CN110428379B - Image gray level enhancement method and system - Google Patents
Image gray level enhancement method and system Download PDFInfo
- Publication number
- CN110428379B CN110428379B CN201910687965.5A CN201910687965A CN110428379B CN 110428379 B CN110428379 B CN 110428379B CN 201910687965 A CN201910687965 A CN 201910687965A CN 110428379 B CN110428379 B CN 110428379B
- Authority
- CN
- China
- Prior art keywords
- image
- pixel point
- processed
- gray
- value
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000009466 transformation Effects 0.000 claims abstract description 58
- 230000001131 transforming effect Effects 0.000 claims abstract description 11
- 238000010606 normalization Methods 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 24
- 239000011159 matrix material Substances 0.000 claims description 16
- 230000002708 enhancing effect Effects 0.000 claims description 5
- 238000012886 linear function Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 9
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005286 illumination Methods 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
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
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 by the use of histogram techniques
-
- G06T5/94—
Abstract
The invention provides an image gray level enhancement method and system, wherein the method comprises the following steps: s1, acquiring the gray value of each pixel point of the image to be processed; s2, determining a nonlinear transformation function according to the gray value of each pixel point, wherein the nonlinear transformation function is continuously derivable everywhere in a defined domain and has symmetry; and S3, transforming the gray value of each pixel point through the nonlinear transformation function to realize gray enhancement of the image to be processed. The method transforms the gray value of the image to be processed through the nonlinear transformation function, and enhances the dark part area in the image to be processed, so that the interested area in the image can be successfully identified, the image enhancement effect is natural, and the transformed image has no obvious uneven color band layering.
Description
Technical Field
The embodiment of the invention relates to the technical field of image processing, in particular to an image gray level enhancement method and system.
Background
In order to improve the good visual effect of the vehicle license plate in the dark environment on the vehicle monitoring platform, an image enhancement technology is very important. Because the position of the monitoring camera is relatively fixed, but the intensity and the direction of the light source in the environment can be changed continuously, so that different exposure environments are generated. If the monitoring camera does not perform exposure control when the vehicle license plate is shot, the shot vehicle license plate image may be overexposed or underexposed to different degrees, which may cause adverse effects on machine recognition and manual recognition of the vehicle license plate, and at this time, the vehicle license plate image needs to be enhanced.
There are many image enhancement processing methods, and the main methods are: (1) image histogram equalization algorithms (HE for short) are of interest because of their intuitive enhancement effect and performance efficiency, and aim to derive a mapping function to maximize the entropy of the output luminance value distribution, however, they often result in some unnatural excessive enhancement of image contrast. (2) Another method for enhancing an image is to use Retinex theory, decompose the image into a reflective layer and an illumination layer based on Retinex theory, and then enhance the image by processing the illumination layer, but this method is complicated in calculation process and is prone to generate color distortion defects caused by contrast enhancement in local areas of the image. (3) The image enhancement method based on the neural network, particularly the convolutional neural network, is also good in effect, but the network model needs a large number of training samples and is poor in real-time performance.
Disclosure of Invention
The embodiment of the invention provides an image gray level enhancement method and system, which are used for overcoming the defect of image over-enhancement in the prior art.
According to an aspect of the present invention, there is provided an image gray scale enhancement method, including:
s1, acquiring the gray value of each pixel point of the image to be processed;
s2, determining a nonlinear transformation function according to the gray value of each pixel point, wherein the nonlinear transformation function is continuously derivable everywhere in a defined domain and has symmetry;
and S3, transforming the gray value of each pixel point through the nonlinear transformation function to realize gray enhancement of the image to be processed.
On the basis of the technical scheme, the invention can be further improved as follows.
Further, after obtaining the gray value of each pixel point of the image to be processed, the method further includes:
performing linear normalization processing on the gray value of each pixel point, so that the gray value of each pixel point after the linear normalization processing is located between [0,1 ];
calculating a gray distribution mean value u of the image to be processed according to the gray value of each pixel point after linear normalization processing;
and when the mean value u of the gray distribution of the image to be processed is less than or equal to a preset threshold value, executing the step S2, otherwise, ending the process, wherein the preset threshold value is a number between 0 and 1.
Further, the nonlinear transformation function is a cubic seebeck curve.
Further, the step S2 specifically includes:
s21, calculating a corresponding f (μ) value according to a preset linear function f (μ) ax + b and the mean value u of the gray scale distribution of the image to be processed, where coefficients a and b are constant parameters, and f (μ) is an enhancement ratio for the mean value of the gray scale of the image to be processed;
s22, setting the cubic Seebel curve as
Wherein, tijkNormalizing the gray value of the pixel point with the index of (i, j, k) in the image to be processed, wherein i, j represents the position of the pixel point in the image to be processed, k is the channel of the pixel point, and P is the gray value0、P1、P2And P3Is the coefficient of the cubic seebeck curve;
s23, determining four points on the cubic Seebel curve, wherein (mu, f (mu)) is one point on the cubic Seebel curve;
and S24, solving the cubic Seebel curve according to the four determined points.
Further, the other three points of the four points on the cubic seebeck curve are (0,0), (0.5 ), and (1, 1).
Further, the calculating the gray distribution mean value u of the image to be processed according to the gray value of each pixel point after the linear normalization processing further includes:
calculating the gray distribution variance sigma of the image to be processed according to the gray value of each pixel point after linear normalization2；
The step S24 is followed by:
for the cubic Seebel curve solved, let P0＝σ/10。
Further, the step S1 further includes:
storing the gray value of each pixel point of the acquired image to be processed in a three-dimensional matrix, wherein i and j in each index [ i, j, k ] in the three-dimensional matrix represent the position of the pixel point in the image to be processed, k represents a channel of the pixel point, and the channel comprises R, G and a channel B;
correspondingly, the step S3 specifically includes:
and transforming the gray value of each pixel point after linear normalization processing through the nonlinear transformation function, and storing the transformed gray value of each pixel point to the same index position of a new matrix with the same dimension according to an index.
Further, after the step of storing the transformed gray value of each pixel point to the same index position of the new matrix with the same dimension size according to the index, the method further comprises the following steps:
and performing linear normalization processing on the gray value of each pixel point stored in the new same-dimension size matrix, so that the value range of the gray value of each pixel point after transformation is restored to the gray value range of each pixel point of the original image to be processed.
According to a second aspect of the present invention, there is provided an image gray scale enhancement system comprising:
the acquisition module is used for acquiring the gray value of each pixel point of the image to be processed;
the determining module is used for determining a nonlinear transformation function according to the gray value of each pixel point, and the nonlinear transformation function is continuously derivable everywhere in a defined domain and has symmetry;
and the transformation module is used for transforming the gray value of each pixel point through the nonlinear transformation function so as to realize gray enhancement of the image to be processed. According to a third aspect of the present invention, there is provided a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of a method of image grayscale enhancement.
The invention has the beneficial effects that: the gray value of the image to be processed is transformed through the nonlinear transformation function, so that the dark part area in the image to be processed is enhanced, the interested area in the image can be successfully identified, the image enhancement effect is natural, and the transformed image has no obvious uneven color band layering.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flowchart of an image gray scale enhancement method according to an embodiment of the present invention;
FIG. 2 is a block diagram of an image enhancement system according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an image grayscale enhancement method according to an embodiment of the present invention is provided, and the method is applied to enhance a dark region of a vehicle license plate image, so that a license plate in the image can be identified. The image gray scale enhancement method comprises the following steps: s1, acquiring the gray value of each pixel point of the image to be processed; s2, determining a nonlinear transformation function according to the gray value of each pixel point, wherein the nonlinear transformation function is continuously derivable everywhere in a defined domain and has symmetry; and S3, transforming the gray value of each pixel point through the nonlinear transformation function to realize gray enhancement of the image to be processed.
In the embodiment of the invention, the image gray scale enhancement method is mainly applied to the recognition process of the vehicle license plate, and when the image of the vehicle license plate shot by the camera is darker or the region of the vehicle license plate in the image is darker, so that the vehicle license plate is difficult to recognize, the gray scale value of the image can be enhanced by adopting the image gray scale enhancement method provided by the embodiment of the invention, so that the vehicle license plate in the enhanced image can be recognized.
Acquiring the gray value of each pixel point in the image to be processed according to the image to be processed which needs to be enhanced, determining a nonlinear transformation function, and performing transformation enhancement on each gray value in the image to be processed. The nonlinear transformation function is determined according to the gray value of each pixel point in the image to be processed, so that the nonlinear transformation function is different for different images to be processed, the determined nonlinear transformation function has higher pertinence relative to the image to be processed, and the effect of enhancing the gray level of the image to be processed is better. In order to enable the effect of the image to be processed after the gray level enhancement to be natural and have no color band layering, the nonlinear transformation function is required to be continuously conductive everywhere in a defined domain and has certain symmetry.
And after the nonlinear transformation function is determined, transforming the gray value of each pixel point of the image to be processed by adopting the nonlinear transformation function, so that the gray value of the image to be processed can be enhanced.
According to the embodiment of the invention, the gray value of the image to be processed is transformed through the nonlinear transformation function, so that the dark part area in the image to be processed is enhanced, the interested area in the image can be successfully identified, the image enhancement effect is natural, and the transformed image has no uneven color band layering.
In an embodiment of the present invention, after obtaining the gray value of each pixel point of the image to be processed, the method further includes: a, performing linear normalization processing on the gray value of each pixel point to enable the gray value of each pixel point to be located at [0,1 ]; b, calculating a gray distribution mean value u of the image to be processed according to the gray value of each pixel point after linear normalization; c, when the mean value u of the gray distribution of the image to be processed is less than or equal to a preset threshold value, executing the step S2, otherwise, ending the process, wherein the preset threshold value is a number between 0 and 1.
Specifically, after the gray value of each pixel point of the image to be processed is obtained, linear normalization processing is performed on the gray value of each pixel point on the premise that the gray value distribution is not changed, and the gray value of each pixel point is scaled to [0,1]]In the meantime. Obtaining a gray level histogram distribution map of the image to be processed according to the gray level value of each pixel point after normalization, and calculating a gray level distribution mean value mu and a variance sigma according to the gray level histogram distribution map2. Because the embodiment of the invention performs enhancement processing on the darker image, when the mean value u of the gray distribution of the image to be processed is less than or equal to the preset threshold, the gray of the image to be processed is enhanced, otherwise, the image to be processed is not enhanced, wherein the preset threshold is a number between 0 and 1, and is usually 0.5, namely when mu is less than or equal to the preset threshold>0.5, no enhancement treatment is carried out; if mu is less than or equal to 0.5, the subsequent enhancement treatment is carried out.
In one embodiment of the invention, the nonlinear transformation function is a cubic seebeck curve.
Specifically, in order to ensure timeliness of the process of enhancing the gray scale of the image to be processed and natural enhancement results, and uniform and continuous color bands, the nonlinear transformation function in the embodiment is required to be continuous and conductive everywhere in the defined domain, so that a new gray scale value can be kept in good continuity after the linear transformation function is adopted for gray scale transformation. In the embodiment of the present invention, a cubic seebeck curve is used as the nonlinear transformation function, and a specific calculation and determination method of the cubic seebeck curve is, S21, a corresponding f (μ) value is calculated according to a preset linear function f (μ) ═ ax + b and a gray distribution mean value u of the image to be processed, where coefficients a and b are constant parameters, and f (μ) is an enhancement ratio of the gray mean value of the image to be processed, that is, a luminance enhancement ratio. S22, setting the cubic Seebel curve as
Wherein, tijkNormalizing the gray value of a pixel point with an index of (i, j, k) in an image to be processed, wherein i, j represents the position of the pixel point in the image to be processed, k is a channel of the pixel point, and P is the channel of the pixel point0、P1、P2And P3Coefficients of cubic seebeck curves; s23, determining four points on the cubic Seebel curve, wherein (mu, f (mu)) is one point on the cubic Seebel curve; and S24, solving the cubic Seebel curve according to the determined four points.
In order to avoid uneven color bands of the original image to be processed after the original image to be processed is transformed by the nonlinear transformation function and maintain the natural feeling of the original image to be processed, three gray values which are consistent before and after transformation are set: 0. 0.5 and 1, namely, in the original image to be processed, after normalization processing, the gray values output by the pixel points with the gray values of 0, 0.5 and 1 after nonlinear transformation are still 0, 0.5 and 1.
Substituting the four determined points (mu, f (mu)), (0,0), (0.5 ) and (1,1) into a cubic Seebel curve, and solving the cubic Seebel curve to obtain P0、P1、P2And P3And (4) obtaining the coefficient of the cubic Seebel curve, namely solving to obtain the cubic Seebel curve.
In an embodiment of the present invention, calculating the mean value u of the gray distribution of the image to be processed according to the gray value of each pixel point after the linear normalization further includes: calculating the gray distribution variance sigma of the image to be processed according to the gray value of each pixel point after linear normalization2(ii) a The step S24 is followed by: for the cubic Seebel curve solved, let P0＝σ/10。
Specifically, after the gray value of each pixel point in the image to be processed is linearly normalized, the gray distribution value u of the image to be processed is calculated, and simultaneously, the gray distribution variance σ of the image to be processed is also calculated2. Wherein the solution is obtained by the four pointsThe parameters of the cubic Seebel curve are the solved P0Constant equal to 0, in order to ensure a bias coefficient P0Can play a proper role in the nonlinear transformation, and simultaneously, in order to ensure the enhancement effect of the pixel points with very low gray values in the image to be processed, the P value is controlled0And sigma is the standard deviation of the gray level histogram of each pixel point of the image to be processed.
In an embodiment of the present invention, the step S1 further includes: storing the obtained gray value of each pixel point of the image to be processed in a three-dimensional matrix, wherein i and j in each index [ i, j, k ] in the three-dimensional matrix represent the position of the pixel point in the image to be processed, k represents a channel of the pixel point, and the channel comprises R, G and B. Correspondingly, the step S3 specifically includes: and transforming the gray value of each pixel point after linear normalization through the nonlinear transformation function, and storing the transformed gray value of each pixel point to the same index position of a new matrix with the same dimension according to an index.
The method for converting the gray value of each pixel point into the gray value of each pixel point comprises the following steps of: and performing linear normalization processing on the gray value of each pixel point stored in the new same-dimension size matrix, so that the value range of the gray value of each pixel point after transformation is restored to the gray value range of each pixel point of the original image to be processed.
Specifically, after the gray value of each pixel point of the image to be processed is obtained, the gray value of each pixel point of the image to be processed is stored in the three-dimensional matrix through an index, and after the gray value of each pixel point of the image to be processed is converted through a nonlinear conversion function, the converted gray value of each pixel point is stored to the same index position of a new matrix with the same dimension according to the index. The non-linear transformation function transforms the gray value after the normalization processing, so that the gray value of each pixel after the transformation is normalized again, and the value range of the gray value of each pixel after the final transformation is restored to the value range of the gray value of each pixel of the original image to be processed, so that the gray value of each pixel of the image to be processed is enhanced.
Referring to fig. 2, an image gray scale enhancement system according to an embodiment of the present invention is provided, which includes an obtaining module 21, a determining module 22 and a transforming module 23.
The obtaining module 21 is configured to obtain a gray value of each pixel of the image to be processed.
And the determining module 22 is configured to determine a nonlinear transformation function according to the gray value of each pixel point, where the nonlinear transformation function is continuous and conductive in processing within a defined domain.
And the transformation module 23 is configured to transform the gray value of each pixel through the nonlinear transformation function.
An image gray scale enhancement system provided in an embodiment of the present invention corresponds to an image gray scale enhancement method provided in the foregoing embodiment, and therefore, the relevant technical features of the image gray scale enhancement system provided in this embodiment may refer to the relevant technical features of the image gray scale enhancement method provided in the foregoing embodiment, and are not described herein again.
An embodiment of the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of an image grayscale enhancement method as above.
According to the method and the system for enhancing the image gray scale, the underexposed part in the image is enhanced according to the imaging characteristic of the image collected by the monitoring camera, so that the area needing to be identified in the image can be effectively identified by ensuring certain brightness, and the natural feeling of the image is kept. Firstly, a non-linear transformation function is determined according to the histogram distribution of an image to be processed. Because the color band of the image after the gray scale conversion is required to be uniform, the cubic Seebel curve is used as the nonlinear conversion function of the gray scale enhancement processing, and the cubic Seebel curve is continuous and conductive everywhere in the defined domain, so after the image to be processed is subjected to the gray scale conversion by using the Seebel curve, the new gray scale value can keep good continuity. When the symmetry center of the cubic Seebel curve meets a certain requirement, the gray value of the bright pixel points in the bright area can be reduced while the gray value of the dark area of the image to be processed is enhanced, so that the bright pixel points can be recovered from overexposure to normal exposure. The gray value of each pixel point in the image to be processed is modified and transformed by adopting the determined nonlinear transformation function, so that the overall dynamic range of the image is changed, and the gray value of the local pixel point of the image to be processed can be effectively adjusted.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (7)
1. An image gray scale enhancement method, comprising:
s1, acquiring the gray value of each pixel point of the image to be processed;
s2, determining a nonlinear transformation function according to the gray value of each pixel point, wherein the nonlinear transformation function is continuously derivable everywhere in a defined domain and has symmetry;
s3, transforming the gray value of each pixel point through the nonlinear transformation function to realize gray enhancement of the image to be processed;
the method further comprises the following steps after the gray value of each pixel point of the image to be processed is obtained:
performing linear normalization processing on the gray value of each pixel point, so that the gray value of each pixel point after the linear normalization processing is located between [0,1 ];
calculating a gray distribution mean value u of the image to be processed according to the gray value of each pixel point after linear normalization processing;
when the mean value u of the gray distribution of the image to be processed is less than or equal to a preset threshold value, executing step S2, otherwise, ending the process, wherein the preset threshold value is a number between 0 and 1;
the nonlinear transformation function is a cubic Seebel curve;
the step S2 specifically includes:
s21, calculating a corresponding f (μ) value according to a preset linear function f (μ) ax + b and the mean value u of the gray scale distribution of the image to be processed, where coefficients a and b are constant parameters, and f (μ) is an enhancement ratio for the mean value of the gray scale of the image to be processed;
s22, setting the cubic Seebel curve as
Wherein, tijkNormalizing the gray value of the pixel point with the index of (i, j, k) in the image to be processed, wherein i, j represents the position of the pixel point in the image to be processed, k is the channel of the pixel point, and P is the gray value0、P1、P2And P3Is the coefficient of the cubic seebeck curve;
s23, determining four points on the cubic Seebel curve, wherein (mu, f (mu)) is one point on the cubic Seebel curve;
and S24, solving the cubic Seebel curve according to the four determined points.
2. The image gray scale enhancement method according to claim 1, wherein the other three points of the four points on the cubic seebeck curve are (0,0), (0.5 ) and (1, 1).
3. The image gray scale enhancement method according to claim 1 or 2, wherein the calculating the mean value u of the gray scale distribution of the image to be processed according to the gray scale value of each pixel point after linear normalization further comprises:
calculating the gray distribution variance sigma of the image to be processed according to the gray value of each pixel point after linear normalization2；
The step S24 is followed by:
for the cubic Seebel curve solved, let P0＝σ/10。
4. The image gray scale enhancement method according to claim 1, wherein said step S1 further comprises:
storing the gray value of each pixel point of the acquired image to be processed in a three-dimensional matrix, wherein i and j in each index [ i, j, k ] in the three-dimensional matrix represent the position of the pixel point in the image to be processed, k represents a channel of the pixel point, and the channel comprises R, G and a channel B;
correspondingly, the step S3 specifically includes:
and transforming the gray value of each pixel point after linear normalization processing through the nonlinear transformation function, and storing the transformed gray value of each pixel point to the same index position of a new matrix with the same dimension according to an index.
5. The method for enhancing image gray scale according to claim 4, wherein the step of storing the transformed gray scale value of each pixel point to the same index position of the new matrix with the same dimension size according to the index further comprises:
and performing linear inverse normalization processing on the gray value of each pixel point stored in the new same-dimension size matrix, so that the value range of the gray value of each pixel point after transformation is restored to the gray value range of each pixel point of the original image to be processed.
6. An image grayscale enhancement system, comprising:
the acquisition module is used for acquiring the gray value of each pixel point of the image to be processed;
the determining module is used for determining a nonlinear transformation function according to the gray value of each pixel point, and the nonlinear transformation function is continuously derivable everywhere in a defined domain and has symmetry;
the transformation module is used for transforming the gray value of each pixel point through the nonlinear transformation function so as to realize gray enhancement of the image to be processed;
the method further comprises the following steps after the gray value of each pixel point of the image to be processed is obtained:
performing linear normalization processing on the gray value of each pixel point, so that the gray value of each pixel point after the linear normalization processing is located between [0,1 ];
calculating a gray distribution mean value u of the image to be processed according to the gray value of each pixel point after linear normalization processing;
when the mean value u of the gray distribution of the image to be processed is less than or equal to a preset threshold value, executing step S2, otherwise, ending the process, wherein the preset threshold value is a number between 0 and 1;
the nonlinear transformation function is a cubic Seebel curve;
the step S2 specifically includes:
s21, calculating a corresponding f (μ) value according to a preset linear function f (μ) ax + b and the mean value u of the gray scale distribution of the image to be processed, where coefficients a and b are constant parameters, and f (μ) is an enhancement ratio for the mean value of the gray scale of the image to be processed;
s22, setting the cubic Seebel curve as
Wherein, tijkNormalizing the gray value of the pixel point with the index of (i, j, k) in the image to be processed, wherein i, j represents the position of the pixel point in the image to be processed, k is the channel of the pixel point, and P is the gray value0、P1、P2And P3Is the coefficient of the cubic seebeck curve;
s23, determining four points on the cubic Seebel curve, wherein (mu, f (mu)) is one point on the cubic Seebel curve;
and S24, solving the cubic Seebel curve according to the four determined points.
7. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of a method for image intensity enhancement as claimed in any one of claims 1 to 5.
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 CN110428379A (en) | 2019-11-08 |
| CN110428379B true 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) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021212440A1 (en) * | 2020-04-23 | 2021-10-28 | 华为技术有限公司 | Image encoding/decoding method and apparatus |
| CN112270284B (en) * | 2020-11-06 | 2021-12-03 | 奥斯福集团有限公司 | 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 |
| 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 |
| 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 |
| CN114998159B (en) * | 2022-08-04 | 2022-10-28 | 邹城市天晖软件科技有限公司 | Design image self-adaptive enhancement method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004023396A2 (en) * | 2002-09-04 | 2004-03-18 | Koninklijke Philips Electronics N.V. | Characterizing, coding and comparing surfaces,contours or boundaries in medical imaging |
| US8577141B2 (en) * | 2010-11-05 | 2013-11-05 | Lg Innotek Co., Ltd. | Method of enhancing contrast using bezier curve |
-
2019
- 2019-07-29 CN CN201910687965.5A patent/CN110428379B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110428379A (en) | 2019-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110428379B (en) | Image gray level enhancement method and system | |
| US11127122B2 (en) | Image enhancement method and system | |
| Cao et al. | Contrast enhancement of brightness-distorted images by improved adaptive gamma correction | |
| CN110232661B (en) | Low-illumination color image enhancement method based on Retinex and convolutional neural network | |
| Celik | Spatial mutual information and PageRank-based contrast enhancement and quality-aware relative contrast measure | |
| CN111583123A (en) | Wavelet transform-based image enhancement algorithm for fusing high-frequency and low-frequency information | |
| CN107798661B (en) | Self-adaptive image enhancement method | |
| CN112734650B (en) | Virtual multi-exposure fusion based uneven illumination image enhancement method | |
| CN103034986A (en) | Night vision image enhancement method based on exposure fusion | |
| CN105809643B (en) | A kind of image enchancing method based on adaptive block channel extrusion | |
| CN107895350B (en) | HDR image generation method based on self-adaptive double gamma transformation | |
| Zakaria et al. | A review: Image compensation techniques | |
| Yang et al. | Low-light image enhancement based on Retinex theory and dual-tree complex wavelet transform | |
| Liu et al. | Enhancement of low illumination images based on an optimal hyperbolic tangent profile | |
| Mu et al. | Low and non-uniform illumination color image enhancement using weighted guided image filtering | |
| Lei et al. | Low-light image enhancement using the cell vibration model | |
| CN112614063B (en) | Image enhancement and noise self-adaptive removal method for low-illumination environment in building | |
| CN110992287B (en) | Method for clarifying non-uniform illumination video | |
| CN112822343B (en) | Night video oriented sharpening method and storage medium | |
| Parihar | Histogram modification and DCT based contrast enhancement | |
| Yadav et al. | Multiple feature-based contrast enhancement of ROI of backlit images | |
| Liu et al. | An adaptive tone mapping algorithm based on gaussian filter | |
| Lee et al. | Visual sensitivity correlated tone reproduction for low dynamic range images in the compression field | |
| Yong et al. | Multi-dimensional multi-scale image enhancement algorithm | |
| Liu et al. | A survey of low-light image enhancement |
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 |