CN110428379A - A kind of image grayscale Enhancement Method and system - Google Patents
A kind of image grayscale Enhancement Method and system Download PDFInfo
- Publication number
- CN110428379A CN110428379A CN201910687965.5A CN201910687965A CN110428379A CN 110428379 A CN110428379 A CN 110428379A CN 201910687965 A CN201910687965 A CN 201910687965A CN 110428379 A CN110428379 A CN 110428379A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- gray value
- processed
- linear
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000010606 normalization Methods 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 239000004744 fabric Substances 0.000 claims description 3
- 230000001965 increasing effect Effects 0.000 claims description 3
- 238000012886 linear function Methods 0.000 claims description 3
- 230000001052 transient effect Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 2
- 230000009466 transformation Effects 0.000 abstract description 18
- 230000000694 effects Effects 0.000 abstract description 6
- 230000002708 enhancing effect Effects 0.000 description 19
- 238000005516 engineering process Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000003014 reinforcing effect Effects 0.000 description 3
- 230000001131 transforming effect Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 235000015170 shellfish Nutrition 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003389 potentiating effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of image grayscale Enhancement Method and system, which comprises S1 obtains the gray value of each pixel of image to be processed；S2 determines non-linear transform function according to the gray value of pixel described in each, and non-linear transform function everywhere continuous in domain can lead and have symmetry；S3 is converted by gray value of the non-linear transform function each pixel, to realize the grey level enhancement to the image to be processed.The present invention is converted by gray value of the non-linear transform function to image to be processed, dark portion region in image to be processed is enhanced, it is successfully identified area-of-interest in image, and the effect of image enhancement is not naturally, image has apparent uneven coler band to be layered after transformation.
Description
Technical field
The present embodiments relate to technical field of image processing more particularly to a kind of image grayscale Enhancement Methods and system.
Background technique
In order to improve the good visual effect of vehicle license plate, image enhancement skill in the case where vehicle monitoring platform is for half-light environment
Art is particularly important.Because the position of monitoring camera is relatively fixed, but the power of light source can be continuous with direction in environment
Variation, to generate different exposure environment.If monitoring camera is not exposed control when shooting vehicle license plate, clap
The vehicle license plate image taken the photograph is it is possible that different degrees of overexposure or under-exposure, machine recognition and people to vehicle license plate
Work identification causes adverse effect, at this time, it may be necessary to carry out enhancing processing to vehicle license plate image.
Image enhancement processing method has very much, and main method has: (1) Image histogram equalization algorithm (abbreviation HE) is because of it
The high efficiency of intuitive reinforcing effect and performance and be concerned, be intended to derive a mapping function, make to export brightness value point
The entropy maximization of cloth, however Image histogram equalization algorithm often will lead to the unnatural excessive increasing of certain picture contrasts
By force.(2) method of another enhancing image is using Retinex theory, and being based on Retinex theory for picture breakdown is reflecting layer
And illuminating layer, image is then enhanced by processing illuminating layer, but the calculating process of this method is complex, and is easy to produce
The raw defect for leading to cross-color because of the enhancing of image local area contrast.(3) based on neural network especially convolution mind
Image enchancing method effect through network is also fine, but network model needs a large amount of training sample, and real-time is poor.
Summary of the invention
The embodiment of the present invention provides a kind of image grayscale Enhancement Method and system, excessive to solve image in the prior art
The defect of reinforcing.
According to an aspect of the invention, there is provided a kind of image grayscale Enhancement Method, comprising:
S1 obtains the gray value of each pixel of image to be processed；
S2 determines non-linear transform function, the non-linear transform function according to the gray value of pixel described in each
Everywhere continuous can lead and have symmetry in domain；
S3 is converted by gray value of the non-linear transform function each pixel, with realization pair
The grey level enhancement of the image to be processed.
Based on the above technical solution, the present invention can also improve as follows.
Further, after the gray value of each pixel for obtaining image to be processed further include:
Linear normalization processing is carried out the gray value of each pixel, so that treated is every for linear normalization
The gray value of one pixel is respectively positioned between [0,1]；
According to the gray value of linear normalization treated each pixel, the ash of the image to be processed is calculated
Degree distribution mean value u；
When the image to be processed intensity profile mean value u be less than or equal to preset threshold, then follow the steps S2, otherwise, stream
Journey terminates, wherein number of the preset threshold between 0-1.
Further, the non-linear transform function is to match Bell curve three times.
Further, the step S2 is specifically included:
S21, according to the intensity profile mean value u of preset once linear function f (μ)=ax+b and the image to be processed,
Calculate corresponding f (μ) value, wherein coefficient a and b are constant parameter, and f (μ) is the gray average for the image to be processed
Enhancing ratio；
S22, if match Bell curve is three timesWherein, tijkFor
Index is the gray value after the pixel normalized of (i, j, k) in the image to be processed, and i, j indicate pixel described
Position in image to be processed, k are the channel of the pixel, P0、P1、P2And P3For the coefficient for matching Bell curve three times；
S23 determines four points matched in Bell curve three times, wherein (μ, f (μ)) is that the Sai Beier three times is bent
A point on line；
S24 solves the Bell curve of match three times according to determining four points.
Further, other three points in four points matched in Bell curve three times are (0,0), (0.5,0.5)
(1,1).
Further, the gray value according to linear normalization treated each pixel, described in calculating
The intensity profile mean value u of image to be processed further include:
According to the gray value of each pixel after linear normalization, the gray scale point of the image to be processed is calculated
Cloth variances sigma2；
After the step S24 further include:
For matching Bell curve described in solution three times, P is enabled0=σ/10.
Further, the step S1 further include:
The gray value of each pixel of the image to be processed of the acquisition is stored in three-dimensional matrice, wherein institute
The i and j stated in each of three-dimensional matrice index [i, j, k] indicates position of the pixel in the image to be processed, k table
Show that the channel of pixel, the channel include R, G and channel B；
Corresponding, the step S3 is specifically included:
By the non-linear transform function the gray value of linear normalization treated each pixel into
Row transformation, and the gray value of each transformed pixel is stored to new according to index with the identical of the big minor matrix of dimension
Index position.
Further, the gray value by each transformed pixel is big to new same dimension according to index storage
After the same index location of minor matrix further include:
The gray value of each pixel stored in the new big minor matrix of same dimension is carried out at linear normalization
Reason, so that the value range of the gray value of each transformed pixel is restored to each pixel of original image to be processed
The gray value value range of point.
According to the second aspect of the invention, a kind of image grayscale enhancing system is provided, comprising:
Obtain module, the gray value of each pixel for obtaining image to be processed；
Determining module determines non-linear transform function for the gray value according to pixel described in each, described non-thread
Property transforming function transformation function everywhere continuous in domain can lead and have symmetry；
Conversion module, for being become by gray value of the non-linear transform function each pixel
It changes, to realize the grey level enhancement to the image to be processed.According to the third aspect of the present invention, a kind of non-transient meter is provided
Calculation machine readable storage medium storing program for executing, is stored thereon with computer program, which realizes a kind of image when being executed by processor
The step of grayscale enhancing method.
Beneficial effects of the present invention position are as follows: it is converted by gray value of the non-linear transform function to image to be processed,
So that enhancing dark portion region in image to be processed, it is successfully identified area-of-interest in image, and image increases
Potent fruit naturally, and transformed image there is no apparent uneven coler band to be layered.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the image grayscale Enhancement Method flow chart of one embodiment of the invention；
Fig. 2 is that the Image Intensified System of one embodiment of the invention connects block diagram.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Referring to Fig. 1, the image grayscale Enhancement Method of one embodiment of the invention is provided, this method is applied to vehicle vehicle
The dark space of board image is enhanced, and the license plate in image is identified.The image grayscale Enhancement Method includes: S1, is obtained
Take the gray value of each pixel of image to be processed；S2 is determined non-linear according to the gray value of pixel described in each
Transforming function transformation function, non-linear transform function everywhere continuous in domain can lead and have symmetry；S3, by described non-thread
Property transforming function transformation function the gray value of each pixel is converted, the gray scale of the image to be processed is increased with realizing
By force.
In embodiments of the present invention, image grayscale Enhancement Method is mainly used in the identification process of vehicle license plate, when taking the photograph
The image of the vehicle license plate shot as head than darker, causes vehicle vehicle than the region where the vehicle license plate in darker or image
When board is not easy to identify, image grayscale Enhancement Method provided in an embodiment of the present invention, which can be used, enhances the gray value of image,
So that the vehicle license plate in enhanced image can be identified.
The image to be processed enhanced as needed obtains the gray value of each of image to be processed pixel, determines
One non-linear transform function carries out transformation enhancing to each of image to be processed gray value.Wherein, non-linear transform function
It is to be determined according to the gray value of each of image to be processed pixel, it is therefore, non-for different images to be processed
Linear transformation function is also different, and the non-linear transform function determined in this way has more relative to image to be processed to be directed to
Property, to the better effect after the grey level enhancement of image to be processed.Wherein, in order to enable effect after the grey level enhancement of image to be processed
Fruit seems that non-linear transform function requirement everywhere continuous in domain can be led and the non-linear change naturally, being layered without colour band
Exchange the letters number has certain symmetry.
After determining non-linear transform function, using the non-linear transform function to each pixel of image to be processed
The gray value of point is converted, and can be realized enhances the gray value of image to be processed.
The embodiment of the present invention is converted by gray value of the non-linear transform function to image to be processed, so that treating place
Dark portion region is enhanced in reason image, is successfully identified area-of-interest in image, and the effect of image enhancement is certainly
So, there is no the layerings of non-uniform colour band for transformed image.
In one embodiment of the invention, after the gray value of each pixel for obtaining image to be processed also
Include: a, linear normalization processing is carried out the gray value of each pixel, so that the ash of each pixel
Angle value is respectively positioned on [0,1]；B calculates the figure to be processed according to the gray value of each pixel after linear normalization
The intensity profile mean value u of picture；C, when the image to be processed intensity profile mean value u be less than or equal to preset threshold, then execute step
Rapid S2, otherwise, process terminates, wherein number of the preset threshold between 0-1.
Specifically, after the gray value of above-mentioned each pixel for getting image to be processed, to each pixel
Gray value under the premise of not changing grey value profile, carry out linear normalization processing, by the gray value of each pixel
Zoom between [0,1].According to the gray value after the normalization of each pixel, the intensity histogram distribution of image to be processed is obtained
Figure, according to intensity histogram distribution map, calculates intensity profile mean μ and variances sigma2.Since the embodiment of the present invention is to darker
Image carries out enhancing processing, therefore, when image to be processed intensity profile mean value u be less than or equal to preset threshold, then this is waited locating
The gray scale of reason image is enhanced, otherwise, to image to be processed without enhancing, wherein number of the preset threshold between 0-1,
0.5 is usually taken, that is, works as μ > 0.5, then is handled without enhancing；If μ≤0.5, subsequent enhancing processing is carried out.
In one embodiment of the invention, the non-linear transform function is to match Bell curve three times.
Specifically, timeliness and enhancing result that the gray scale to guarantee to image to be processed carries out enhanced processes are certainly
So, colour band uniformly continuous, the non-linear transform function in the present embodiment require the everywhere continuous in domain and can lead, exist in this way
Good continuity can be kept using gray value new after linear transformation function progress greyscale transformation.In the embodiment of the present invention
In, non-linear transform function using Bell curve is matched three times, and the specific calculating for matching Bell curve three times determines that method is S21, root
According to the intensity profile mean value u of preset once linear function f (μ)=ax+b and image to be processed, corresponding f (μ) value is calculated,
In, coefficient a and b are constant parameter, and f (μ) is the enhancing ratio for the gray average of image to be processed, the i.e. promotion of brightness
Ratio.S22, if match Bell curve is three timesWherein, tijkFor wait locate
Gray value after managing the pixel normalization that index in image is (i, j, k), i, j indicate pixel in the image to be processed
Position, k be the pixel channel, P0、P1、P2And P3For the coefficient for matching Bell curve three times；Shellfish is matched in S23, determination three times
Four points on your curve, wherein (μ, f (μ)) is the point matched in Bell curve three times；S24, according to determining four
Point solves the Bell curve of match three times.
In order to avoid the uneven coler band that original image to be processed occurs after the transformation by non-linear transform function, together
When keep the natural sense of original image to be processed, if the gray values that three transformation front and backs are consistent: 0,0.5,1, i.e., original
In image to be processed, after normalized, gray value be respectively 0,0.5,1 pixel it is defeated after nonlinear transformation
It is constant that gray value out remains as 0,0.5,1.
Determine four points (μ, f (μ)), (0,0), (0.5,0.5) and (1,1) are updated to and match Bell curve three times
In, match Bell curve three times is solved, P is obtained0、P1、P2And P3For the coefficient for matching Bell curve three times, that is, solves and obtain
Bell curve is matched three times.
In one embodiment of the invention, according to the gray value of each pixel after linear normalization, calculate to
Handle the intensity profile mean value u of image further include: according to the gray value of each pixel after linear normalization, calculate
The intensity profile variances sigma of the image to be processed2；After the step S24 further include: for Sai Beier three times described in solution
Curve enables P0=σ/10.
Specifically, being calculated after the gray value to each of image to be processed pixel carries out linear normalization
While the intensity profile value u of image to be processed, the intensity profile variances sigma of image to be processed is also calculated2.Wherein, by above-mentioned
Four points come solve three times match Bell curve parameter be the P solved0It is constantly equal to 0, in order to guarantee to bias FACTOR P0It can be with
Play the role of in nonlinear transformation it is appropriate, and also to guarantee the pixel of very low gray value in image to be processed
Reinforcing effect enables P0=σ/10, σ are the standard deviation of the grey level histogram of each pixel of image to be processed.
In one embodiment of the invention, the step S1 further include: each picture for the image to be processed that will acquire
The gray value of vegetarian refreshments is stored in three-dimensional matrice, wherein each of three-dimensional matrice indexes i and j expression picture in [i, j, k]
Position of the vegetarian refreshments in the image to be processed, k indicate the channel of pixel, and the channel includes R, G and B.It is corresponding, it is described
Step S3 is specifically included: by the non-linear transform function the gray value of each pixel after linear normalization
It is converted, and by the gray value of each transformed pixel according to the phase of index storage to the new big minor matrix of same dimension
Same index position.
Wherein, the gray value by each transformed pixel is according to index storage to new same dimension size square
After the same index location of battle array further include: the gray scale to each pixel stored in the new big minor matrix of same dimension
Value carries out linear normalization processing, so that the value range of the gray value of each transformed pixel is restored to original wait locate
Manage the gray value value range of each pixel of image.
Specifically, after getting the gray value of each pixel of image to be processed, by each of image to be processed
The gray value of a pixel is stored in three-dimensional matrice by index, when the gray value of each pixel of image to be processed is logical
After crossing non-linear transform function transformation, by the gray value of each transformed pixel according to index storage to new same dimension
The same index location of big minor matrix.Since non-linear transform function is converted to the gray value after normalized, because
This, is normalized the gray value of each transformed pixel again, so that each final transformed picture
The value range of the gray value of vegetarian refreshments restores the gray value value range of each pixel to original image to be processed, until
This, i.e., carried out enhancing processing to the gray scale of each pixel of image to be processed.
Referring to fig. 2, the image grayscale enhancing system of one embodiment of the invention is provided, including obtains module 21, determine
Module 22 and conversion module 23.
Wherein, module 21, the gray value of each pixel for obtaining image to be processed are obtained.
Determining module 22 determines non-linear transform function for the gray value according to pixel described in each, described non-
Linear transformation function handles continuous in domain and can lead.
Conversion module 23, for being become by gray value of the non-linear transform function each pixel
It changes.
A kind of image grayscale that a kind of image grayscale enhancing system and previous embodiment provided in an embodiment of the present invention provide
Enhancement Method is corresponding, and therefore, the relevant technologies feature of image grayscale enhancing system provided in this embodiment can refer to aforementioned reality
The relevant technologies feature of the image grayscale Enhancement Method of example is applied, details are not described herein.
One embodiment of the present of invention additionally provides a kind of non-transient computer readable storage medium, is stored thereon with calculating
Machine program, the step of a kind of image grayscale Enhancement Method as above is realized when which is executed by processor.
A kind of image grayscale Enhancement Method and system provided by the invention, this method is according to collected in monitoring camera
The imaging characteristics of image carry out enhancing processing in under-exposed part in image, protect the region for needing to identify in image
Certain brightness is demonstrate,proved so as to be effectively recognized, while keeping the natural sense of image.First according to the histogram of image to be processed
Non-linear transform function is determined in figure distribution.Due to requiring the pattern colour band after greyscale transformation uniform, the present invention is using shellfish three times
The non-linear transform function that Sai Er curve is handled as grey level enhancement, because matching Bell curve everywhere continuous in domain three times
And can lead, so new gray value can be kept after carrying out greyscale transformation to image to be processed using round of competition match Bell curve
Good continuity.When the symmetrical centre for matching Bell curve three times meets certain requirements, the dark space of image to be processed is carried out
The gray value for crossing bright pixel point in clear zone can also be reduced while grey level enhancement, restore it to more normal from overexposure
Exposure.It is modified using gray value of the non-linear transform function determined to each of image to be processed pixel
Transformation, to change the dynamic range of image entirety, can effectively adjust the gray value of image local pixel to be processed.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of image grayscale Enhancement Method and system characterized by comprising
S1 obtains the gray value of each pixel of image to be processed；
S2 determines non-linear transform function, the non-linear transform function is fixed according to the gray value of pixel described in each
Everywhere continuous can lead and have symmetry in adopted domain；
S3 is converted by gray value of the non-linear transform function each pixel, to realize to described
The grey level enhancement of image to be processed.
2. image grayscale Enhancement Method according to claim 1, which is characterized in that described to obtain each of image to be processed
After the gray value of a pixel further include:
Linear normalization processing is carried out the gray value of each pixel so that linear normalization treated each
The gray value of the pixel is respectively positioned between [0,1]；
According to the gray value of linear normalization treated each pixel, the gray scale point of the image to be processed is calculated
Cloth mean value u；
When the image to be processed intensity profile mean value u be less than or equal to preset threshold, then follow the steps S2, otherwise, process knot
Beam, wherein number of the preset threshold between 0-1.
3. image grayscale Enhancement Method according to claim 2, which is characterized in that the non-linear transform function is three times
Match Bell curve.
4. image grayscale Enhancement Method according to claim 3, which is characterized in that the step S2 is specifically included:
S21 is calculated according to the intensity profile mean value u of preset once linear function f (μ)=ax+b and the image to be processed
Corresponding f (μ) value, wherein coefficient a and b are constant parameter, and f (μ) is the increasing for the gray average of the image to be processed
Strong ratio；
S22, if match Bell curve is three timesWherein, tijkIt is described
Index is the gray value after the pixel normalized of (i, j, k) in image to be processed, and i, j indicate pixel described wait locate
The position in image is managed, k is the channel of the pixel, P0、P1、P2And P3For the coefficient for matching Bell curve three times；
S23 determines four points matched in Bell curve three times, wherein (μ, f (μ)) is matched in Bell curve three times to be described
A point；
S24 solves the Bell curve of match three times according to determining four points.
5. image grayscale Enhancement Method according to claim 4, which is characterized in that four matched in Bell curve three times
Other three points in a point are (0,0), (0.5,0.5) and (1,1).
6. image grayscale Enhancement Method according to claim 4 or 5, which is characterized in that it is described according to linear normalization at
The gray value of each pixel after reason calculates the intensity profile mean value u of the image to be processed further include:
According to the gray value of each pixel after linear normalization, the intensity profile side of the image to be processed is calculated
Poor σ2；
After the step S24 further include:
For matching Bell curve described in solution three times, P is enabled0=σ/10.
7. image grayscale Enhancement Method according to claim 2, which is characterized in that the step S1 further include:
The gray value of each pixel of the image to be processed of the acquisition is stored in three-dimensional matrice, wherein described three
The i and j tieed up in each of matrix index [i, j, k] indicates position of the pixel in the image to be processed, and k indicates picture
The channel of vegetarian refreshments, the channel include R, G and channel B；
Corresponding, the step S3 is specifically included:
Become by gray value of the non-linear transform function linear normalization treated each pixel
It changes, and by the gray value of each transformed pixel according to the same index of index storage to the new big minor matrix of same dimension
Position.
8. image grayscale Enhancement Method according to claim 7, which is characterized in that described by each transformed pixel
After same index location of the gray value of point according to index storage to the new big minor matrix of same dimension further include:
Linear normalization processing is carried out to the gray value of each pixel stored in the new big minor matrix of same dimension, is made
The value range for obtaining the gray value of each transformed pixel is restored to each pixel of original image to be processed
Gray value value range.
9. a kind of image grayscale enhances system characterized by comprising
Obtain module, the gray value of each pixel for obtaining image to be processed；
Determining module determines non-linear transform function, the non-linear change for the gray value according to pixel described in each
Exchange the letters number everywhere continuous in domain can lead and have symmetry；
Conversion module, for being converted by gray value of the non-linear transform function each pixel, with
Realize the grey level enhancement to the image to be processed.
10. a kind of non-transient computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer
It is realized when program is executed by processor as described in any one of claim 1 to 8 the step of a kind of image grayscale Enhancement Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910687965.5A CN110428379B (en) | 2019-07-29 | 2019-07-29 | Image gray level enhancement method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910687965.5A CN110428379B (en) | 2019-07-29 | 2019-07-29 | Image gray level enhancement method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110428379A true CN110428379A (en) | 2019-11-08 |
| CN110428379B CN110428379B (en) | 2021-10-29 |
Family
ID=68411044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910687965.5A Active CN110428379B (en) | 2019-07-29 | 2019-07-29 | Image gray level enhancement method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110428379B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112270284A (en) * | 2020-11-06 | 2021-01-26 | 南京斌之志网络科技有限公司 | Lighting facility monitoring method and system and electronic equipment |
| CN112655211A (en) * | 2020-04-23 | 2021-04-13 | 华为技术有限公司 | Image coding and decoding method and device |
| CN112950515A (en) * | 2021-01-29 | 2021-06-11 | Oppo广东移动通信有限公司 | Image processing method and device, computer readable storage medium and electronic device |
| CN113256522A (en) * | 2021-05-21 | 2021-08-13 | 上海国茂数字技术有限公司 | Method and device for enhancing low-illumination image and readable storage medium |
| CN113592712A (en) * | 2021-07-30 | 2021-11-02 | 北京百度网讯科技有限公司 | Image processing method, device, equipment, storage medium and cloud VR system |
| CN114066881A (en) * | 2021-12-01 | 2022-02-18 | 常州市宏发纵横新材料科技股份有限公司 | Nonlinear transformation based detection method, computer equipment and storage medium |
| CN114417906A (en) * | 2022-03-14 | 2022-04-29 | 深圳前海量子云码科技有限公司 | Method, device, equipment and storage medium for identifying microscopic image identification |
| CN114998159A (en) * | 2022-08-04 | 2022-09-02 | 邹城市天晖软件科技有限公司 | Design image self-adaptive enhancement method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060120580A1 (en) * | 2002-09-04 | 2006-06-08 | Sherif Makram-Ebeid | Characterizing, surfaces in medical imaging |
| US20120114267A1 (en) * | 2010-11-05 | 2012-05-10 | Lg Innotek Co., Ltd. | Method of enhancing contrast using bezier curve |
| CN102831592A (en) * | 2012-08-10 | 2012-12-19 | 中国电子科技集团公司第四十一研究所 | Image nonlinearity enhancement method based on histogram subsection transformation |
| CN103020902A (en) * | 2011-09-20 | 2013-04-03 | 富士通株式会社 | Exposure enhancement method and exposure enhancement device for mist elimination images |
| CN106462955A (en) * | 2014-06-14 | 2017-02-22 | 微软技术许可有限责任公司 | Automatic video quality enhancement with temporal smoothing and user override |
| CN106651818A (en) * | 2016-11-07 | 2017-05-10 | 湖南源信光电科技有限公司 | Improved Histogram equalization low-illumination image enhancement algorithm |
| CN109685750A (en) * | 2018-12-14 | 2019-04-26 | 厦门美图之家科技有限公司 | Image enchancing method and calculating equipment |
-
2019
- 2019-07-29 CN CN201910687965.5A patent/CN110428379B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060120580A1 (en) * | 2002-09-04 | 2006-06-08 | Sherif Makram-Ebeid | Characterizing, surfaces in medical imaging |
| US20120114267A1 (en) * | 2010-11-05 | 2012-05-10 | Lg Innotek Co., Ltd. | Method of enhancing contrast using bezier curve |
| CN103020902A (en) * | 2011-09-20 | 2013-04-03 | 富士通株式会社 | Exposure enhancement method and exposure enhancement device for mist elimination images |
| CN102831592A (en) * | 2012-08-10 | 2012-12-19 | 中国电子科技集团公司第四十一研究所 | Image nonlinearity enhancement method based on histogram subsection transformation |
| CN106462955A (en) * | 2014-06-14 | 2017-02-22 | 微软技术许可有限责任公司 | Automatic video quality enhancement with temporal smoothing and user override |
| CN106651818A (en) * | 2016-11-07 | 2017-05-10 | 湖南源信光电科技有限公司 | Improved Histogram equalization low-illumination image enhancement algorithm |
| CN109685750A (en) * | 2018-12-14 | 2019-04-26 | 厦门美图之家科技有限公司 | Image enchancing method and calculating equipment |
Non-Patent Citations (1)
| Title |
|---|
| 遥感研究会: "《遥感精解》", 31 December 1993 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112655211A (en) * | 2020-04-23 | 2021-04-13 | 华为技术有限公司 | Image coding and decoding method and device |
| WO2021212440A1 (en) * | 2020-04-23 | 2021-10-28 | 华为技术有限公司 | Image encoding/decoding method and apparatus |
| CN112655211B (en) * | 2020-04-23 | 2023-07-11 | 华为技术有限公司 | Image coding and decoding method and device |
| CN112270284A (en) * | 2020-11-06 | 2021-01-26 | 南京斌之志网络科技有限公司 | Lighting facility monitoring method and system and electronic equipment |
| CN112950515A (en) * | 2021-01-29 | 2021-06-11 | Oppo广东移动通信有限公司 | Image processing method and device, computer readable storage medium and electronic device |
| CN113256522A (en) * | 2021-05-21 | 2021-08-13 | 上海国茂数字技术有限公司 | Method and device for enhancing low-illumination image and readable storage medium |
| CN113592712A (en) * | 2021-07-30 | 2021-11-02 | 北京百度网讯科技有限公司 | Image processing method, device, equipment, storage medium and cloud VR system |
| CN114066881A (en) * | 2021-12-01 | 2022-02-18 | 常州市宏发纵横新材料科技股份有限公司 | Nonlinear transformation based detection method, computer equipment and storage medium |
| CN114066881B (en) * | 2021-12-01 | 2022-07-15 | 常州市宏发纵横新材料科技股份有限公司 | Nonlinear transformation based detection method, computer equipment and storage medium |
| CN114417906A (en) * | 2022-03-14 | 2022-04-29 | 深圳前海量子云码科技有限公司 | Method, device, equipment and storage medium for identifying microscopic image identification |
| CN114417906B (en) * | 2022-03-14 | 2022-07-22 | 量子云码(福建)科技有限公司 | Method, device, equipment and storage medium for identifying microscopic image identification |
| CN114998159A (en) * | 2022-08-04 | 2022-09-02 | 邹城市天晖软件科技有限公司 | Design image self-adaptive enhancement method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110428379B (en) | 2021-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110428379A (en) | A kind of image grayscale Enhancement Method and system | |
| CN107798661B (en) | Self-adaptive image enhancement method | |
| Mahmood et al. | An adaptive image contrast enhancement technique for low-contrast images | |
| CN108416745B (en) | Image self-adaptive defogging enhancement method with color constancy | |
| CN110428389B (en) | Low-light-level image enhancement method based on MSR theory and exposure fusion | |
| Maurya et al. | Contrast and brightness balance in image enhancement using Cuckoo Search-optimized image fusion | |
| CN110503617A (en) | A kind of underwater picture Enhancement Method based on the fusion of high and low frequency information | |
| Zeng et al. | Image processing effects on the deep face recognition system | |
| Ma et al. | Underwater image restoration through a combination of improved dark channel prior and gray world algorithms | |
| Wu et al. | A novel scheme for infrared image enhancement by using weighted least squares filter and fuzzy plateau histogram equalization | |
| Tao et al. | An effective and robust underwater image enhancement method based on color correction and artificial multi-exposure fusion | |
| CN110400270B (en) | License plate defogging method utilizing image decomposition and multiple correction fusion | |
| Xi et al. | Enhancement of unmanned aerial vehicle image with shadow removal based on optimized retinex algorithm | |
| CN112822343B (en) | Night video oriented sharpening method and storage medium | |
| Yu et al. | Single image dehazing based on multi-scale segmentation and deep learning | |
| US11900564B2 (en) | Storage medium storing program, image processing apparatus, and training method of machine learning model | |
| Gaber et al. | Performance evaluation of infrared image enhancement techniques | |
| Kadhim et al. | Enhancement of Microscopy Images by Using a Hybrid Technique Based on Adaptive Histogram Equalisation and Fuzzy Logic. | |
| Yong et al. | Multi-dimensional multi-scale image enhancement algorithm | |
| Jayanthi et al. | Underwater haze removal using contrast boosted grayscale image | |
| Yadav et al. | Enhancement of region of interest from a single backlit image with multiple features | |
| KR102615125B1 (en) | System and method for denoising image, and a recording medium having computer readable program for executing the method | |
| Lee et al. | Deep region adaptive denoising for texture enhancement | |
| Zhang et al. | Contourlet-based non-local mean via Retinex theory for robot infrared image enhancement | |
| Zhang et al. | Image Dehazing via Multilayer Detail Enhancement and Saturation Compensation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |