CN113763265A - Infrared image contrast gain adjusting method, storage medium and infrared detector - Google Patents
Infrared image contrast gain adjusting method, storage medium and infrared detector Download PDFInfo
- Publication number
- CN113763265A CN113763265A CN202110907236.3A CN202110907236A CN113763265A CN 113763265 A CN113763265 A CN 113763265A CN 202110907236 A CN202110907236 A CN 202110907236A CN 113763265 A CN113763265 A CN 113763265A
- Authority
- CN
- China
- Prior art keywords
- infrared image
- fuzzy
- input
- contrast gain
- output
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000009466 transformation Effects 0.000 claims abstract description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 2
- 230000001131 transforming effect Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 4
- 230000005855 radiation Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 238000003331 infrared imaging Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000004377 microelectronic Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000001931 thermography 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
- G06T5/73—Deblurring; Sharpening
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20182—Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an infrared image contrast gain adjusting method, a storage medium and an infrared detector. The method comprises 1) segmenting an input infrared image; 2) designing a fuzzy controller, and determining an input variable and an output variable of the fuzzy controller; 3) carrying out scale transformation on an input variable and an output variable of the fuzzy controller; 4) fuzzy processing is carried out on input variables; 5) carrying out fuzzy reasoning; 6) performing fuzzy solution; 7) and calculating the gray value after the contrast gain adjustment. According to the established fuzzy rule base, the contrast gain of the infrared image can be adjusted, the method has strong robustness, the noise of the infrared image can be effectively inhibited, the image contrast is improved, and the detail information of the infrared image is enhanced.
Description
Technical Field
The invention relates to an infrared image contrast gain adjusting method, a storage medium and an infrared detector.
Background
With the rapid development of infrared technology, infrared imaging systems are widely used in many fields. With the benefit of microelectronics, infrared imaging systems are moving toward low power consumption, small volume, and multiple functions. The infrared processing system comprises an infrared detector, an FPGA and other necessary components, and can acquire an infrared image with higher quality.
The infrared thermal imaging technology is used for imaging by detecting thermal radiation on the surface of an object, but due to atmospheric attenuation, infrared radiation energy reaching an optical lens is little, the infrared image contrast is low, and the vision is blurred. Meanwhile, when the infrared radiation of the detected object is received, a large number of interference factors such as ambient temperature, dust, atmospheric radiation and the like are received, so that the problems of large non-uniformity, more noise, unclear detail texture, low contrast and the like of the infrared image are caused, the requirements of people on the high-quality infrared image are difficult to meet, and the development of the infrared technology is limited to a certain extent.
The existing technology and process of the infrared focal plane detector are not perfect enough, for example, factors such as random interference to the external environment, thermal balance of the environment, long transmission distance, serious atmospheric attenuation and the like directly cause the problems of low contrast, fuzzy image effect and the like of an infrared image.
Disclosure of Invention
The invention aims to solve the technical problems of low infrared image contrast, fuzzy visual effect, large infrared image nonuniformity, high noise, unclear detail texture and the like, and provides an infrared image contrast gain adjusting method, a storage medium and an infrared detector.
The infrared image contrast gain adjusting method is based on a fuzzy control algorithm, can adjust the infrared image contrast gain according to the established fuzzy rule base, has strong robustness, can effectively inhibit infrared image noise, improves image contrast and enhances infrared image detail information.
The technical scheme for solving the technical problems comprises the following steps:
an infrared image contrast gain adjustment method comprises the following steps:
(1) and segmenting the input infrared image to obtain different dimension information of the infrared image.
(2) Designing a fuzzy controller, and determining an input variable and an output variable of the fuzzy controller, wherein the input variable of the fuzzy controller is a parameter capable of reflecting the whole fluctuation range of the infrared image and a parameter capable of reflecting the local information quantity, so that the fuzzy controller can realize the function of adjusting the contrast gain of the infrared image.
(3) Carrying out scale transformation on input variables and output variables of the fuzzy controller, and transforming the input variables and the output variables into respective discourse domain ranges, wherein the scale transformation formula is as follows:
(4) and carrying out fuzzy processing on the input variable to convert the accurate value of the input variable into a fuzzy value.
(5) And carrying out fuzzy reasoning, dividing the input variable and the output variable into A fuzzy subsets, and establishing a fuzzy rule base according to expert experience.
(6) And performing deblurring, wherein the obtained output variable is still a fuzzy value after fuzzy reasoning, and the output variable is deblurred to be an accurate output quantity which can reflect the weight of the whole fluctuation of the infrared image and the weight of the local information quantity of the infrared image.
(7) Calculating the gray value after the contrast gain adjustment, and substituting the output quantity into the following formula to obtain the gray value I after the contrast gain adjustment:
I=S1*G1+S2{G2+L+Sn*Gn
in the formula: s1,S2,…,SnAs input to a fuzzy controller, G1,G2,…,GnIs the output of the fuzzy controller.
A computer-readable storage medium having stored thereon a computer program for execution by a processor to perform the steps of implementing the infrared image contrast gain adjustment method described above.
An infrared detector comprising the computer readable storage medium described above.
The infrared image contrast gain adjusting method provided by the invention effectively inhibits noise, improves the infrared image contrast and enhances the infrared image detail information.
Drawings
Fig. 1 is a schematic block diagram of embodiment 1.
FIG. 2 is a membership function of an input-output variable, in which: the abscissa is the domain of input and output variables, the ordinate is the degree of membership, and NB, NS, Z, PS, PB are five fuzzy subsets of the input and output variables.
Fig. 3 is a comparison chart before and after contrast gain adjustment of the infrared image according to example 1, in which (a) is an original image and (b) is an image after contrast gain adjustment.
Detailed Description
The invention provides an infrared image contrast gain adjusting method, aiming at solving the defects of low contrast, low definition, weak and small target shape resolution, poor fineness and energy conservation and the like of an infrared image. The infrared image contrast gain is adjusted through fuzzy control, and the infrared image contrast gain can be adjusted according to the established fuzzy rule base by the algorithm, so that the infrared image noise can be effectively inhibited, the infrared image details are enhanced, and the infrared image contrast is improved.
In order to further illustrate the technical solution of the present invention, example 1 is described in detail below.
Example 1
As shown in fig. 1, the present embodiment includes the following steps:
1) taking the infrared image divided into several blocks as an example, the input 768 rows and 1024 columns of infrared images are divided into 64 12 rows and 16 columns of infrared images.
2) For example, a single fuzzy controller with two single inputs and one output is designed to realize the function of adjusting the contrast gain of the infrared image. Since the gray value difference and the variance can well reflect the contrast, detail information and noise information of the region, the input of the fuzzy controller is selected to be the infrared image pixel point difference DiAnd variance DvarThe output is respectively the infrared image difference DiWeight G of1And a variance weight G2。
Suppose the gray value of each pixel point is IijRespectively calculating the difference D between the maximum value and the minimum value of the gray value of each pixel point of the cut infrared image according to the following formulaiAnd variance Dvar. Wherein, Imax、IminIs the maximum and minimum of the gray value of the region, ImeanIs the mean of the gray values of the region.
3) The input and output of the fuzzy controller are scaled and transformed to the respective domain of discourse range. Quantization factor kaThe calculation is shown below:
in the formula: DD is the discourse domain range, RIIs a range of values.
4) The input amount is then blurred, converting the input accurate value into a blurred value. A is the fuzzy set on R, muA(x) The degree to which x belongs to the fuzzy set a is called, namely, the membership function of a. Because the Gaussian type membership functions have good smoothness and symmetry and no zero point, the input and output membership functions of the fuzzy controller are designed to be the Gaussian type membership functions f (x) by taking the Gaussian type membership functions as an example.
In the formula: σ represents the standard deviation and c represents a mathematical expectation followed by the random variable X.
5) Dividing input and output variables into 5 fuzzy subsets (PB, PS, Z, NS, NB) as an example, and establishing a fuzzy rule base according to expert experience. The difference between the maximum and minimum gray values of the region and the variance can reflect the detailed information of the region, but the dimension of the variance is higher than that of the difference, and the information is more comprehensive. According to experience, when the difference is small, the noise of the region is strong, and the contrast gain needs to be suppressed so as to achieve the effect of suppressing the noise; when the difference is not small, the detail information needs to be enhanced, so that the contrast gain needs to be increased; when the difference is large, the detail information of the region is rich, the contrast gain needs to be reduced, otherwise, the noise is amplified. Similarly, when the variance is small, the contrast gain needs to be reduced to suppress noise; when the variance is not small, the contrast gain is required to be increased to enhance the detail information of the region; when the variance is large, the detail information of the region is rich, the contrast gain basically does not need to be adjusted, and otherwise, noise can be amplified. According to the above experience, a fuzzy rule base is established as shown in the following table, and the designed fuzzy controllers all adopt the Mamdani If-Then rule by taking the Mamdani If-Then rule as an example.
G1Fuzzy rule table
Di | NB | NS | Z | PS | PB |
G1 | NB | NS | PS | Z | NS |
G2Fuzzy rule table
Dvar | NB | NS | Z | PS | PB |
G2 | NB | NS | PB | Z | Z |
In the above table, DiIs the difference value of the maximum value and the minimum value of the gray value of the pixel point of the infrared image, DvarIs the variance, G1Is a difference DiWeight of (1), G2Is the variance weight.
The membership functions of the input and output variables are shown in FIG. 2, the abscissa is the discourse domain of the input and output variables, the ordinate is the membership degree, and NB, NS, Z, PS, and PB are five fuzzy subsets of the input and output variables.
6) After the input variables are fuzzified, which fuzzy rules are activated can be deduced according to the established fuzzy rule base, the output value obtained after the activated fuzzy rules are subjected to fuzzy reasoning is still a fuzzy value, and the fuzzy value is changed into an accurate output value by the step of resolving the fuzzy. Taking the gravity center method for blur solution as an example, the blur solution formula is shown as follows.
In the formula: u. ofN(xi) Is xiDegree of membership, xiThe abscissa corresponding to the area center.
7) After the ambiguity resolution, the difference weight G is obtained1Sum variance weight G2The gray value I after the contrast gain adjustment can be obtained by substituting the accurate value into the following formula.
I=(Iij-Imean)*G1+(Iij-Imean)*G2+Imean
In the formula: i isijIs the gray value of the point, ImeanIs the mean of the gray values of the region, G1Is a difference weight, G2Is the variance weight.
As can be seen from fig. 3, the infrared image contrast gain adjustment method based on the fuzzy control can effectively enhance the contrast and detail information of the infrared image, has a good suppression effect on the noise of the infrared image, and effectively improves the quality of the infrared image.
Claims (10)
1. An infrared image contrast gain adjusting method is characterized by comprising the following steps:
(1) segmenting an input infrared image to obtain different dimensional information of the infrared image;
(2) designing a fuzzy controller, determining an input variable and an output variable of the fuzzy controller, wherein the input variable of the fuzzy controller is a parameter capable of reflecting the whole fluctuation range of the infrared image and a parameter capable of reflecting the local information quantity respectively, so that the fuzzy controller can realize the function of adjusting the contrast gain of the infrared image;
(3) carrying out scale transformation on input variables and output variables of the fuzzy controller, and transforming the input variables and the output variables into respective discourse domain ranges, wherein the scale transformation formula is as follows:
in the formula: quantization factor kaDD is the discourse domain range, RIIs a range of values;
(4) fuzzy processing is carried out on the input variable, so that the accurate value of the input variable is converted into a fuzzy value;
(5) performing fuzzy reasoning, dividing input variables and output variables into A fuzzy subsets, and establishing a fuzzy rule base according to expert experience;
(6) performing deblurring, wherein the obtained output variable is still a fuzzy value after fuzzy reasoning, and the output variable is deblurred to be an accurate output quantity which can reflect the weight of the whole fluctuation of the infrared image and the weight of the local information quantity of the infrared image;
(7) calculating the gray value after the contrast gain adjustment, and substituting the output quantity into the following formula to obtain the gray value I after the contrast gain adjustment:
I=S1*G1+S2*G2+L+Sn*Gn
in the formula: s1,S2,…,SnAs input to a fuzzy controller, G1,G2,…,GnIs the output of the fuzzy controller.
2. The infrared image contrast gain adjustment method of claim 1, wherein the method of (1) segmenting the input infrared image comprises:
and dividing the infrared image into a plurality of squares to obtain different dimensionality information of the infrared image.
3. The infrared image contrast gain adjustment method of claim 1, wherein the blur controller in (2) comprises a multi-input multi-output blur controller or a single-input single-output blur controller.
4. The infrared image contrast gain adjustment method of claim 1, wherein the input variables in (2) are capable of reflecting an overall fluctuation range of the infrared image and a local information amount of the infrared image.
5. The infrared image contrast gain adjustment method of claim 1, wherein the blurring of the input variables in (4) includes any one of a hierarchical fuzzy set method, an input point membership 1 method, a single-point fuzzy set method, and a membership method.
6. The infrared image contrast gain adjustment method of claim 1, wherein the method of performing fuzzy inference in (5) includes any one of Mamdani fuzzy inference, Larsen fuzzy inference, Zadeh fuzzy inference, and Takagi-Sugeno fuzzy inference.
7. The infrared image contrast gain adjustment method of claim 6, wherein If-Then rule of the Mamdani fuzzy inference method is:
G1fuzzy rule table
G2Fuzzy rule table
In the above table, DiIs the difference value of the maximum value and the minimum value of the gray value of the pixel point of the infrared image, DvarIs the variance, G1Is a difference DiWeight of (1), G2Is the weight of the variance.
8. The infrared image contrast gain adjustment method of any one of claims 1 to 7, wherein the algorithm for resolving the blur in (6) includes any one of a maximum membership method, a barycentric method, and a median method.
9. A computer-readable storage medium, having stored thereon a computer program, characterized in that the computer program is executed by a processor for implementing the steps of the infrared image contrast gain adjustment method according to any one of claims 1 to 8.
10. An infrared detector comprising the computer readable storage medium of claim 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110907236.3A CN113763265A (en) | 2021-08-09 | 2021-08-09 | Infrared image contrast gain adjusting method, storage medium and infrared detector |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110907236.3A CN113763265A (en) | 2021-08-09 | 2021-08-09 | Infrared image contrast gain adjusting method, storage medium and infrared detector |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113763265A true CN113763265A (en) | 2021-12-07 |
Family
ID=78788758
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110907236.3A Pending CN113763265A (en) | 2021-08-09 | 2021-08-09 | Infrared image contrast gain adjusting method, storage medium and infrared detector |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113763265A (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7496237B1 (en) * | 2004-01-02 | 2009-02-24 | The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration | Image processing for binarization enhancement via fuzzy reasoning |
CN103020923A (en) * | 2011-09-28 | 2013-04-03 | 中国航天科工集团第二研究院二0七所 | Fuzzy-field-enhanced image preprocessing method for photoelectric search-track system |
CN104463804A (en) * | 2014-12-12 | 2015-03-25 | 中国科学院武汉物理与数学研究所 | Image enhancement method based on intuitional fuzzy set |
CN105139392A (en) * | 2015-08-18 | 2015-12-09 | 昆明理工大学 | Improved fuzzy inference rule edge detection method |
CN105787904A (en) * | 2016-03-25 | 2016-07-20 | 桂林航天工业学院 | Adaptive global dark channel prior image dehazing method for bright area |
CN107886485A (en) * | 2017-12-01 | 2018-04-06 | 国网山东省电力公司菏泽供电公司 | Image Method of Fuzzy Enhancement and system based on Logistic membership functions |
CN108495109A (en) * | 2018-03-23 | 2018-09-04 | 深圳市华星光电半导体显示技术有限公司 | Saturation degree Enhancement Method based on fuzzy control and device |
CN112598606A (en) * | 2020-12-18 | 2021-04-02 | 南京邮电大学 | Local self-adaptive infrared image enhancement method based on image decomposition |
-
2021
- 2021-08-09 CN CN202110907236.3A patent/CN113763265A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7496237B1 (en) * | 2004-01-02 | 2009-02-24 | The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration | Image processing for binarization enhancement via fuzzy reasoning |
CN103020923A (en) * | 2011-09-28 | 2013-04-03 | 中国航天科工集团第二研究院二0七所 | Fuzzy-field-enhanced image preprocessing method for photoelectric search-track system |
CN104463804A (en) * | 2014-12-12 | 2015-03-25 | 中国科学院武汉物理与数学研究所 | Image enhancement method based on intuitional fuzzy set |
CN105139392A (en) * | 2015-08-18 | 2015-12-09 | 昆明理工大学 | Improved fuzzy inference rule edge detection method |
CN105787904A (en) * | 2016-03-25 | 2016-07-20 | 桂林航天工业学院 | Adaptive global dark channel prior image dehazing method for bright area |
CN107886485A (en) * | 2017-12-01 | 2018-04-06 | 国网山东省电力公司菏泽供电公司 | Image Method of Fuzzy Enhancement and system based on Logistic membership functions |
CN108495109A (en) * | 2018-03-23 | 2018-09-04 | 深圳市华星光电半导体显示技术有限公司 | Saturation degree Enhancement Method based on fuzzy control and device |
CN112598606A (en) * | 2020-12-18 | 2021-04-02 | 南京邮电大学 | Local self-adaptive infrared image enhancement method based on image decomposition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109685743B (en) | Image mixed noise elimination method based on noise learning neural network model | |
Kanmani et al. | An image contrast enhancement algorithm for grayscale images using particle swarm optimization | |
CN110211056A (en) | Adaptive infrared image based on value histogram in part removes striped algorithm | |
CN116091455A (en) | Steel mesh surface defect judging method based on machine vision | |
CN110365404B (en) | Wavefront-free sensing self-adaptive system and method for improving convergence speed by using same | |
CN111861957A (en) | Image fusion method and device | |
CN116645608A (en) | Remote sensing target detection based on Yolox-Tiny biased feature fusion network | |
CN113763265A (en) | Infrared image contrast gain adjusting method, storage medium and infrared detector | |
CN112785512B (en) | Optimization method for Gaussian blur image processing | |
CN113838104A (en) | Registration method based on multispectral and multi-mode image consistency enhancement network | |
Zhang et al. | A fuzzy neural network approach for quantitative evaluation of mura in TFT-LCD | |
CN117649694A (en) | Face detection method, system and device based on image enhancement | |
Parihar et al. | A study on dark channel prior based image enhancement techniques | |
Beknazarova et al. | Iterative methods for solving managed problems of the television image processing | |
CN108765304B (en) | High-dynamic infrared image enhancement method based on adaptive gradient gain control | |
CN116416227A (en) | Background image processing method and device | |
CN115482434A (en) | Small sample high-quality generation method based on multi-scale generation countermeasure network | |
CN112634176B (en) | Mobile phone shot image denoising method based on multi-perception countermeasure generation network | |
CN114170109A (en) | Image noise reduction method and device based on MEMS (micro-electromechanical systems) stripe structured light | |
Li et al. | Infrared imaging enhancement through local window‐based saliency extraction with spatial weight | |
CN113132482A (en) | Distributed message system parameter adaptive optimization method based on reinforcement learning | |
CN112508168A (en) | Frame regression neural network construction method based on automatic correction of prediction frame | |
CN112001956A (en) | CNN-based schlieren strong laser far-field focal spot measurement image denoising method | |
Tai et al. | Research on Image Restoration Processing Based on Gaussian Blur Algorithm | |
Huang et al. | Image haze removal based on rolling deep learning and Retinex theory |
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 |