CN111105371B - Enhancement method of low-contrast infrared image - Google Patents
Enhancement method of low-contrast infrared image Download PDFInfo
- Publication number
- CN111105371B CN111105371B CN201911257400.XA CN201911257400A CN111105371B CN 111105371 B CN111105371 B CN 111105371B CN 201911257400 A CN201911257400 A CN 201911257400A CN 111105371 B CN111105371 B CN 111105371B
- Authority
- CN
- China
- Prior art keywords
- image
- infrared
- value
- infrared image
- image2
- 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 34
- 238000012545 processing Methods 0.000 claims abstract description 23
- 230000002708 enhancing effect Effects 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 8
- 101100129500 Caenorhabditis elegans max-2 gene Proteins 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 8
- 239000011159 matrix material Substances 0.000 abstract description 4
- 230000007547 defect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000003331 infrared imaging Methods 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
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/18—Image warping, e.g. rearranging pixels individually
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention provides a method for enhancing a low-contrast infrared image, which aims at an image in a low-contrast scene, evaluates the contrast of the infrared image by solving the standard deviation of the infrared image, is used for judging whether the method is suitable for the infrared image or not, maps the infrared image which accords with the low contrast to a logarithmic domain for stretching treatment, and reconverts through an exponential domain. Judging whether the infrared image is required to be subjected to anti-color processing, carrying out mean value blurring processing on the infrared image, calculating an infrared image enhancement coefficient p, and calculating an enhancement parameter matrix by using the enhancement coefficient p, the infrared image before blurring processing and the infrared image after blurring processing to obtain a corresponding enhancement parameter A; and enhancing the infrared image before the blurring process through the enhancement coefficient and the enhancement parameter matrix, and if the infrared image is subjected to the inverse color process in the previous step, performing the inverse color process again to obtain a final image. If the previous step is not done with the inverse color process, the final image is obtained.
Description
Technical Field
The invention relates to the field of infrared image processing, in particular to a method for enhancing a low-contrast infrared image.
Background
With the development of technology, the application of infrared images is more and more widespread, and the search for the mystery covered by darkness is not separated from infrared imaging. However, due to the problems of the detector or the environment, the obtained infrared image is also ragged, and valuable information is difficult to obtain in the low-contrast infrared image, so that the quality of the image is particularly important to improve. Histogram equalization is a common image enhancement method, which can effectively improve the contrast of an image, but when more noise exists in the image, the corresponding noise is amplified, and when the gray values of the image are too concentrated, the histogram equalization cannot achieve a good effect; the genetic algorithm can adaptively enhance the gray characteristic property of the infrared image, but the calculated amount is too long, and real-time processing is difficult to realize under the general condition of calculation resources. Although researchers at home and abroad propose a plurality of infrared enhancement methods, there are still some defects, and the main problems are summarized as follows: the calculation amount of the algorithm is large, the real-time calculation is difficult to realize, the intelligence and the self-adaptability of the algorithm are poor, and the algorithm needs to consider the problems of parameter setting and the like.
Disclosure of Invention
The invention aims to: the invention aims to solve the technical problem of providing a method for enhancing a low-contrast infrared image, which aims at the defects of the prior art and comprises the following steps: the method comprises the following steps:
step 1, acquiring an infrared image, judging whether the infrared image is a low-contrast image or not by solving the standard deviation of the image, if so, executing the step 2, otherwise, not processing;
step 2, stretching transformation is carried out on the infrared image with low contrast in a logarithmic domain, so as to obtain a stretched image;
step 3, calculating the gray average value of the infrared image, judging whether the inverse color treatment is needed, if so, executing step 4, and if not, directly executing step 4;
step 4, calculating standard deviation of the infrared image, and carrying out mean filtering on the image;
step 5, calculating an enhancement coefficient to obtain a residual image;
and 6, obtaining a final enhanced image by using the mapping relation between the residual image and the stretching image.
In step 1, the standard deviation of the image is obtained by the following formula:
wherein N is the number of pixels of the obtained infrared Image1, mu is the average value of the gray values of the pixels of the infrared Image, sigma is the standard deviation of the calculated Image, and x i The gray value of the i-th pixel of the infrared Image1 is shown.
In step 1, if the standard deviation σ is smaller than 30, it is judged to be a low-contrast image.
In step 2, for the infrared Image1 meeting the low contrast requirement, the following formula is adopted to stretch in the logarithmic domain:
wherein Pmax is the maximum value of gray values in the infrared Image1, average is a logarithmic Average value of all pixels in the infrared Image1 based on e, and an exponent of the logarithmic Average value based on e is calculated, and the calculation method is as follows:
wherein delta is a minimum value, and is generally 0.0001, so that the situation that logarithm of 0 is taken is avoided, and the Image1 is mapped to a logarithm domain through the formula to be subjected to stretching transformation, so that a new infrared Image2 is obtained.
In step 3, the average gray level μ2 of the infrared Image2 is obtained, and if μ2<128, a color reversal process is required.
In step 3, the specific implementation method of the inverse color processing is to traverse the infrared Image2, and for each pixel gray Value, there are: value=255-Value.
In step 4, the specific implementation method for carrying out mean filtering on the image comprises the following steps: and calculating the average value of the pixel gray value of the infrared Image and the pixel gray value of the eight neighborhood thereof, and updating the pixel value of the infrared Image to be equal to the average value to obtain an Image3.
The specific implementation method for calculating the enhancement coefficient in the step 5 is as follows: calculating a standard deviation sd of the infrared Image2, if the sd is larger than 50, the sd takes a value of 50, calculating an infrared Image enhancement coefficient p, wherein p=1-sd/50, traversing the infrared Image3, and multiplying the gray value of each pixel by the infrared Image enhancement coefficient p to obtain a new infrared Image4.
In step 5, the specific implementation method of the residual image is as follows: and traversing the infrared images Image2 and Image4, subtracting the pixel gray value of the Image4 from the pixel gray value of the Image2 at the same position, wherein the value smaller than 0 is 0, and obtaining a residual Image5 as a result.
In step 6, the specific implementation method for obtaining the enhanced image is as follows:
wherein value_image5 (x) represents the pixel gray Value of the corresponding position of Image5, value_image4 (x) represents the Value of the corresponding position of Image4, F (x) is the enhancement pixel gray Value of the corresponding position value_image5 (x) of residual Image5, and the enhancement coefficient is
Traversing the Image5 to obtain an Image6;
the calculation method of the coefficient A comprises the following steps: traversing the infrared images Image2 and Image3 to obtain maximum pixel gray values max2 and max3 respectively, and calculating a coefficient A= (max2+max3)/2;
the obtained enhanced Image is denoted as Image6, and if the enhanced Image6 obtained in step 6 is subjected to the color reversal processing in step 3, the enhanced Image6 is subjected to the color reversal processing again, thereby obtaining a final enhanced Image.
The beneficial effects are that: the invention provides an image enhancement method aiming at an infrared image with low contrast, which comprises the steps of judging the image quality by utilizing image variance, carrying out transformation of stretching a logarithmic domain on the infrared image conforming to the low contrast, and carrying out transformation again by an exponential domain. Judging whether the infrared image is required to be subjected to anti-color processing, carrying out mean value blurring processing on the infrared image, calculating an infrared image enhancement coefficient p, and calculating an enhancement parameter matrix by using the enhancement coefficient p, the infrared image before blurring processing and the infrared image after blurring processing to obtain a corresponding enhancement parameter A; and enhancing the infrared image before the blurring process through the enhancement coefficient and the enhancement parameter matrix, and if the infrared image is subjected to the inverse color process in the previous step, performing the inverse color process again to obtain a final image. If the previous step does not do the inverse color treatment, the final image is obtained, and the enhancement method has the characteristics of no parameter setting and obvious contrast stretching.
Drawings
The foregoing and/or other advantages of the invention will become more apparent from the following detailed description of the invention when taken in conjunction with the accompanying drawings and detailed description.
FIG. 1 is a flow chart of a low contrast infrared image enhancement method in an embodiment of the invention.
FIG. 2 is an infrared input image selected in an embodiment of the invention.
Fig. 3 is a result of performing logarithmic and exponential domain transformation on an infrared image in accordance with an embodiment of the present invention.
Fig. 4 is the final enhanced image result in an embodiment of the present invention.
Detailed Description
The invention provides a method for enhancing a low-contrast infrared image, which comprises the following steps:
a) The infrared image data image1 is acquired as shown in fig. 2. The standard deviation of the image is obtained, the smaller the standard deviation is, the more concentrated the distribution of the image is, the lower the contrast of the image is, the standard deviation of the image is used for judging whether the image belongs to the low-contrast infrared image, and when the standard deviation of the infrared image is smaller than 30, the infrared image has lower contrast and is considered as the low-contrast infrared image through data statistics. The standard deviation value of the image is 8.45505, and meets the judging condition of the low-contrast infrared image.
b) The infrared Image1 is traversed, and the value with the largest gray value in the Image is found and is recorded as Pmax, pmax=255. And calculating the logarithmic Average value of all pixels based on e in the infrared image1, and solving an index Average of the logarithmic Average value based on e. The calculation method comprises the following steps:
wherein delta is a minimum value, and the situation of taking the logarithm of 0 is avoided. Traversing the infrared Image1, using the formula: />
Image1 is mapped to the logarithmic domain and subjected to stretching transformation, so that a new infrared Image2 is obtained, as shown in fig. 3.
c) The average value of the infrared Image2 is 67.4991 and is smaller than 128, the infrared Image2 is subjected to inverse color processing, namely the infrared Image2 is traversed, and the value of each pixel value is value=255-value.
d) And carrying out mean filtering processing on the infrared Image2 to obtain a new infrared Image3.
e) The standard deviation sd= 16.7889 of the infrared Image2 is calculated, and if sd is greater than 50, the sd takes a value of 50, and the infrared Image enhancement coefficient p is calculated, with p=1-sd/50= 0.664222.
f) And traversing the infrared Image3, and multiplying the gray value of each pixel by the infrared Image enhancement coefficient p to obtain a new infrared Image4.
g) And traversing the infrared images Image2 and Image4, and subtracting the value of Image4 from the value of Image2 at the same position, wherein all values smaller than 0 are 0, so as to obtain a residual Image5.
h) The infrared images Image2 and Image3 are traversed to obtain maximum values max2 and max3 thereof, respectively, and a coefficient a= (max2+max3)/2 is calculated.
i) The following expression is used:
the enhanced infrared Image6 is obtained, wherein value_image5 (x) represents a Value of a position corresponding to the Image5, and value_image4 (x) represents a Value of a position corresponding to the Image4.
j) Because the inverse color processing is performed in step c), the inverse color processing is performed on the infrared Image6 again, so as to obtain a final enhanced Image, as shown in fig. 4.
The present invention provides a method for enhancing a low-contrast infrared image, and the method and the way for realizing the technical scheme are numerous, the above is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and the improvements and modifications should also be regarded as the protection scope of the present invention. The components not explicitly described in this embodiment can be implemented by using the prior art.
Claims (1)
1. A method of enhancing a low contrast infrared image, comprising the steps of:
step 1, acquiring an infrared image, judging whether the infrared image is a low-contrast image or not by solving the standard deviation of the image, if so, executing the step 2, otherwise, not processing;
step 2, stretching transformation is carried out on the infrared Image with low contrast in a logarithmic domain, and stretched infrared Image2 is obtained;
step 3, calculating the gray average value of the infrared Image2, judging whether the inverse color processing is needed, if so, executing the step 4, and if not, directly executing the step 4;
step 4, calculating standard deviation of the infrared Image, and carrying out mean filtering on the Image to obtain an Image3;
step 5, calculating an enhancement coefficient to obtain a residual image;
step 6, obtaining a final enhanced image by using the mapping relation between the residual image and the stretching image;
in step 1, the standard deviation of the image is obtained by the following formula:
wherein N is the number of pixels of the obtained infrared Image1, mu is the average value of the gray values of the pixels of the infrared Image, sigma is the standard deviation of the calculated Image, and x i A gray value representing the i-th pixel of the infrared Image 1;
in step 1, if the standard deviation sigma is smaller than 30, judging that the image is a low-contrast image;
in step 2, for the infrared Image1 meeting the low contrast requirement, the following formula is adopted to stretch in the logarithmic domain:
wherein Pmax is the maximum value of gray values in the infrared Image1, average is a logarithmic Average value of all pixels in the infrared Image1 based on e, and an exponent of the logarithmic Average value based on e is calculated, and the calculation method is as follows:
wherein delta is a minimum value, mapping the Image1 to a logarithmic domain through the formula, and performing stretching transformation to obtain a new infrared Image2;
in the step 3, a gray average value mu 2 of the infrared Image2 is obtained, and if mu 2 is less than 128, the inverse color treatment is needed;
in step 3, the specific implementation method of the inverse color processing is to traverse the infrared Image2, and for each pixel gray Value, there are: value = 255-Value;
in step 4, the specific implementation method for carrying out mean filtering on the image comprises the following steps: calculating the average value of the pixel gray value of the infrared Image and the pixel gray value of the eight neighborhood thereof, and updating the pixel value of the infrared Image to be equal to the average value to obtain an Image3;
the specific implementation method for calculating the enhancement coefficient in the step 5 is as follows: calculating a standard deviation sd of the infrared Image2, if the sd is larger than 50, taking the sd as 50, calculating an infrared Image enhancement coefficient p, wherein p=1-sd/50, traversing the infrared Image3, and multiplying the gray value of each pixel by the infrared Image enhancement coefficient p to obtain a new infrared Image4;
in step 5, the specific implementation method of the residual image is as follows: traversing the infrared images Image2 and Image4, subtracting the pixel gray value of the Image4 from the pixel gray value of the Image2 at the same position, wherein the value smaller than 0 is 0, and obtaining a residual Image5 as a result;
in step 6, the specific implementation method for obtaining the enhanced image is as follows:
wherein value_image5 (x) represents the pixel gray Value of the corresponding position of Image5, value_image4 (x) represents the Value of the corresponding position of Image4, F (x) is the enhancement pixel gray Value of the corresponding position value_image5 (x) of residual Image5, and the enhancement coefficient is
Traversing the Image5 to obtain an Image6;
the calculation method of the coefficient A comprises the following steps: traversing the infrared images Image2 and Image3 to obtain maximum pixel gray values max2 and max3 respectively, and calculating a coefficient A= (max2+max3)/2;
the obtained enhanced Image is denoted as Image6, and if the enhanced Image6 obtained in step 6 is subjected to the color reversal processing in step 3, the enhanced Image6 is subjected to the color reversal processing again, thereby obtaining a final enhanced Image.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911257400.XA CN111105371B (en) | 2019-12-10 | 2019-12-10 | Enhancement method of low-contrast infrared image |
| PCT/CN2020/089852 WO2021114564A1 (en) | 2019-12-10 | 2020-05-12 | Enhancement method for low-contrast infrared image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911257400.XA CN111105371B (en) | 2019-12-10 | 2019-12-10 | Enhancement method of low-contrast infrared image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111105371A CN111105371A (en) | 2020-05-05 |
| CN111105371B true CN111105371B (en) | 2023-05-02 |
Family
ID=70423127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911257400.XA Active CN111105371B (en) | 2019-12-10 | 2019-12-10 | Enhancement method of low-contrast infrared image |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111105371B (en) |
| WO (1) | WO2021114564A1 (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111105371B (en) * | 2019-12-10 | 2023-05-02 | 南京莱斯电子设备有限公司 | Enhancement method of low-contrast infrared image |
| CN112561881B (en) * | 2020-12-16 | 2023-09-05 | 南京莱斯电子设备有限公司 | Infrared image self-adaptive data enhancement method based on evaluation model |
| CN116342635B (en) * | 2023-05-26 | 2023-08-08 | 山东省地质矿产勘查开发局第一地质大队（山东省第一地质矿产勘查院） | Crack contour extraction method in geological mapping |
| CN116485686B (en) * | 2023-06-19 | 2023-08-29 | 青岛国源中创电气自动化工程有限公司 | Sewage treatment image enhancement method by activated sludge process |
| CN116883279B (en) * | 2023-07-11 | 2024-03-12 | 北京龙知远科技发展有限公司 | Short wave infrared image enhancement method with low noise and high real-time performance |
| CN117297554A (en) * | 2023-11-16 | 2023-12-29 | 哈尔滨海鸿基业科技发展有限公司 | Control system and method for lymphatic imaging device |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100563312C (en) * | 2007-12-25 | 2009-11-25 | 青岛海信信芯科技有限公司 | A kind of contrast enhancement process |
| CN102413283B (en) * | 2011-10-25 | 2013-08-14 | 广州飒特红外股份有限公司 | Infrared chart digital signal processing system and method |
| CN102547117B (en) * | 2011-12-22 | 2014-12-03 | 北京英泰智软件技术发展有限公司 | Method for enhancing contrast ratio of camera |
| CN104574284A (en) * | 2013-10-24 | 2015-04-29 | 南京普爱射线影像设备有限公司 | Digital X-ray image contrast enhancement processing method |
| FR3015090B1 (en) * | 2013-12-18 | 2016-01-15 | Thales Sa | METHOD OF PROCESSING IMAGES, PARTICULARLY FROM NIGHT VISUALIZATION SYSTEMS AND SYSTEM THEREFOR |
| CN106127694B (en) * | 2016-05-20 | 2018-11-09 | 重庆医科大学 | Adaptive two-way guarantor's bandwidth logarithmic transformation method of uneven illumination image enhancement |
| CN107392866B (en) * | 2017-07-07 | 2019-09-17 | 武汉科技大学 | A kind of facial image local grain Enhancement Method of illumination robust |
| CN109584181A (en) * | 2018-12-03 | 2019-04-05 | 北京遥感设备研究所 | It is a kind of improved based on Retinex infrared image detail enhancing method |
| CN109685742A (en) * | 2018-12-29 | 2019-04-26 | 哈尔滨理工大学 | A kind of image enchancing method under half-light environment |
| CN111105371B (en) * | 2019-12-10 | 2023-05-02 | 南京莱斯电子设备有限公司 | Enhancement method of low-contrast infrared image |
-
2019
- 2019-12-10 CN CN201911257400.XA patent/CN111105371B/en active Active
-
2020
- 2020-05-12 WO PCT/CN2020/089852 patent/WO2021114564A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021114564A1 (en) | 2021-06-17 |
| CN111105371A (en) | 2020-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111105371B (en) | Enhancement method of low-contrast infrared image | |
| CN108876743B (en) | Image rapid defogging method, system, terminal and storage medium | |
| CN109872285B (en) | Retinex low-illumination color image enhancement method based on variational constraint | |
| Zhang et al. | A naturalness preserved fast dehazing algorithm using HSV color space | |
| CN109919859B (en) | Outdoor scene image defogging enhancement method, computing device and storage medium thereof | |
| CN112308803B (en) | Self-supervision low-illumination image enhancement and denoising method based on deep learning | |
| CN105046658A (en) | Low-illumination image processing method and device | |
| CN110533614B (en) | Underwater image enhancement method combining frequency domain and airspace | |
| CN112116536A (en) | Low-illumination image enhancement method and system | |
| CN110189266B (en) | Self-adaptive rapid image enhancement method | |
| CN105809643A (en) | Image enhancing method based on self-adaptive block channel stretching | |
| CN111563854B (en) | Particle swarm optimization method for underwater image enhancement processing | |
| CN113592750B (en) | Infrared enhancement method based on gradient histogram | |
| CN112541869A (en) | Retinex image defogging method based on matlab | |
| Yang et al. | Low-light image enhancement based on Retinex theory and dual-tree complex wavelet transform | |
| CN114693548B (en) | Dark channel defogging method based on bright area detection | |
| Mu et al. | Low and non-uniform illumination color image enhancement using weighted guided image filtering | |
| Xue et al. | Video image dehazing algorithm based on multi-scale retinex with color restoration | |
| CN111476744A (en) | Underwater image enhancement method based on classification and atmospheric imaging model | |
| CN109345479B (en) | Real-time preprocessing method and storage medium for video monitoring data | |
| WO2020107308A1 (en) | Low-light-level image rapid enhancement method and apparatus based on retinex | |
| CN116862809A (en) | Image enhancement method under low exposure condition | |
| CN116630198A (en) | Multi-scale fusion underwater image enhancement method combining self-adaptive gamma correction | |
| CN116883259A (en) | Underwater image enhancement method based on denoising diffusion probability model | |
| Chen et al. | An adaptive image dehazing algorithm based on dark channel prior |
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 |