CN108876738A - A kind of mono- scape image internal brightness compensation method of SAR based on gamma correction - Google Patents
A kind of mono- scape image internal brightness compensation method of SAR based on gamma correction Download PDFInfo
- Publication number
- CN108876738A CN108876738A CN201810588116.XA CN201810588116A CN108876738A CN 108876738 A CN108876738 A CN 108876738A CN 201810588116 A CN201810588116 A CN 201810588116A CN 108876738 A CN108876738 A CN 108876738A
- Authority
- CN
- China
- Prior art keywords
- image
- gray level
- gamma correction
- mono
- sar
- 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 43
- 230000000694 effects Effects 0.000 abstract description 12
- 238000001914 filtration Methods 0.000 description 19
- 230000000717 retained effect Effects 0.000 description 7
- 206010027146 Melanoderma Diseases 0.000 description 5
- 230000009466 transformation Effects 0.000 description 4
- 235000008331 Pinus X rigitaeda Nutrition 0.000 description 3
- 235000011613 Pinus brutia Nutrition 0.000 description 3
- 241000018646 Pinus brutia Species 0.000 description 3
- 230000000052 comparative effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 241000167857 Bourreria Species 0.000 description 2
- 238000005315 distribution function Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000005070 sampling Methods 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
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- 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
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to digital image processing techniques fields, and in particular to a kind of mono- scape image internal brightness compensation method of SAR based on gamma correction, including step in detail below：S1：By traversing image, pixel gray level maximum value is found；S2：Obtain normalized image；S3：Carry out gamma correction；S4：Make error image, error image is made to the image after normalized image and correction；S5：Gray level is adjusted, by error image multiplied by pixel gray level maximum value, obtaining error image grey level range is [0-255], and the result images for adjusting gray level are the final result image of algorithm process；S6：Export image, output S5 treated image.The mono- scape image internal brightness compensation method of SAR based on gamma correction of the invention has the characteristics that the accurate compensation that can be realized brightness of image, and even color effect and reservation information are more excellent.
Description
Technical field
The invention belongs to technical field of image processing, and in particular to inside a kind of mono- scape image of SAR based on gamma correction
Luminance compensation method.
Background technique
No. three satellites of high score are a remote sensing satellites of Chinese high score specialty work, are the conjunctions that imaging pattern is most in the world
At aperture radar (SAR) satellite.Satellite imagery breadth is big, combines with high spatial resolution advantage, has both been able to achieve a wide range of general
Look into, also can detailed survey specific region, can meet different user to different target be imaged the needs of.
It is single however due to SAR imaging angle, landform, the variation of radar antenna figure and the strong back scattering of special atural object
Occur the non-uniform problem of Luminance Distribution inside width SAR image, shows apparent bright road, seriously affect the subsequent processing of image
With interpretation, it is particularly important so effectively even color can be carried out to image and handled.
No. three satellites of high score can obtain high-resolution SAR image, with details such as apparent edge, point, textures
Feature, so how to retain apparent detailed information while eliminating bright road is the another of the even color processing of three SAR image of high score
A important goal.
Solution (the king nation pine .SAR image autoregistration using frequency domain low-pass filtering that 2015 Nian Wang nation pines propose
With method for embedding study [D] Wuhan University, 2015), referring to fig. 4, the solution process of frequency domain low-pass filtering is as follows：
Original image progress Fast Fourier Transform (FFT) is obtained into Fourier spectrum figure first, frequency domain Gauss is obtained by given cutoff frequency
Fourier spectrum figure, is multiplied with frequency domain Gaussian filter to obtain the spectrogram after low-pass filtering by filter, then by low-pass filtering
Spectrogram afterwards carries out inverse fast Fourier transform and obtains background image, finally by original image and background image corresponding pixel points
Pixel value subtract each other to obtain result images.In terms of physical effect, Fourier transform is that image is changed to frequency domain from transform of spatial domain,
Its inverse transformation is that image is transformed into spatial domain from frequency domain.In other words, the physical significance of Fourier transform is by image
Distributed function is transformed to the frequency distribution function of image, and inverse fourier transform is to be transformed to the frequency distribution function of image
Distributed function, before Fourier transform, image is led to by obtaining the set of series of points to the sampling on continuous space
Each point on a common two-dimensional matrix representation space.Again because space be it is three-dimensional, image is two-dimensional, therefore object exists in space
Relationship in another dimension must just be indicated that we could learn object in three-dimensional space by observing image in this way by gradient
Between in corresponding relationship.Two-dimension fourier transform is carried out to image and obtains spectrogram, is exactly the distribution map of image gradient.
In image procossing, many characteristics of gauss low frequency filter are widely used it, the height of frequency domain
The mathematic(al) representation of this low-pass filter is：
H is gauss low frequency filter, and u, v are respectively the laterally and longitudinally coordinate of frequency domain, and D (u, v) is frequency domain coordinates system
In a bit (u, v) arrive coordinate origin (0,0) plan range, D0It is the cutoff frequency of filter.
As can be seen from the above equation, if given cutoff frequency D0It is bigger than normal, then it is bigger than normal to will lead to gauss low frequency filter numerical value；
If given cutoff frequency D0It is less than normal, then it is less than normal to will lead to gauss low frequency filter numerical value.
Low-pass filtering is the low frequency component in image to be retained and removes the high fdrequency component in image.Edge in image and
High frequency section in noise all correspondence image frequency domains, can remove or slacken influence of noise simultaneously by low-pass filtering in a frequency domain
Fuzzy edge profile.In order to preferably remove or slacken influence of noise and fuzzy edge profile, cutoff frequency D0Selection cannot
It is less than normal.
Frequency domain low-pass filtering algorithm can reduce the bright road of image to a certain extent, but it is existing simultaneously not operatively to eliminate bright road
As the gray level of result images still shows more apparent difference；And cutoff frequency is bigger than normal to lead to Gaussian filter number
It is worth larger, being multiplied obtains spectrogram after low-pass filtering and carry out the background image pixel values that inverse fast Fourier transform obtains being greater than original
Image pixel value, then the respective pixel gray value of error image just will appear negative value.And image data range is [0-255], phase
It is 0 that the pixel for subtracting to obtain negative value can be mended automatically, and original detailed information can be shown as the black of gray value 0 by these pixels
Point causes result images not only to lose corresponding detailed information, but also shows black spot phenomenon on luminance compensation image.Always
It, in terms of even color effect and information retain two, all without obtaining good effect.
Summary of the invention
In order to solve the above-mentioned problems in the prior art, the present invention provides a kind of SAR based on gamma correction is mono-
Scape image internal brightness compensation method, it using power law transformation in gamma correction method, can strict guarantee error image not
It will appear negative value, reduce the loss of information, it is ensured that the precision of brightness of image adjustment has even color effect and retains information more
Excellent feature.
The technical problem to be solved in the present invention is achieved through the following technical solutions：
Including step in detail below：
S1：By traversing image, pixel gray level maximum value I is foundmax。
S2：Obtain normalized image
With each pixel gray value of original image divided by the pixel gray level maximum value Imax, obtain normalization figure
The pixel gray value of original image is mapped in [0,1] range and obtains image I by pictureN；That is, normalized imageIN∈[0,1]；
S3：Carry out gamma correction
To the normalized imageUse gamma correctionImage after being corrected,
In, c (0 < c < 1) is constant, and γ (γ > 1) is Gamma factor, due to IN∈ [0,1], 0 < c < 1, λ > 1 are apparent from JN∈[0,
, and and if only if I 1)NWhen taking 0, JNIt is 0；
S4：Make error image
To the normalized imageWith the image after the correctionMake difference, obtains difference
Image is：Δ J=IN-JN, wherein Δ J >=0；
S5：Adjust gray level
By the error image Δ J=IN-JNMultiplied by the pixel gray level maximum value Imax, it is adjusted the knot of gray level
Fruit image, it is described adjustment gray level result images result grey level range be [0-255], and it is described adjustment gray level result
Image is the final result image of algorithm process；
S6：Export image
Export the final result image of the algorithm process.
Further, in S1, scape image mono- for SAR, the image is uint8 format, and gray value data range is [0-
255], each pixel is a gray value of [0-255], traverses original image I by circulation all pixels point, finds picture
Vegetarian refreshments gray scale maximum value Imax。
Compared with prior art, the present invention has beneficial effect below：
The present invention handles normalized image, not only makes gamma using the method for gamma correction in power law transformation
Image after correction can obtain effective luminance compensation, and image is made to obtain preferably even color effect；Meanwhile after making gamma correction
Image pixel gray level value be not more than original normalized image grey scale pixel value, avoid corresponding subtract each other between pixel and negative value occur
The case where, reduce the loss of information, to realize the accurate compensation of brightness of image.
Detailed description of the invention
Fig. 1 is the flow chart of the method for the present invention.
Fig. 2 (a), Fig. 2 (b), Fig. 2 (c), which are one group of three SAR images of high score, passes through distinct methods treated image comparison；
Wherein, Fig. 2 (a) is untreated original image；Fig. 2 (b) is the image after frequency domain low-pass filtering treatment,
Wherein, cutoff frequency 6；Fig. 2 (c) is the method for the present invention treated image, wherein (c=0.7, γ=10).
Fig. 3 (a), Fig. 3 (b), Fig. 3 (c), which are another group of three SAR images of high score, passes through distinct methods treated image pair
Than；
Wherein, Fig. 3 (a) is untreated original image；Fig. 3 (b) is the image after frequency domain low-pass filtering treatment,
Wherein, cutoff frequency 6；Fig. 3 (c) is the method for the present invention treated image, wherein (c=0.99, γ=20).
Fig. 4 is the flow chart of frequency domain low-pass filtering method.
Specific embodiment
In order to make the objectives, technical solutions and advantages of the present invention clearer, with reference to the accompanying drawing to the present invention make with
Detailed description.However, it should be understood that these descriptions are merely illustrative, and it is not intended to limit the scope of the invention.In addition, with
In lower explanation, the description of part common knowledge and technology is omitted, obscures the understanding of the present invention to avoid unnecessary.
It is single due to SAR satellite imagery angle, landform, the variation of radar antenna figure and the strong back scattering of special atural object
Occur the non-uniform problem of Luminance Distribution inside width SAR image, shows apparent bright road, seriously affect the subsequent processing of image
With interpretation, it is particularly important so effectively even color can be carried out to image and handled.
No. three satellites of high score can obtain high-resolution SAR image, with details such as apparent edge, point, textures
Feature, so how to retain apparent detailed information while eliminating bright road is the another of the even color processing of three SAR image of high score
A important goal.
It is the specific implementation program for realizing its required processing result below：
Referring to Fig. 1, a kind of mono- scape image internal brightness compensation method of SAR based on gamma correction of the present invention is specific to walk
It is rapid as follows：
S1：Scape image mono- for SAR, the image are uint8 format, and gray value data range is [0-255], each picture
Vegetarian refreshments is a gray value of [0-255], traverses original image I by circulation all pixels point, finds pixel gray level maximum
Value Imax。
S2：Obtain normalized image
With each pixel gray value of original image divided by the pixel gray level maximum value Imax, obtain normalization figure
The pixel gray value of original image is mapped in [0,1] range and obtains image I by pictureN；That is, normalized imageIN∈[0,1]；
S3：Carry out gamma correction
To the normalized imageUse gamma correctionImage after being corrected,
In, c (0 < c < 1) is constant, and γ (γ > 1) is Gamma factor, due to IN∈ [0,1], 0 < c < 1, λ > 1 are apparent from JN∈[0,
, and and if only if I 1)NWhen taking 0, JNIt is 0；
S4：Make error image
To the normalized imageWith the image after the correctionMake difference, obtains difference
Image is：Δ J=IN-JN, wherein Δ J >=0；
S5：Adjust gray level
By the error image Δ J=IN-JNMultiplied by the pixel gray level maximum value Imax, it is adjusted the knot of gray level
Fruit image, it is described adjustment gray level result images result grey level range be [0-255], and it is described adjustment gray level result
Image is the final result image of algorithm process；
S6：Export image
Export the final result image of the algorithm process.
It compares and analyzes the following are specific result：
Comparative example 1：
(a) is untreated original image referring to fig. 2；
Fig. 2 (b) is image of the original image after frequency domain low-pass filtering treatment, wherein cutoff frequency 6；
Fig. 2 (c) is the image obtained after the method for the present invention is handled, wherein c=0.7, γ=10；
Comparison diagram 2 (a) and Fig. 2 (b), it is known that, referring to fig. 2 (a), original of the untreated original image due to radiant correction
There is the problem of brightness irregularities in SAR image in cause, shows apparent bright road phenomenon.For the smooth development of subsequent processing,
It has to compensate the brightness of image, i.e., even color processing is carried out to the road image Zhong Liang.Obviously, referring to fig. 2 (b), through frequency
Rate domain low-pass filtering method treated image, it can be seen that the bright road of image can be reduced to a certain extent, but there is no effectively
The bright road phenomenon of elimination, the gray level of result images still shows more apparent difference, i.e., preferable bright there is no obtaining
Degree compensation and even color effect.Especially since frequency domain low-pass filtering method cannot be guaranteed that the gray level of background image is strictly small
It will appear negative situation in the gray level of original image, therefore error image, thus have lost corresponding detailed information, in image
On show many black spot phenomenons.
Wherein, even color be in one or more image brightness, contrast, tone, saturation distribution non-uniform phenomenon into
Row correction, keeps the brightness of each position of image, contrast, tone, saturation degree almost the same.Luminance compensation is exactly at a kind of even color
Reason.
Fig. 2 (c) is that the present invention is based on the image of the mono- scape image internal brightness compensation method processing of the SAR of gamma correction, ginsengs
See Fig. 2 (c), the luminance compensation method based on gamma correction that the present invention is mentioned, by carrying out reasonable power to normalized image
The gamma correction of rate transformation, can effectively eliminate the influence of bright road phenomenon, obtain ideal even color effect.Meanwhile this hair
Bright mentioned method can guarantee that the gray level of error image is not in negative, thus can be effectively retained the details letter of image
Breath, avoids the appearance of black spot phenomenon, carries out subsequent processing efficiently.In short, retaining two from even color effect and information
Aspect, mentioned method are substantially better than frequency domain low-pass filtering method.
To sum up, comparison diagram 2 (a), Fig. 2 (b), Fig. 2 (c), it is known that, occur in untreated original image SAR image bright
Non-uniform problem is spent, apparent bright road phenomenon is shown；And the image after frequency domain low-pass filtering treatment, it can be seen that energy
It is enough to reduce the bright road of image to a certain extent, but bright road phenomenon is not effectively eliminated, the gray level of result images is still presented
More apparent difference out；Meanwhile because the gray level of error image will appear negative, the details letter of image cannot be effectively retained
Breath；The image of the method for the present invention processing, can effectively eliminate the influence of bright road phenomenon, obtain ideal even color effect, this
Inventing proposed method can guarantee that the gray level of error image is not in negative, thus can be effectively retained the details letter of image
Breath, avoids the appearance of black spot phenomenon, carries out subsequent processing efficiently.
Treated in order to further illustrating the method for the present invention image effect is better than Wang Bangsong (king nation pine .SAR image
Autoregistration and method for embedding study [D] Wuhan University, 2015) processing method for the frequency domain low-pass filtering mentioned in paper,
Make to compare further below：
Comparative example 2：
Different from comparative example 1 groups of three SAR image of high score；Referring to Fig. 3 (a), referring to Fig. 3 (b), referring to Fig. 3 (c)；
Fig. 3 (a) is untreated original image；
Fig. 3 (b) is image of the original image after frequency domain low-pass filtering treatment, wherein cutoff frequency 6；
Fig. 3 (c) is the image obtained after the method for the present invention is handled, wherein c=0.99, γ=20；
Comparison diagram 3 (a), Fig. 3 (b) and Fig. 3 (c) are same available, occur in untreated original image SAR image
The problem of brightness irregularities, shows apparent bright road phenomenon；And the image after frequency domain low-pass filtering treatment, it can be seen that
The bright road of image can be reduced to a certain extent, but does not effectively eliminate bright road phenomenon, and the gray level of result images is still in
Reveal more apparent difference；Meanwhile because the gray level of error image will appear negative, the details of image cannot be effectively retained
Information；The image of the method for the present invention processing, can effectively eliminate the influence of bright road phenomenon, obtain ideal even color effect,
The mentioned method of the present invention can guarantee that the gray level of error image is not in negative, thus can be effectively retained the details of image
Information avoids the appearance of black spot phenomenon, carries out subsequent processing efficiently.
As it can be seen that the method for the present invention can effectively eliminate bright road phenomenon, ideal even color effect is obtained；Meanwhile energy
Enough guarantee that the gray level of error image is not in negative, thus the detailed information of image can be effectively retained, avoids stain
The appearance of phenomenon.
The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be said that
Specific implementation of the invention is only limited to these instructions.For those of ordinary skill in the art to which the present invention belongs, exist
Under the premise of not departing from present inventive concept, a number of simple deductions or replacements can also be made, all shall be regarded as belonging to of the invention
Protection scope.
Claims (2)
1. a kind of mono- scape image internal brightness compensation method of SAR based on gamma correction, which is characterized in that specific step is as follows：
S1：By traversing image, pixel gray level maximum value I is foundmax；
S2：Obtain normalized image
With each pixel gray value of original image divided by pixel gray level maximum value Imax, obtain normalized image, i.e., it will be former
The pixel gray value of beginning image maps in [0,1] range and obtains image IN；That is, normalized imageIN∈[0,
1]；
S3：Carry out gamma correction
To normalized imageUse gamma correctionImage after being corrected, wherein c (0 < c
< 1) it is constant, γ (γ > 1) is Gamma factor, due to IN∈ [0,1], 0 < c < 1, λ > 1 are apparent from JN∈ [0,1), and only
Work as INWhen taking 0, JNIt is 0；
S4：Make error image
To normalized imageWith the image after correctionIt is obtained as error image：Δ J=IN-JN, wherein
ΔJ≥0；
S5：Adjust gray level
By error image Δ J=IN-JNMultiplied by pixel gray level maximum value Imax, obtaining error image grey level range is [0-
255], the result images for adjusting gray level are the final result image of algorithm process；
S6：Export image
Export S5 treated image.
2. the mono- scape image internal brightness compensation method of a kind of SAR based on gamma correction according to claim 1, feature
It is, the S1 is specifically：
Scape image mono- for SAR, the image are uint8 format, and gray value data range is [0-255], each pixel is
One gray value of [0-255] traverses original image I by circulation all pixels point, finds pixel gray level maximum value Imax。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810588116.XA CN108876738A (en) | 2018-06-08 | 2018-06-08 | A kind of mono- scape image internal brightness compensation method of SAR based on gamma correction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810588116.XA CN108876738A (en) | 2018-06-08 | 2018-06-08 | A kind of mono- scape image internal brightness compensation method of SAR based on gamma correction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108876738A true CN108876738A (en) | 2018-11-23 |
Family
ID=64337598
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810588116.XA Pending CN108876738A (en) | 2018-06-08 | 2018-06-08 | A kind of mono- scape image internal brightness compensation method of SAR based on gamma correction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108876738A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110132823A (en) * | 2019-05-15 | 2019-08-16 | 林伟阳 | A kind of method for cell count based on template matching and lookup profile |
| CN110246091A (en) * | 2019-04-25 | 2019-09-17 | 新疆大学 | The method and apparatus for determining SAR figure diff area |
| CN112950657A (en) * | 2021-03-29 | 2021-06-11 | 合肥京东方显示技术有限公司 | Gamma value correction method, gamma value correction device, electronic device, and readable storage medium |
| CN113870233A (en) * | 2021-09-30 | 2021-12-31 | 常州市宏发纵横新材料科技股份有限公司 | Binding yarn detection method, computer equipment and storage medium |
| WO2023142915A1 (en) * | 2022-01-29 | 2023-08-03 | 京东方科技集团股份有限公司 | Image processing method, apparatus and device, and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567959A (en) * | 2010-12-31 | 2012-07-11 | 新奥特（北京）视频技术有限公司 | Multi-way image grey adjusting method |
| US20170098429A1 (en) * | 2009-09-01 | 2017-04-06 | Entertainment Experience Llc | Method for producing a color image and imaging device employing same |
| CN107527333A (en) * | 2017-07-31 | 2017-12-29 | 湖北工业大学 | A kind of rapid image Enhancement Method based on gamma transformation |
-
2018
- 2018-06-08 CN CN201810588116.XA patent/CN108876738A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170098429A1 (en) * | 2009-09-01 | 2017-04-06 | Entertainment Experience Llc | Method for producing a color image and imaging device employing same |
| CN102567959A (en) * | 2010-12-31 | 2012-07-11 | 新奥特（北京）视频技术有限公司 | Multi-way image grey adjusting method |
| CN107527333A (en) * | 2017-07-31 | 2017-12-29 | 湖北工业大学 | A kind of rapid image Enhancement Method based on gamma transformation |
Non-Patent Citations (1)
| Title |
|---|
| 刘祖根著: "《图像隐写分析算法研究及其应用》", 31 January 2016, 西南交通大学出版社 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110246091A (en) * | 2019-04-25 | 2019-09-17 | 新疆大学 | The method and apparatus for determining SAR figure diff area |
| CN110132823A (en) * | 2019-05-15 | 2019-08-16 | 林伟阳 | A kind of method for cell count based on template matching and lookup profile |
| CN112950657A (en) * | 2021-03-29 | 2021-06-11 | 合肥京东方显示技术有限公司 | Gamma value correction method, gamma value correction device, electronic device, and readable storage medium |
| CN113870233A (en) * | 2021-09-30 | 2021-12-31 | 常州市宏发纵横新材料科技股份有限公司 | Binding yarn detection method, computer equipment and storage medium |
| WO2023142915A1 (en) * | 2022-01-29 | 2023-08-03 | 京东方科技集团股份有限公司 | Image processing method, apparatus and device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108876738A (en) | A kind of mono- scape image internal brightness compensation method of SAR based on gamma correction | |
| Wang et al. | Naturalness preserved enhancement algorithm for non-uniform illumination images | |
| CN107301661B (en) | High-resolution remote sensing image registration method based on edge point features | |
| CN105931201B (en) | A kind of image subjective vision effect reinforcing method based on wavelet transformation | |
| CN110232661A (en) | Low illumination colour-image reinforcing method based on Retinex and convolutional neural networks | |
| CN103942769B (en) | A kind of satellite remote-sensing image fusion method | |
| CN112307901A (en) | Landslide detection-oriented SAR and optical image fusion method and system | |
| CN111968065B (en) | Self-adaptive enhancement method for image with uneven brightness | |
| CN106971379A (en) | A kind of underwater picture Enhancement Method merged based on stratified calculation | |
| Paul et al. | Plateau limit‐based tri‐histogram equalisation for image enhancement | |
| Wei et al. | Ship detection in remote sensing image based on faster R-CNN with dilated convolution | |
| CN102208101A (en) | Self-adaptive linearity transformation enhancing method of infrared image | |
| CN106981052B (en) | Adaptive uneven brightness variation correction method based on variation frame | |
| Yu et al. | Image and video dehazing using view-based cluster segmentation | |
| CN103489168A (en) | Enhancing method and system for infrared image being converted to pseudo color image in self-adaptive mode | |
| CN113450272A (en) | Image enhancement method based on sinusoidal curve change and application thereof | |
| Hu et al. | Maritime video defogging based on spatial-temporal information fusion and an improved dark channel prior | |
| CN110706180B (en) | Method, system, equipment and medium for improving visual quality of extremely dark image | |
| CN108198163A (en) | A kind of PAN and multi-spectral image interfusion method based on discrete cosine transform | |
| Xi et al. | Enhancement of unmanned aerial vehicle image with shadow removal based on optimized retinex algorithm | |
| CN110807748A (en) | New tone mapping image enhancement method based on high dynamic range | |
| CN114359083B (en) | High-dynamic thermal infrared image self-adaptive preprocessing method for interference environment | |
| CN115937302A (en) | Hyperspectral image sub-pixel positioning method combined with edge preservation | |
| CN117974502B (en) | Color correction and naturalness recovery method for multiple images with uneven brightness | |
| Ozturk et al. | A Hybrid Method for Enhancement of Both Contrast Distorted and Low-Light Images |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181123 |