certain size window
Value figure.
S103, calculating gray scale weights, that is, when calculating enhancing gray scale, the gray scale weights multiplied.
In view of image's authenticity, that is, eliminate the problem of dtmf distortion DTMF that image is blocked and caused.During enhancing, for each picture
Element is all multiplied by different gray scale weights, and gray scale weights should be transformed into monotonic relationshi with pixel value.Pass through in the present embodiment
Particular design and test have obtained a transforming function transformation function.Specific conversion process is as follows：
Wherein, wi,jIt is, according to image local gray value, to be obtained using special function；The special function and current gray level
Value Ii,jWith the gray value Avg at average image midpoint (i, j)i,jThere is relation, pushed away according to the property of exponential function and inverse proportion function
Calculate and obtain, it is specific as follows：
First, the ratio r atio of gray value and average value is calculated by formula (1), and is weighed as calculating
The truth of a matter of value exponential function used：
Secondly, the exponent e xp of gray scale weights is calculated for the function of variable using ratio, shown in such as formula (2)；
Optimal transformation function formula (3) is chosen, w is obtained by formula (4)i,j：
Exp=f (ratio), ratio ∈ [0,255] (2)
wi,j=ratioexp (4)
S104, the global grey level enhancement figure of calculating and local grey level enhancement figure, it is final to obtain grey level enhancement figure.
Using gray scale weights, enhancing gray value is calculated, grey level enhancement figure is acquired.According to the gray scale weight w calculatedi,j,
Enhanced gray value I is obtained by formula (5)i,j'：
Ii,j'=wi,j·Ii,j=ratioexp·Ii,j (5)
Meanwhile, in actual applications also can be respectively with two different size of window averaged Avgi,j, obtain global
Strengthen gray value and local enhancement gray value Ii,j bAnd Ii,j s, the gray value of the pixel is finally obtained by formula (6), i.e., it is final
Grey level enhancement figure：
Ii,j'=α Ii,j b+(1-α)·Ii,j s (6)
Wherein, α (0≤α≤1) represents to utilize the enhanced figure proportion of big window.
It should be noted that because said process includes most multiplication and divisions and exponent arithmetic, if each pixel removes meter
It is very poorly efficient at last, in the present embodiment, precompute data result using the method for inquiry table.So, afterwards not
Pipe image size, can directly obtain result, deduplication is calculated no needs again from table.It the experiment proved that, the present invention is in effect
It is all very outstanding on fruit and efficiency.
Technical scheme flexibility is strong, can make region bright in image more using technical scheme
Bright, dark region is darker so that image seems to become apparent from.
Note, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art it is various it is obvious change,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although the present invention is carried out by above example
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (2)
1. a kind of gradation of image Enhancement Method, it is characterised in that comprise the following steps：
A, image preprocessing：Denoising is carried out to image using two-sided filter；
B, the global average image and local mean value image for calculating image；
C, calculating gray scale weights；The gray scale weights and pixel value are transformed into monotonic relationshi, and calculating process is as follows：
Wherein, wi,jIt is, according to image local gray value, to be obtained using special function；The special function and current grayvalue Ii,j
With the gray value Avg at average image midpoint (i, j)i,jThere is relation, calculated and obtained according to the property of exponential function and inverse proportion function
, it is specific as follows：
First, the ratio r atio of gray value and average value is calculated by formula (1), and as index letter used in calculating weights
Several truth of a matter：
<mrow>
<mi>r</mi>
<mi>a</mi>
<mi>t</mi>
<mi>i</mi>
<mi>o</mi>
<mo>=</mo>
<mfrac>
<msub>
<mi>I</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
<mrow>
<msub>
<mi>Avg</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
</mrow>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
2nd, the exponent e xp of gray scale weights is calculated for the function of variable using ratio, shown in such as formula (2)；Choose optimal transformation
Function formula (3), w is obtained by formula (4)i,j：
Exp=f (ratio), ratio ∈ [0,255] (2)
<mrow>
<mi>exp</mi>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mi>r</mi>
<mi>a</mi>
<mi>t</mi>
<mi>i</mi>
<mi>o</mi>
</mrow>
</mfrac>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>Avg</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
</mrow>
<msub>
<mi>I</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
wi,j=ratioexp(4)；
D, the global grey level enhancement figure of calculating and local grey level enhancement figure, it is final to obtain grey level enhancement figure.
2. gradation of image Enhancement Method according to claim 1, it is characterised in that the step D is specifically included：According to step
The gray scale weight w calculated in rapid Ci,j, enhanced gray value I is obtained by formula (5)i,j'：
Ii,j'=wi,j·Ii,j=ratioexp·Ii,j (5)
Respectively with two different size of window averaged Avgi,j, obtain global enhancing gray value and local enhancement gray scale
Value Ii,j bAnd Ii,j s, the gray value for finally obtaining the pixel by formula (6) is：
Ii,j'=α Ii,j b+(1-α)·Ii,j s (6)
Wherein, α (0≤α≤1) represents to utilize the enhanced figure proportion of big window.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410738404.0A CN104463800B (en) | 2014-12-04 | 2014-12-04 | A kind of gradation of image Enhancement Method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410738404.0A CN104463800B (en) | 2014-12-04 | 2014-12-04 | A kind of gradation of image Enhancement Method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104463800A CN104463800A (en) | 2015-03-25 |
| CN104463800B true CN104463800B (en) | 2017-09-29 |
Family
ID=52909788
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410738404.0A Active CN104463800B (en) | 2014-12-04 | 2014-12-04 | A kind of gradation of image Enhancement Method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104463800B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106737870A (en) * | 2017-03-02 | 2017-05-31 | 深圳万智联合科技有限公司 | A kind of good arenas robot cooling platform of heat dispersion |
| CN112953632A (en) * | 2018-12-29 | 2021-06-11 | 长沙天仪空间科技研究院有限公司 | Laser capture system and method |
| CN111814599A (en) * | 2020-06-22 | 2020-10-23 | 河南工业职业技术学院 | Embedded pick-up weft straightening intelligent control method and device thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101452575A (en) * | 2008-12-12 | 2009-06-10 | 北京航空航天大学 | Image self-adapting enhancement method based on neural net |
| CN101853497A (en) * | 2010-02-25 | 2010-10-06 | 杭州海康威视软件有限公司 | Image enhancement method and device |
| CN103700077A (en) * | 2013-12-30 | 2014-04-02 | 北京理工大学 | Human visual characteristic-based adaptive image enhancement method |
| CN104112253A (en) * | 2014-06-16 | 2014-10-22 | 武汉博睿达信息技术有限公司 | Low-illumination image/video enhancement method based on self-adaptive multiple-dimensioned filtering |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5007953B2 (en) * | 2008-03-14 | 2012-08-22 | 日本電気株式会社 | Image processing apparatus, image processing method, and program |
-
2014
- 2014-12-04 CN CN201410738404.0A patent/CN104463800B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101452575A (en) * | 2008-12-12 | 2009-06-10 | 北京航空航天大学 | Image self-adapting enhancement method based on neural net |
| CN101853497A (en) * | 2010-02-25 | 2010-10-06 | 杭州海康威视软件有限公司 | Image enhancement method and device |
| CN103700077A (en) * | 2013-12-30 | 2014-04-02 | 北京理工大学 | Human visual characteristic-based adaptive image enhancement method |
| CN104112253A (en) * | 2014-06-16 | 2014-10-22 | 武汉博睿达信息技术有限公司 | Low-illumination image/video enhancement method based on self-adaptive multiple-dimensioned filtering |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104463800A (en) | 2015-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Loris et al. | On a generalization of the iterative soft-thresholding algorithm for the case of non-separable penalty | |
| Saleem et al. | Image fusion-based contrast enhancement | |
| Shin et al. | Efficient naturalness restoration for non‐uniform illumination images | |
| CN103116875B (en) | Self-adaptation bilateral filtering image de-noising method | |
| CN106127688B (en) | A kind of super-resolution image reconstruction method and its system | |
| CN104463800B (en) | A kind of gradation of image Enhancement Method | |
| Branchitta et al. | Dynamic-range compression and contrast enhancement in infrared imaging systems | |
| CN102567996A (en) | Remote sensing satellite image quality evaluation method | |
| CN109903224A (en) | Image-scaling method, device, computer equipment and storage medium | |
| CN102346910B (en) | A kind of real-time detection method of the point target based on Single Infrared Image Frame | |
| Jia et al. | Bayesian approach to inverse problems for functions with a variable-index Besov prior | |
| CN104680485A (en) | Method and device for denoising image based on multiple resolutions | |
| CN101976436A (en) | Pixel-level multi-focus image fusion method based on correction of differential image | |
| CN104715453A (en) | Image enhancement method by adopting regional processing mode and circuit | |
| Zhu et al. | Infrared moving point target detection based on an anisotropic spatial-temporal fourth-order diffusion filter | |
| Mahanti et al. | A standardized approach for quantitative characterization of impact crater topography | |
| Gao et al. | Enhancement MSRCR algorithm of color fog image based on the adaptive scale | |
| CN101917624B (en) | Method for reconstructing high resolution video image | |
| Chen et al. | Comparison of point spread models for underwater image restoration | |
| CN105279742A (en) | Quick image denoising method on the basis of partition noise energy estimation | |
| CN104463799A (en) | Image boundary enhancing method | |
| US20180014006A1 (en) | Electronic device with an upscaling processor and associated methods | |
| CN108537810B (en) | Improved Zernike moment sub-pixel edge detection method | |
| CN108230251A (en) | Combined type image recovery method and device | |
| CN103325090A (en) | Method and device for restraining speckles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 214145, No. 208-7, tin Tong Road, Hongshan street, Wuxi New District, Jiangsu Applicant after: WUXI UNICOMP TECHNOLOGY CO., LTD. Address before: 214145, No. 208-7, tin Tong Road, Hongshan street, Wuxi New District, Jiangsu Applicant before: Wuxi Unicomp Technology Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |