CN112927158A - Image restoration method of blurred image, storage medium and terminal - Google Patents
Image restoration method of blurred image, storage medium and terminal Download PDFInfo
- Publication number
- CN112927158A CN112927158A CN202110253900.7A CN202110253900A CN112927158A CN 112927158 A CN112927158 A CN 112927158A CN 202110253900 A CN202110253900 A CN 202110253900A CN 112927158 A CN112927158 A CN 112927158A
- Authority
- CN
- China
- Prior art keywords
- image
- decomposition
- decomposed
- blurred
- initial point
- 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
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 68
- 238000005311 autocorrelation function Methods 0.000 claims abstract description 10
- 230000009466 transformation Effects 0.000 claims abstract description 6
- 238000009792 diffusion process Methods 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 26
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 3
- 230000003321 amplification Effects 0.000 abstract description 6
- 238000003199 nucleic acid amplification method Methods 0.000 abstract description 6
- 238000001914 filtration Methods 0.000 description 5
- 230000015556 catabolic process Effects 0.000 description 4
- 238000006731 degradation reaction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012634 optical imaging Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an image restoration method of a blurred image, a storage medium and a terminal, belonging to the technical field of image restoration, wherein the method comprises the following steps: performing wavelet decomposition on an image to be restored to obtain a multi-band decomposition image; calculating the autocorrelation function of each frequency band decomposition image so as to obtain the initial point spread function of the decomposition image; performing R-L iterative processing on the decomposed image according to the initial point diffusion function; and performing wavelet inverse transformation on the decomposed image subjected to the R-L iterative processing to realize image restoration processing. According to the method, wavelet decomposition is utilized to separate frequency band components in the image to be restored, R-L iterative processing is carried out on the decomposed image based on the point spread function of each decomposed image, the image noise amplification phenomenon can be effectively reduced, image detail information is well stored, the precision of a deconvolution algorithm is improved, and then the clear restored image is obtained.
Description
Technical Field
The present invention relates to the field of image restoration technologies, and in particular, to an image restoration method for a blurred image, a storage medium, and a terminal.
Background
At present, human beings have entered the information age, the information acquisition capability is an important embodiment of national comprehensive strength, the image is a substance reproduction of the information which is perceived by people to be visual, and the image can be recorded and stored on paper media, films and other media which are sensitive to light signals. In the imaging process of a large-field camera, there are many reasons for image blurring, including image motion, defocusing of an imaging system, atmospheric turbulence and the like, which all cause image quality degradation, and cause image detail blurring and unclear features. While the goal of a large field of view camera is to acquire a high quality continuous seamless wide coverage image, so the acquired image needs to be restored. Firstly, the quality degradation phenomenon of each channel image is restored to improve the definition, then, each channel image is spliced continuously and seamlessly, and finally, a high-quality continuous seamless wide-coverage image covering the whole view field is obtained.
The image restoration is very important in the field of image processing, and the restoration process is to construct a corresponding restoration model according to the image blurring factors, so that a corresponding image restoration algorithm is adopted to restore the blurred image, the definition of the image is improved, and the visual effect of the image is improved. As known from PSF (point spread function), blurred image restoration is divided into blind restoration and non-blind restoration, and blind restoration mainly has more estimation processes of PSF than non-blind restoration. The image restoration is a process of solving an original image approximate value of a degraded image by using the prior knowledge of an optical imaging system in the imaging process. The image degradation is caused by a plurality of reasons, and a plurality of effective restoration algorithms such as classical wiener filtering, Richardson-Lucy (R-L) algorithm based on Bayesian theorem and wavelet domain restoration algorithm are proposed for different degradation situations. When noise exists, the restoration effect of the classical inverse filtering method is not ideal, and the wiener filtering method overcomes the defects of the inverse filtering method to some extent, but needs the prior knowledge about the image; R-L is a classic algorithm in an iterative algorithm for image restoration, and although the algorithm has a good restoration effect, a noise amplification phenomenon occurs when the noise of an image is increased.
Disclosure of Invention
The invention aims to overcome the problem of noise amplification when noise is increased in the prior art of image restoration, and provides an image restoration method, a storage medium and a terminal for a blurred image.
The purpose of the invention is realized by the following technical scheme: an image restoration method of a blurred image, the method comprising the steps of:
performing wavelet decomposition on an image to be restored to obtain a multi-band decomposition image;
calculating the autocorrelation function of each frequency band decomposition image so as to obtain the initial point spread function of the decomposition image;
performing R-L iterative processing on the decomposed image according to the initial point diffusion function;
and performing wavelet inverse transformation on the decomposed image subjected to the R-L iterative processing to realize image restoration processing.
As an option, the performing wavelet decomposition on the image to be restored is specifically performing dual-tree complex wavelet decomposition twice on the image to be restored.
As an option, the calculation formula of the autocorrelation function R of each frequency band decomposition image is:
R＝g(x,y)*g(x,y)
wherein g (x, y) is the decomposition image of each frequency band, and represents complex conjugate.
As an option, the initial point spread function h of the decomposed image0The calculation formula of (2) is as follows:
h0＝R-min(R)+ε[max(R)-min(R)]
where ε represents the percentage of dynamic change of the autocorrelation function R.
As an option, the R-L iterative processing on the decomposed image according to the initial point spread function further includes: and determining the corresponding R-L iteration times according to the size and the frequency band of each decomposition image.
As an option, the number of R-L iterations for each of the decomposed images follows: the R-L iteration times of the large-size image are less than the R-L iteration times of the high-frequency decomposition image and less than the R-L iteration times of the low-frequency decomposition image.
As an option, the R-L iteration number of the large-size image is greater than or equal to 10.
As an option, the calculation formula for performing R-L iterative processing on the decomposed image according to the initial point spread function is:
where n is the number of iterations, h (x, y) is the point spread function, h0F (x, y) is the decomposition image that completes the R-L iteration process for the initial point spread function.
It should be further noted that the technical features corresponding to the above-mentioned method options can be combined with each other or replaced to form a new technical solution.
The present invention also includes a storage medium having stored thereon computer instructions which, when executed, perform the steps of a method for image restoration of a blurred image as described above.
The invention also includes a terminal comprising a memory and a processor, wherein the memory stores computer instructions capable of running on the processor, and the processor executes the computer instructions to execute the steps of the image restoration method for blurred images.
Compared with the prior art, the invention has the beneficial effects that:
(1) according to the method, wavelet decomposition is utilized to separate frequency band components in the image to be restored, R-L iterative processing is carried out on the decomposed image based on the point spread function of each decomposed image, the image noise amplification phenomenon can be effectively reduced, image detail information is well stored, the precision of a deconvolution algorithm is improved, and then the clear restored image is obtained.
(2) The method carries out double-tree complex wavelet decomposition twice on the image to be restored, and the decomposed image has time-frequency local analysis characteristics, approximate translation invariance and multi-direction selectivity, can better retain image details and avoids the Gibuss phenomenon.
(3) The invention determines the corresponding R-L iteration times according to the size and the frequency band of each decomposition image, and the R-L iteration times of each decomposition image follow that: the R-L iteration number of the size image is less than that of the high-frequency decomposition image and less than that of the low-frequency decomposition image, so that the problem of noise amplification of each frequency band can be effectively solved, and the calculation amount is reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention.
FIG. 1 is a flowchart of a method of example 1 of the present invention;
FIG. 2 is a flowchart of a method according to an embodiment of the present invention;
fig. 3 is a schematic diagram of performing dual-tree complex wavelet decomposition on a two-dimensional image according to embodiment 1 of the present invention;
fig. 4 is a schematic diagram of performing a 2-time dual-tree complex wavelet decomposition on a two-dimensional image according to embodiment 1 of the present invention;
fig. 5 is a schematic diagram of performing a 2-time dual-tree complex wavelet decomposition on a two-dimensional image in embodiment 1 of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that directions or positional relationships indicated by "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", and the like are directions or positional relationships based on the drawings, and are only for convenience of description and simplification of description, and do not indicate or imply that the device or element referred to must have a specific orientation, be configured and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly stated or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Example 1
As shown in fig. 1-2, in embodiment 1, an image restoration method for a blurred image specifically includes the following steps:
s11: performing wavelet decomposition on an image to be restored to obtain a multi-band decomposition image;
s12: calculating the autocorrelation function of each frequency band decomposition image so as to obtain the initial point spread function of the decomposition image;
s13: performing R-L iterative processing on the decomposed image according to the initial point diffusion function;
s14: and performing wavelet inverse transformation on the decomposed image subjected to the R-L iterative processing to realize image restoration processing.
The invention separates each frequency band component in the image (blurred image) to be restored by utilizing wavelet decomposition, and performs R-L iterative processing on the decomposed image based on the point spread function of each decomposed image, thereby effectively reducing the image noise amplification phenomenon, better storing the image detail information, improving the precision of the deconvolution algorithm and further obtaining a clear restored image.
Further, performing wavelet decomposition on the image to be restored specifically includes performing dual-tree complex wavelet decomposition twice on the image to be restored. Specifically, the highest decomposition level of the dual-tree complex wavelet decomposition of the image to be restored is M, where M is less than or equal to 10, in this embodiment, M is 2, and after the image to be restored is decomposed twice, a plurality of high-band decomposition images and a plurality of low-band decomposition images are obtained.
More specifically, in this embodiment, the blurred image is denoted as an image I, and the size of the image I is m × n, and after the first dual-tree complex wavelet transform (decomposition) is performed on the image I, the image I is filtered and down-sampled to obtain a size of m × n
Real part of the imagexxAnd virtual part to solve image I'xxPerforming a second dual-tree complex wavelet decomposition on the image I based on the first dual-tree complex wavelet decomposition, i.e. filtering and downsampling to obtain the image with the size of
Real part of the imagexxxAnd virtual part to solve image I'xxxAs shown in FIGS. 3-4, h in FIG. 30、h1Conjugate quadrature filter pair, g, for tree A0、g1For the conjugate quadrature filter pair of tree B, x represents downsampling. Filter pair h0、h1Corresponding real number scale function phih(t) and wavelet functions
Comprises the following steps:
filter pair g0、g1Corresponding real number scale function phig(t) and wavelet functions
Comprises the following steps:
in this example, in FIG. 4, I01、I10、I11High-frequency detail images I 'in the directions of +/-15 degrees, +/-45 degrees and +/-75 degrees of the tree A part after the primary double-tree complex wavelet transform of the original image I is finished respectively'01、I'10、I'11High-frequency detail images in the directions of +/-15 degrees, +/-45 degrees and +/-75 degrees of a tree B part after primary double-tree complex wavelet transformation is completed on the original image I respectively01、I10、I11And l'01、I'10、I'11The image sizes of the decomposed images are all
I001、I010、I011Respectively carrying out first dual-tree complex wavelet transform on the original image I and then carrying out low-frequency image I00And high-frequency detail images I 'in the directions of +/-15 degrees, +/-45 degrees and +/-75 degrees are obtained after the double-tree complex wavelet decomposition is carried out again'001、I'010、I'011Respectively carrying out first double-tree complex wavelet transform on the original image I and then carrying out low-frequency image I'00Performing double-tree complex wavelet decomposition again to obtain high-frequency detail images I in the directions of +/-15 degrees, +/-45 degrees and +/-75 degrees001、I010、I011And l'001、I'010、I'011The image sizes of the decomposed images are all
And l'000、I000The image size is low-frequency information obtained after 2 times of dual-tree complex wavelet decomposition
The method carries out double-tree complex wavelet decomposition twice on the image to be restored, and the decomposed image has time-frequency local analysis characteristics, approximate translation invariance and multi-direction selectivity, can better retain image details and avoids the Gibuss phenomenon.
Further, the formula for calculating the autocorrelation function R of each band decomposition image in step S12 is as follows:
R＝g(x,y)*g(x,y)
wherein g (x, y) is the decomposed image of each frequency band, x represents the complex conjugate, and x, y represent the pixel coordinates of the image respectively.
Further, an initial Point Spread Function (PSF) h of the decomposed image0The calculation formula of (2) is as follows:
h0＝R-min(R)+ε[max(R)-min(R)]
wherein epsilon represents the percentage of dynamic change of the autocorrelation function R, and is generally a small non-negative integer, where the value is 0.01.
Further, performing R-L iterative processing on the decomposed image according to the initial point spread function further includes:
and determining the corresponding R-L iteration times according to the size and the frequency band of each decomposition image. According to the method and the device, the corresponding R-L iteration times are determined according to the size and the frequency band of the decomposition image, and the noise in each decomposition image can be removed to the maximum extent according to the characteristics of each decomposition image.
Further, the number of R-L iterations for each decomposed image follows:
the R-L iteration times of the large-size image are less than the R-L iteration times of the high-frequency decomposition image and less than the R-L iteration times of the low-frequency decomposition image, namely, the R-L algorithm is used for iterating the high-frequency detail part for a few times, the R-L algorithm is used for iterating the low-frequency image part for a plurality of times, and less R-L algorithm is used for iterating the large-size image.
In this example, I000Has a size of
Low-frequency image of (1)001、I010、I011And l'001、I'010、I'011Is of a size of
High frequency detail image of，I01、I10、I11And l'01、I'01、I'11Is of a size of
As shown in fig. 3 and 5, the image I is decomposed01、I10、I11、I'01、I'01、I'11Is set to be N, I is decomposed001、I010、I011And l'001、I'010、I'011With an iteration number of 2N, decompose the image I000The number of iterations of (3N). Further, the R-L iteration number of the large-size image is more than or equal to 10 (iteration number (I) of the large-size high-frequency decomposition image01) < number of iterations of small-sized high-frequency decomposition image (I)001) < number of iterations of a small-sized low-frequency decomposed image (I)000) In this embodiment, the image I is decomposed01、I10、I11、I'01、I'01、I'11Is set to 10, the decomposition I is carried out001、I010、I011And l'001、I'010、I'011Is 20, the image I is decomposed000Is 30.
Further, the calculation formula for performing R-L iterative processing on the decomposed image according to the initial point spread function is:
where n is the number of iterations, h (x, y) is the point spread function, h0F (x, y) is the restored image for the initial point spread function.
And finally, performing dual-tree complex wavelet inverse transformation on the decomposed image f (x, y) subjected to the R-L iterative processing, namely performing the inverse operation of the graph 3, so as to obtain a clear restored image M.
Example 2
The present embodiment provides a storage medium having the same inventive concept as embodiment 1, and having stored thereon computer instructions which, when executed, perform the steps of the image restoration method for a blurred image in embodiment 1.
Based on such understanding, the technical solution of the present embodiment or parts of the technical solution may be essentially implemented in the form of a software product, which is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Example 3
The present embodiment also provides a terminal, which has the same inventive concept as that of embodiment 1, and includes a memory and a processor, wherein the memory stores computer instructions executable on the processor, and the processor executes the computer instructions to perform the steps of the image restoration method for blurred images in embodiment 1. The processor may be a single or multi-core central processing unit or a specific integrated circuit, or one or more integrated circuits configured to implement the present invention.
Each functional unit in the embodiments provided by the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The above detailed description is for the purpose of describing the invention in detail, and it should not be construed that the detailed description is limited to the description, and it will be apparent to those skilled in the art that various modifications and substitutions can be made without departing from the spirit of the invention.
Claims (10)
1. An image restoration method for a blurred image, characterized by: the method comprises the following steps:
performing wavelet decomposition on an image to be restored to obtain a multi-band decomposition image;
calculating the autocorrelation function of each frequency band decomposition image so as to obtain the initial point spread function of the decomposition image;
performing R-L iterative processing on the decomposed image according to the initial point diffusion function;
and performing wavelet inverse transformation on the decomposed image subjected to the R-L iterative processing to realize image restoration processing.
2. The image restoration method for blurred images according to claim 1, wherein: the performing wavelet decomposition on the image to be restored specifically includes performing double-tree complex wavelet decomposition twice on the image to be restored.
3. The image restoration method for blurred images according to claim 1, wherein: the calculation formula of the autocorrelation function R of each frequency band decomposition image is as follows:
R＝g(x,y)*g(x,y)
wherein g (x, y) is the decomposition image of each frequency band, and represents complex conjugate.
4. The image restoration method for a blurred image according to claim 3, wherein: initial point spread function h of the decomposed image0The calculation formula of (2) is as follows:
h0＝R-min(R)+ε[max(R)-min(R)]
where ε represents the percentage of dynamic change of the autocorrelation function R.
5. The image restoration method for blurred images according to claim 2, wherein: the R-L iterative processing of the decomposed image according to the initial point spread function further includes:
and determining the corresponding R-L iteration times according to the size and the frequency band of each decomposition image.
6. The image restoration method for blurred images according to claim 5, wherein: the R-L iteration number of each decomposition image follows:
the R-L iteration times of the large-size image are less than the R-L iteration times of the high-frequency decomposition image and less than the R-L iteration times of the low-frequency decomposition image.
7. The image restoration method for blurred images according to claim 6, wherein: and the R-L iteration number of the large-size image is more than or equal to 10.
8. The image restoration method for a blurred image according to claim 3, wherein: the calculation formula for performing R-L iterative processing on the decomposition image according to the initial point diffusion function is as follows:
where n is the number of iterations, h (x, y) is the point spread function, h0F (x, y) is the decomposition image that completes the R-L iteration process for the initial point spread function.
9. A storage medium having stored thereon computer instructions, characterized in that: the computer instructions when executed perform the steps of a method for image restoration of a blurred image according to any of claims 1 to 8.
10. A terminal comprising a memory and a processor, the memory having stored thereon computer instructions executable on the processor, the terminal comprising: the processor, when executing the computer instructions, performs the steps of a method for image restoration of a blurred image according to any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110253900.7A CN112927158A (en) | 2021-03-09 | 2021-03-09 | Image restoration method of blurred image, storage medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110253900.7A CN112927158A (en) | 2021-03-09 | 2021-03-09 | Image restoration method of blurred image, storage medium and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112927158A true CN112927158A (en) | 2021-06-08 |
Family
ID=76172032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110253900.7A Pending CN112927158A (en) | 2021-03-09 | 2021-03-09 | Image restoration method of blurred image, storage medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112927158A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101930601A (en) * | 2010-09-01 | 2010-12-29 | 浙江大学 | Edge information-based multi-scale blurred image blind restoration method |
| US20180373010A1 (en) * | 2016-03-14 | 2018-12-27 | Olympus Corporation | Point-spread-function measurement device and measurement method, image acquisition apparatus, and image acquisition method |
| CN110415193A (en) * | 2019-08-02 | 2019-11-05 | 平顶山学院 | The restored method of coal mine low-light (level) blurred picture |
| CN111476722A (en) * | 2020-03-12 | 2020-07-31 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | Image restoration method and device based on point spread function and related equipment thereof |
-
2021
- 2021-03-09 CN CN202110253900.7A patent/CN112927158A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101930601A (en) * | 2010-09-01 | 2010-12-29 | 浙江大学 | Edge information-based multi-scale blurred image blind restoration method |
| US20180373010A1 (en) * | 2016-03-14 | 2018-12-27 | Olympus Corporation | Point-spread-function measurement device and measurement method, image acquisition apparatus, and image acquisition method |
| CN110415193A (en) * | 2019-08-02 | 2019-11-05 | 平顶山学院 | The restored method of coal mine low-light (level) blurred picture |
| CN111476722A (en) * | 2020-03-12 | 2020-07-31 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | Image restoration method and device based on point spread function and related equipment thereof |
Non-Patent Citations (4)
| Title |
|---|
| ZEWEI DUAN 等: "A Modified Method On The Point Spread Function Of Motion Blur Image", 《4TH INTERNATIONAL CONFERENCE ON MECHATRONICS, MATERIALS, CHEMISTRY AND COMPUTER ENGINEERING (ICMMCCE 2015》 * |
| 张建国 等: "Richardson-Lucy算法在模糊图像复原中的改进", 《计量学报》 * |
| 徐晓睿: "基于小波变换的湍流退化图像复原技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 曾明: "自适应光学系统中图像复原技术及应用", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kang et al. | Learning-based joint super-resolution and deblocking for a highly compressed image | |
| Naimi et al. | Medical image denoising using dual tree complex thresholding wavelet transform and Wiener filter | |
| Knaus et al. | Dual-domain image denoising | |
| EP2662825B1 (en) | Method and device for generating a super-resolution version of a low resolution input data structure | |
| US9965832B2 (en) | Method for performing super-resolution on single images and apparatus for performing super-resolution on single images | |
| JP5348145B2 (en) | Image processing apparatus and image processing program | |
| Zheng et al. | Wavelet based nonlocal-means super-resolution for video sequences | |
| Hill et al. | The undecimated dual tree complex wavelet transform and its application to bivariate image denoising using a cauchy model | |
| CN110211084B (en) | Image multi-resolution reconstruction method based on weight wavelet transform | |
| CN112163994B (en) | Multi-scale medical image fusion method based on convolutional neural network | |
| KR102195047B1 (en) | Method and apparatus for enhancing quality of 3D image | |
| Witwit et al. | Global motion based video super-resolution reconstruction using discrete wavelet transform | |
| Xu et al. | Wavelet domain compounding for speckle reduction in optical coherence tomography | |
| CN111192204A (en) | Image enhancement method, system and computer readable storage medium | |
| CN110599406B (en) | Image enhancement method and device | |
| CN112927158A (en) | Image restoration method of blurred image, storage medium and terminal | |
| KR101180884B1 (en) | Apparatus and method for real-time image restoration by Vaguelette-Wavelet decomposition | |
| Li et al. | Regularization with multilevel non-stationary tight framelets for image restoration | |
| Tayade et al. | Medical image denoising and enhancement using DTCWT and Wiener filter | |
| Gan et al. | Adaptive joint nonlocal means denoising back projection for image super resolution | |
| Tun et al. | Joint Training of Noisy Image Patch and Impulse Response of Low-Pass Filter in CNN for Image Denoising | |
| Tajima et al. | Chromatic interpolation based on anisotropy-scale-mixture statistics | |
| KR101650897B1 (en) | Window size zooming method and the apparatus for lower resolution contents | |
| Acharya et al. | Efficient fuzzy composite predictive scheme for effectual 2-D up-sampling of images for multimedia applications | |
| Meng et al. | A pseudo cross bilateral filter for image denoising based on laplacian pyramid |
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 |