CN109377464A - A kind of Double plateaus histogram equalization method and its application system of infrared image - Google Patents
A kind of Double plateaus histogram equalization method and its application system of infrared image Download PDFInfo
- Publication number
- CN109377464A CN109377464A CN201811167737.7A CN201811167737A CN109377464A CN 109377464 A CN109377464 A CN 109377464A CN 201811167737 A CN201811167737 A CN 201811167737A CN 109377464 A CN109377464 A CN 109377464A
- Authority
- CN
- China
- Prior art keywords
- infrared image
- histogram
- accounting
- threshold value
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012545 processing Methods 0.000 claims description 17
- 238000009825 accumulation Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 3
- 238000005303 weighing Methods 0.000 claims 1
- 230000003014 reinforcing effect Effects 0.000 abstract description 11
- 238000004364 calculation method Methods 0.000 abstract description 2
- 238000010276 construction Methods 0.000 abstract 1
- 238000010187 selection method Methods 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 9
- 230000002708 enhancing effect Effects 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000005764 inhibitory process Effects 0.000 description 2
- 235000007926 Craterellus fallax Nutrition 0.000 description 1
- 240000007175 Datura inoxia Species 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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 discloses a kind of Double plateaus histogram equalization method and its application systems of infrared image, comprising: histogram upper limit platform threshold value THWith lower limit platform threshold value TLSelection and calculation method, the construction of Double tabletop histogram, Double plateaus histogram equalization step.The advantage is that: the reinforcing effect to infrared image is good, solve the problems, such as " excessively bright " occur in high gray area, and reduce gray level merging, preferably reservation image detail.Algorithm is simple, and operand is small, and real-time is good.In addition, keep the value of Double tabletop threshold value more scientific accurate without artificial setting parameter, it is more obvious to the reinforcing effect of infrared image, and its applicability is good, can have good reinforcing effect to various infrared images.
Description
Technical field
The present invention relates to infrared image enhancement processing technology fields, and in particular to a kind of Double tabletop histogram of infrared image
Equalize method and its application system.
Background technique
In infrared imagery technique, since the intrinsic resolution by infrared sensor is limited and infrared ray is in transmission process
In by Atmospheric Absorption and scattering effect so that the disadvantages of infrared image there are signal-to-noise ratio low, object edge and fuzzy details.For
Target can be correctly identified out, it is necessary to which enhancing pretreatment is carried out to infrared image.
Histogram equalization (HE) is a kind of common image enchancing method, it carries out ash according to the accumulation histogram of image
Degree adjustment has the characteristics that operation is simple, good to visible light image enhancement effects to achieve the effect that enhance image.Due to
Infrared image background and noise occupy a large amount of gray level, and the gray level of target is less, and infrared image is through histogram equalization
After change, the contrast of background and noise is enhanced, and the contrast of target is lowered, and " excessively bright " existing in the appearance of high gray area
As.Therefore, general histogram equalization is not suitable for the enhancing of infrared image.
Plateau equalization (PHE) is the innovatory algorithm of histogram equalization, on statistic histogram is arranged
Platform is limited, the inhibition of appropriateness is carried out to the background for occupying a large amount of pixels in image, leaves space to the promotion of target detail.It is double
Plateau equalization (DPHE) is the innovatory algorithm of plateau equalization, by the way that two fixed platform thresholds are arranged
Value, wherein upper limit platform threshold value is used to inhibit background and noise, and lower limit platform threshold value is used to promote target detail, and effect is better than
Plateau equalization.
The key for realizing Double plateaus histogram equalization is the selection of Double tabletop threshold value, and the Double tabletop threshold value indicates the upper limit
Platform threshold value and lower limit platform threshold value.Existing Double tabletop thresholding algorithm is more complicated, related with primary condition etc., and operation
Amount is big, is not easy real-time implementation.Thus, substantially carry out the selection of Double tabletop threshold value by rule of thumb at present.Therefore, how easily
Enhance infrared image, while making image enhancement effects good again, is a problem to be solved.
Summary of the invention
In order to solve the above-mentioned problems of the prior art, it is an object of that present invention to provide a kind of Double tabletops of infrared image
Histogram equalization method and its application system.The present invention is good to the reinforcing effect of infrared image, and calculation amount is small, and real-time is good.
A kind of Double plateaus histogram equalization method of infrared image of the present invention, comprising the following steps:
S0, original infrared image is obtained;
S1, it converts original infrared image to original infrared image histogram, and calculates the first accounting p (k);Described first
Accounting p (k) indicates accounting of k-th of gray level in original infrared image histogram,
P (k)=nk/ N k=0,1 ..., L-1,
N indicates that total number of pixels of original infrared image, the grey level distribution range of original infrared image are [0, L-1],
nkIndicate the number for the pixel that k-th of gray level occurs;
Non-zero unit in S2, the first accounting p (k) of extraction, composition set F (n) | 1≤n≤M1},M1For the first accounting p
(k) number of non-zero unit in;
S3, according to information entropy theory, take the average value a of the non-zero unit in the first accounting p (k) as upper limit platform threshold value
TH;Upper limit platform threshold value THExpression formula are as follows:
S4, the upper limit platform threshold value T obtained according to step S3H, upper limit platform limit is carried out to original infrared image histogram
Width processing obtains upper limit Plateau histogram, and calculates the second accountingSecond accountingIndicate k-th of gray scale
Accounting of the grade in upper limit Plateau histogram,
S5, the second accounting is extractedIn non-zero unit, constitute set G (n) | 1≤n≤M2},M2For the second accountingThe number of middle non-zero unit;
S6, according to information entropy theory, take the second accountingIn non-zero unit average value b as lower limit platform threshold
Value TL, lower limit platform threshold value TLExpression formula are as follows:
S7, the upper limit platform threshold value T according to obtained in step S3, S6H, lower limit platform threshold value TLConstruct Double tabletop histogram;
S8, the Double tabletop histogram according to obtained in step S7 carry out equalization processing to original infrared image.
Preferably, the step S7 includes: the upper limit platform threshold value T according to obtained in step S3, S6H, lower limit platform threshold
Value TLDouble tabletop histogram is converted by original infrared image histogram;And calculate third accounting pDT(k);The third accounting pDT
(k) accounting of k-th of gray level in Double tabletop histogram is indicated,
Preferably, the step S8 the following steps are included:
S81, accumulation histogram is converted by Double tabletop histogram, to third accounting pDT(k) summation obtains FDT(k),
S82, according to accumulation histogram and third accounting pDT(k) FDT(k) reallocation gray level D is calculatedDT(k),
Wherein, [] indicates to be rounded to obtain reallocation gray level D to the calculated result in []DT(k);
The reallocation gray level D that S83, basis are calculatedDT(k) gray level of original infrared image is redistributed, is obtained
Infrared image after obtaining equalization processing.
A kind of system of the Double plateaus histogram equalization method using the infrared image, including image acquisition unit,
Image processing unit and image output unit;Described image acquiring unit is used to obtain original infrared image, and will be original infrared
Image transmitting is to image processing unit;Original infrared image, operation obtain the upper limit and put down described image processing unit based on the received
Platform threshold value TH, lower limit platform threshold value TL, the upper limit platform threshold value T that is obtained according to operationH, lower limit platform threshold value TLTo original infrared
Image carries out Double plateaus histogram equalization, and the infrared image delivery after Double plateaus histogram equalization to image is exported list
Member;Described image output unit is for exporting received infrared image to other equipment.
A kind of Double plateaus histogram equalization method and its application system of infrared image of the present invention, advantage exist
In, it is good to the reinforcing effect of infrared image, solve the problems, such as " excessively bright " occur in high gray area, and reduce gray level merging,
Preferably retain image detail.Algorithm is simple, and operand is small, and real-time is good.In addition, making Double tabletop without artificial setting parameter
The value of threshold value is more scientific accurate, more obvious to the reinforcing effect of infrared image, and its applicability is good, can be to various infrared
Image has good reinforcing effect.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the Double plateaus histogram equalization method of infrared image of the present invention.
Fig. 2 is one of experimental result of the embodiment of the present invention.
Fig. 3 is the two of the experimental result of the embodiment of the present invention.
Fig. 4 is the three of the experimental result of the embodiment of the present invention.
Specific embodiment
As shown in Figure 1, a kind of Double plateaus histogram equalization method of infrared image of the present invention, including following step
It is rapid:
S0, original infrared image is obtained;
S1, it converts original infrared image to original infrared image histogram, and calculates the first accounting p (k);Described first
Accounting p (k) indicates accounting of k-th of gray level in original infrared image histogram,
P (k)=nk/ N k=0,1 ..., L-1,
N indicates that total number of pixels of original infrared image, the grey level distribution range of original infrared image are [0, L-1],
nkIndicate the number for the pixel that k-th of gray level occurs;
Non-zero unit in S2, the first accounting p (k) of extraction, composition set F (n) | 1≤n≤M1},M1For the first accounting p
(k) number of non-zero unit in;
S3, according to information entropy theory, take the average value a of the non-zero unit in the first accounting p (k) as upper limit platform threshold value
TH;Upper limit platform threshold value THExpression formula are as follows:
S4, the upper limit platform threshold value T obtained according to step S3H, upper limit platform limit is carried out to original infrared image histogram
Width processing obtains upper limit Plateau histogram, and calculates the second accountingSecond accountingIndicate k-th of gray scale
Accounting of the grade in upper limit Plateau histogram,
S5, the second accounting is extractedIn non-zero unit, constitute set G (n) | 1≤n≤M2},M2For the second accountingThe number of middle non-zero unit;
S6, according to information entropy theory, take the second accountingIn non-zero unit average value b as lower limit platform threshold
Value TL, lower limit platform threshold value TLExpression formula are as follows:
S7, the upper limit platform threshold value T according to obtained in step S3, S6H, lower limit platform threshold value TLConstruct Double tabletop histogram;
S8, the Double tabletop histogram according to obtained in step S7 carry out equalization processing to original infrared image.
The step S7 includes: the upper limit platform threshold value T according to obtained in step S3, S6H, lower limit platform threshold value TLIt will be former
Beginning infrared image histogram is converted into Double tabletop histogram;And calculate third accounting pDT(k);The third accounting pDT(k) it indicates
Accounting of k-th of gray level in Double tabletop histogram,
The value range of L expression gray level.Gray scale is that brightness is divided into 256 grades for monochrome, just what a
Byte.In the present embodiment, the value of L is 256, and the value range for representing gray level k is 0 to 255, totally 256 grades.
The specific configuration process of Double tabletop histogram herein are as follows: if a certain gray level is in original infrared image histogram
Accounting p be greater than upper limit platform threshold value TH, then it is revised as TH, realize and the higher image background of gray level and noise carried out
The effect of moderate inhibition;If accounting p of a certain gray level in original infrared image histogram is less than lower limit platform threshold value TL
And the value is not equal to 0, then the gray level is changed to TL, realize that carrying out appropriateness to the lesser image detail of gray level in image puts
Greatly.
The step S8 the following steps are included:
S81, accumulation histogram is converted by Double tabletop histogram, to third accounting pDT(k) summation obtains FDT(k),
S82, according to accumulation histogram and third accounting pDT(k) FDT(k) reallocation gray level D is calculatedDT(k),
Wherein, [] indicates to be rounded to obtain reallocation gray level D to the calculated result in []DT(k);Rounding can be upward
Or it is rounded downwards;
The reallocation gray level D that S83, basis are calculatedDT(k) gray level of original infrared image is redistributed, is obtained
Infrared image after obtaining equalization processing.
A kind of system of the Double plateaus histogram equalization method using the infrared image, including image acquisition unit,
Image processing unit and image output unit;Described image acquiring unit is used to obtain original infrared image, and will be original infrared
Image transmitting is to image processing unit;Original infrared image, operation obtain the upper limit and put down described image processing unit based on the received
Platform threshold value TH, lower limit platform threshold value TL, the upper limit platform threshold value T that is obtained according to operationH, lower limit platform threshold value TLTo original infrared
Image carries out Double plateaus histogram equalization, and the infrared image delivery after Double plateaus histogram equalization to image is exported list
Member;Described image output unit is for exporting received infrared image to other equipment.
Below in conjunction with experimental data, the Double plateaus histogram equalization, straight of infrared image of the present invention is respectively adopted
Side's figure equalization and three kinds of methods of platform histogram equalization carry out infrared image enhancement effect experiment.With comentropy H, ambiguity
Index FSAnd image grayscale series M is evaluation index, and the objective quantification of reinforcing effect is carried out to it.Index of fuzziness FSIt is fixed
Justice are as follows:
Q (x)=sin (0.5 π (1-I (x)/Imax))
In formula, Imax is the maximum gray scale of image.According to the definition of index of fuzziness, index of fuzziness FSIt is smaller, figure
As more clear.
The expression formula of comentropy H are as follows:
Experimental Hardware environment are as follows: AMD Athlon (tm) 64x2Dual core Processor 5200+2.7GHz,
1.75GB memory;Software environment are as follows: Windows XP Sp2+Matlab R2009b.The reinforcing effect image of three kinds of methods is shown in figure
2~Fig. 4, experimental result data are as shown in table 1.
From Fig. 2~Fig. 4, original image gray scale narrow dynamic range, picture contrast and clarity are low;Histogram equalization
(HE) image, gray scale dynamic model is big, but high grade grey level pixel increases much in histogram, causes the high gray area of image to occur serious
" excessively bright " phenomenon, and loss in detail, some mixed and disorderly ambient noises are amplified;Plateau equalization (PHE) image
Reinforcing effect is better than histogram equalization, but the clutter and noise in background are still larger, and " mistake still occurs in the high gray area of image
It is bright " phenomenon;High gray area is overcome using Double plateaus histogram equalization (DPHE) image of Double tabletop threshold value of the present invention to occur
" excessively bright " phenomenon, target sharpness is high, and ambient noise is low, and the subjective vision effect of image is better than other two kinds of methods.
As shown in Table 1, the present invention enhances the comentropy H value maximum of image, illustrates that the information that its image is included is greater than it
The image that his two kinds of processing methods obtain, image enhancement effects are obvious.Index of fuzziness FSIt is minimum, illustrate the clarity of its image
It is substantially better than the image that other two kinds of processing methods obtain.Image grayscale series M is maximum, and number of greyscale levels M is significantly greater than other
The image that two kinds of processing methods obtain, the value of M illustrate the ash of present invention enhancing image closer to the number of greyscale levels of original image
It spends grade to merge less, reinforcing effect is good, image detail more horn of plenty.This is just consistent with the result of subjective assessment.Experiment knot
Fruit shows: the Double plateaus histogram equalization method and its system practicability and effectiveness of infrared image of the present invention.
1 three kinds of Enhancement Method evaluation index comparisons of table
For those skilled in the art, it can make other each according to the above description of the technical scheme and ideas
The corresponding change of kind and deformation, and all these changes and deformation all should belong to the protection model of the claims in the present invention
Within enclosing.
Claims (4)
1. a kind of Double plateaus histogram equalization method of infrared image, which comprises the following steps:
S0, original infrared image is obtained;
S1, it converts original infrared image to original infrared image histogram, and calculates the first accounting p (k);First accounting
P (k) indicates accounting of k-th of gray level in original infrared image histogram,
P (k)=nk/ N k=0,1 ..., L-1,
N indicates that total number of pixels of original infrared image, the grey level distribution range of original infrared image are [0, L-1], nkIt indicates
The number for the pixel that k-th of gray level occurs;
Non-zero unit in S2, the first accounting p (k) of extraction, composition set F (n) | 1≤n≤M1},M1For in the first accounting p (k)
The number of non-zero unit;
S3, according to information entropy theory, take the average value a of the non-zero unit in the first accounting p (k) as upper limit platform threshold value TH;On
Limit platform threshold value THExpression formula are as follows:
S4, the upper limit platform threshold value T obtained according to step S3H, original infrared image histogram is carried out at upper limit platform clipping
Reason obtains upper limit Plateau histogram, and calculates the second accountingSecond accountingIndicate k-th of gray level
Accounting in upper limit Plateau histogram,
K=0,1 ..., L-1;
S5, the second accounting is extractedIn non-zero unit, constitute set G (n) | 1≤n≤M2},M2For the second accountingThe number of middle non-zero unit;
S6, according to information entropy theory, take the second accountingIn non-zero unit average value b as lower limit platform threshold value TL,
Lower limit platform threshold value TLExpression formula are as follows:
S7, the upper limit platform threshold value T according to obtained in step S3, S6H, lower limit platform threshold value TLConstruct Double tabletop histogram;
S8, the Double tabletop histogram according to obtained in step S7 carry out equalization processing to original infrared image.
2. a kind of Double plateaus histogram equalization method of infrared image according to claim 1, which is characterized in that the step
Rapid S7 includes: the upper limit platform threshold value T according to obtained in step S3, S6H, lower limit platform threshold value TLBy original infrared image histogram
Figure is converted into Double tabletop histogram;And calculate third accounting pDT(k);The third accounting pDT(k) indicate that k-th of gray level exists
Accounting in Double tabletop histogram,
K=0,1 ..., L-1.
3. a kind of Double plateaus histogram equalization method of infrared image according to claim 2, which is characterized in that the step
Rapid S8 the following steps are included:
S81, accumulation histogram is converted by Double tabletop histogram, to third accounting pDT(k) summation obtains FDT(k),
S82, according to accumulation histogram and third accounting pDT(k) FDT(k) reallocation gray level D is calculatedDT(k),
Wherein, [] indicates to be rounded to obtain reallocation gray level D to the calculated result in []DT(k);
The reallocation gray level D that S83, basis are calculatedDT(k) gray level of original infrared image is redistributed, is obtained equal
Weighing apparatusization treated infrared image.
4. a kind of system of the Double plateaus histogram equalization method using any infrared image of claims 1 to 3, special
Sign is, including image acquisition unit, image processing unit and image output unit;Described image acquiring unit is for obtaining original
Beginning infrared image, and by original infrared image delivery to image processing unit;Described image processing unit is original based on the received
Infrared image, operation obtain upper limit platform threshold value TH, lower limit platform threshold value TL, the upper limit platform threshold value T that is obtained according to operationH, under
Limit platform threshold value TLDouble plateaus histogram equalization is carried out to original infrared image, and will be red after Double plateaus histogram equalization
Outer image transmitting is to image output unit;Described image output unit is for exporting received infrared image to other equipment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811167737.7A CN109377464B (en) | 2018-10-08 | 2018-10-08 | Double-platform histogram equalization method for infrared image and application system thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811167737.7A CN109377464B (en) | 2018-10-08 | 2018-10-08 | Double-platform histogram equalization method for infrared image and application system thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109377464A true CN109377464A (en) | 2019-02-22 |
CN109377464B CN109377464B (en) | 2021-07-20 |
Family
ID=65403770
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811167737.7A Active CN109377464B (en) | 2018-10-08 | 2018-10-08 | Double-platform histogram equalization method for infrared image and application system thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109377464B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110400274A (en) * | 2019-07-19 | 2019-11-01 | 西安科技大学 | A kind of vehicle mounted infrared pedestrian detection infrared image enhancing method |
CN112348763A (en) * | 2020-11-09 | 2021-02-09 | 西安宇视信息科技有限公司 | Image enhancement method, device, electronic equipment and medium |
CN113191990A (en) * | 2021-05-28 | 2021-07-30 | 浙江宇视科技有限公司 | Image processing method and device, electronic equipment and medium |
CN113487525A (en) * | 2021-07-06 | 2021-10-08 | 河南慧联世安信息技术有限公司 | Self-iterative infrared image enhancement method based on double-platform histogram |
CN113888451A (en) * | 2020-07-02 | 2022-01-04 | 北京华科德科技有限公司 | Infrared image processing method and device and electronic equipment |
CN115660997A (en) * | 2022-11-08 | 2023-01-31 | 杭州微影软件有限公司 | Image data processing method and device and electronic equipment |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102521813A (en) * | 2011-11-21 | 2012-06-27 | 华中科技大学 | Infrared image adaptive enhancement method based on dual-platform histogram |
CN102693531A (en) * | 2012-01-11 | 2012-09-26 | 河南科技大学 | Adaptive double-platform based infrared image enhancement method |
US20120257164A1 (en) * | 2011-04-07 | 2012-10-11 | The Chinese University Of Hong Kong | Method and device for retinal image analysis |
CN103353349A (en) * | 2013-06-18 | 2013-10-16 | 南京理工大学 | Infrared-thermometer self-adaption three platform histogram equalization system and method thereof |
CN103747537A (en) * | 2014-01-15 | 2014-04-23 | 广东交通职业技术学院 | Wireless sensor network outlier data self-adaption detecting method based on entropy measurement |
CN104392417A (en) * | 2014-11-28 | 2015-03-04 | 嘉应学院 | Image haze removal method based on pixel dark channel and anisotropic diffusion filtering |
CN104408695A (en) * | 2014-12-05 | 2015-03-11 | 嘉应学院 | Infrared image intensification method through histogram fuzzy weighting adjustment and equalization |
CN105913406A (en) * | 2016-04-08 | 2016-08-31 | 北京航天计量测试技术研究所 | SoPC-based novel infrared image enhancement processing method |
WO2017052948A1 (en) * | 2015-09-25 | 2017-03-30 | Intel Corporation | Histogram-based image segmentation |
CN108122217A (en) * | 2016-11-30 | 2018-06-05 | 北京航天计量测试技术研究所 | A kind of real-time infrared image Enhancement Method of adaptive scene |
-
2018
- 2018-10-08 CN CN201811167737.7A patent/CN109377464B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120257164A1 (en) * | 2011-04-07 | 2012-10-11 | The Chinese University Of Hong Kong | Method and device for retinal image analysis |
CN102521813A (en) * | 2011-11-21 | 2012-06-27 | 华中科技大学 | Infrared image adaptive enhancement method based on dual-platform histogram |
CN102693531A (en) * | 2012-01-11 | 2012-09-26 | 河南科技大学 | Adaptive double-platform based infrared image enhancement method |
CN103353349A (en) * | 2013-06-18 | 2013-10-16 | 南京理工大学 | Infrared-thermometer self-adaption three platform histogram equalization system and method thereof |
CN103747537A (en) * | 2014-01-15 | 2014-04-23 | 广东交通职业技术学院 | Wireless sensor network outlier data self-adaption detecting method based on entropy measurement |
CN104392417A (en) * | 2014-11-28 | 2015-03-04 | 嘉应学院 | Image haze removal method based on pixel dark channel and anisotropic diffusion filtering |
CN104408695A (en) * | 2014-12-05 | 2015-03-11 | 嘉应学院 | Infrared image intensification method through histogram fuzzy weighting adjustment and equalization |
WO2017052948A1 (en) * | 2015-09-25 | 2017-03-30 | Intel Corporation | Histogram-based image segmentation |
CN105913406A (en) * | 2016-04-08 | 2016-08-31 | 北京航天计量测试技术研究所 | SoPC-based novel infrared image enhancement processing method |
CN108122217A (en) * | 2016-11-30 | 2018-06-05 | 北京航天计量测试技术研究所 | A kind of real-time infrared image Enhancement Method of adaptive scene |
Non-Patent Citations (4)
Title |
---|
JUN HUANG ET AL: ""Infrared image enhancement algorithm based on adaptive histogram segmentation"", 《APPLIED OPTICS》 * |
宋岩峰 等: ""基于双平台直方图的红外图像增强算法"", 《红外与激光工程》 * |
胡振龙: ""自然环境下人脸识别技术研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
龚昌来 等: ""基于加权直方图均衡的红外图像增强方法"", 《激光与红外》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110400274A (en) * | 2019-07-19 | 2019-11-01 | 西安科技大学 | A kind of vehicle mounted infrared pedestrian detection infrared image enhancing method |
CN113888451A (en) * | 2020-07-02 | 2022-01-04 | 北京华科德科技有限公司 | Infrared image processing method and device and electronic equipment |
CN112348763A (en) * | 2020-11-09 | 2021-02-09 | 西安宇视信息科技有限公司 | Image enhancement method, device, electronic equipment and medium |
CN112348763B (en) * | 2020-11-09 | 2024-05-14 | 西安宇视信息科技有限公司 | Image enhancement method, device, electronic equipment and medium |
CN113191990A (en) * | 2021-05-28 | 2021-07-30 | 浙江宇视科技有限公司 | Image processing method and device, electronic equipment and medium |
CN113191990B (en) * | 2021-05-28 | 2023-05-23 | 浙江宇视科技有限公司 | Image processing method, device, electronic equipment and medium |
CN113487525A (en) * | 2021-07-06 | 2021-10-08 | 河南慧联世安信息技术有限公司 | Self-iterative infrared image enhancement method based on double-platform histogram |
CN113487525B (en) * | 2021-07-06 | 2022-07-01 | 河南慧联世安信息技术有限公司 | Self-iterative infrared image enhancement method based on double-platform histogram |
CN115660997A (en) * | 2022-11-08 | 2023-01-31 | 杭州微影软件有限公司 | Image data processing method and device and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN109377464B (en) | 2021-07-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109377464A (en) | A kind of Double plateaus histogram equalization method and its application system of infrared image | |
Shi et al. | Normalised gamma transformation‐based contrast‐limited adaptive histogram equalisation with colour correction for sand–dust image enhancement | |
CN102693531B (en) | Adaptive double-platform based infrared image enhancement method | |
Ma et al. | An effective fusion defogging approach for single sea fog image | |
CN106651818A (en) | Improved Histogram equalization low-illumination image enhancement algorithm | |
CN105303561A (en) | Image preprocessing grayscale space division method | |
CN110298796B (en) | Low-illumination image enhancement method based on improved Retinex and logarithmic image processing | |
CN105139366A (en) | Image enhancement method based on space domain | |
CN102436647A (en) | Image enhancement method based on adaptive gray mapping | |
CN106529543B (en) | A kind of dynamic calculates the method and its system of polychrome grade binaryzation adaptive threshold | |
CN108805829A (en) | Video data processing method, device, equipment and computer readable storage medium | |
CN105046677A (en) | Enhancement processing method and apparatus for traffic video image | |
CN110276764A (en) | K-Means underwater picture background segment innovatory algorithm based on the estimation of K value | |
CN105225238A (en) | A kind of gray space division methods of the Image semantic classification based on mean filter | |
CN112991197B (en) | Low-illumination video enhancement method and device based on detail preservation of dark channel | |
Zhuang et al. | Adaptive Image Enhancement Using Entropy‐Based Subhistogram Equalization | |
CN100377169C (en) | Method for picture binaryzation | |
Wei et al. | An image fusion dehazing algorithm based on dark channel prior and retinex | |
He et al. | A night low‐illumination image enhancement model based on small probability area filtering and lossless mapping enhancement | |
CN109859138B (en) | Infrared image enhancement method based on human visual characteristics | |
CN111027564A (en) | Low-illumination imaging license plate recognition method and device based on deep learning integration | |
CN110633705A (en) | Low-illumination imaging license plate recognition method and device | |
CN116309168A (en) | Low-illumination image enhancement method and system for parallel hybrid attention progressive fusion | |
CN103839231A (en) | Image enhancement method based on maximization of human vision minimum detection probability | |
Parihar | Histogram modification and DCT based contrast 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 |