CN102800076A - Image super-resolution reconstruction method based on double-dictionary learning - Google Patents
Image super-resolution reconstruction method based on double-dictionary learning Download PDFInfo
- Publication number
- CN102800076A CN102800076A CN2012102455303A CN201210245530A CN102800076A CN 102800076 A CN102800076 A CN 102800076A CN 2012102455303 A CN2012102455303 A CN 2012102455303A CN 201210245530 A CN201210245530 A CN 201210245530A CN 102800076 A CN102800076 A CN 102800076A
- Authority
- CN
- China
- Prior art keywords
- mrow
- resolution
- low
- image
- msub
- 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 39
- 239000011159 matrix material Substances 0.000 claims abstract description 43
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims description 23
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 101000755816 Homo sapiens Inactive rhomboid protein 1 Proteins 0.000 claims description 5
- 102100022420 Inactive rhomboid protein 1 Human genes 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 2
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 230000009977 dual effect Effects 0.000 claims 3
- 238000002474 experimental method Methods 0.000 description 11
- 238000004088 simulation Methods 0.000 description 8
- 238000011160 research Methods 0.000 description 3
- 230000000903 blocking effect Effects 0.000 description 2
- 238000012733 comparative method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 101001050487 Homo sapiens IST1 homolog Proteins 0.000 description 1
- 102100023423 IST1 homolog Human genes 0.000 description 1
- 101100192157 Mus musculus Psen2 gene Proteins 0.000 description 1
- 101150011873 Pdcd6 gene Proteins 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an image super-resolution reconstruction method based on double-dictionary learning, which mainly solves the problem that detailed information cannot be effectively supplemented in the prior art when super-resolution reconstruction is performed on a low-resolution image. A realization process comprises the following steps of: firstly, inputting a low-resolution image XL to be processed, constructing five pairs of high-resolution dictionaries and low-resolution dictionaries (Dh1, Dl1), (Dh2, Dl2),..., (Dh5, Dl5), and reconstructing five high-resolution estimation images under the five pairs of dictionaries; constructing one pair of high-frequency dictionary and low-resolution dictionary Df={Dhf, Dlf} by virtue of the high-frequency information and low-frequency information of the input low-resolution image, and reconstructing five pairs of high-resolution estimation images with different neighbor parameters; and finally, performing low-rank decomposition on the ten pairs of reconstructed high-resolution estimation images, and solving a mean value of a low-rank matrix obtained from the decomposition to obtain a final reconstructed high-resolution image XH. The method provided by the invention can be used for obtaining the high-resolution image with clear edges and rich details when being used for performing the super-resolution reconstruction on the low-resolution image and is suitable for super-resolution reconstruction on various natural images.
Description
Technical Field
The invention belongs to the technical field of image processing, in particular to a super-resolution reconstruction method for a low-resolution image.
Background
The super-resolution reconstruction of the image refers to reconstructing a clear high-resolution image according to a corresponding algorithm by using one or more low-resolution images, is an important and challenging research content in image processing, and is widely applied to the aspects of video monitoring, high-definition television imaging and the like. At present, a great deal of research work is carried out at home and abroad aiming at the super-resolution reconstruction of images, and a plurality of classical algorithms are provided.
The traditional image super-resolution reconstruction method comprises bilinear interpolation, bicubic interpolation, iterative back projection, convex set projection method and the like. The methods have small calculated amount and simple principle, and are widely applied to image super-resolution reconstruction, but the traditional methods can generate artificial traces such as ringing, blocking effect and the like in the super-resolution reconstruction process, and the quality of the reconstructed image is seriously reduced under the condition of high magnification factor.
Aiming at the problems that the traditional image super-resolution reconstruction method has poor effect and cannot be well realized in practical application, some super-resolution reconstruction algorithms for improving the defects are proposed internationally at present. For example, Hong Chang et al propose a neighborhood embedding based Super-resolution reconstruction algorithm, see document "Super-resolution through neighbor image embedding". CVPR, 2004. In the algorithm, the high-resolution image and the low-resolution image are assumed to have similar structures, and the weight of the low-resolution space is applied to the high-resolution space to reconstruct the high-resolution image. However, the high-resolution image obtained by the algorithm lacks detail information, and the edge of the image is fuzzy; later, Yang et al propose a sparse representation dictionary learning-based algorithm, see more specifically document "Super-Resolution Via sparse representation" IEEE trans. image processing, 2010, vol.19, pp: 2861-2872. the algorithm first obtains a low Resolution dictionary and a high Resolution dictionary through a dictionary learning method, then projects a low Resolution image to be processed under the low Resolution dictionary to obtain a sparse representation coefficient of the low Resolution image, and finally obtains a reconstructed high Resolution image according to the sparse representation coefficient and the high Resolution dictionary obtained by projection. However, the method needs a large number of low-resolution images and high-resolution image blocks to ensure the sufficiency of the detailed information of the prior contour, and has huge calculation amount and long image reconstruction time, which results in low efficiency.
Disclosure of Invention
The invention aims to provide an image super-resolution reconstruction method based on double-dictionary learning, aiming at overcoming the defects of the prior art, so that artificial traces such as ringing and blocking effects can be removed during image super-resolution reconstruction, more image detail information can be recovered, and the quality of a reconstructed image can be improved.
In order to achieve the purpose, the technical scheme of the invention comprises the following steps:
(1) inputting a low-resolution image X to be processedLThe image size is mxn, and the magnification of the image is set to be 2;
(2) low resolution image X to be processedL3 × 3 blocks are divided, 2 pixels are overlapped between adjacent blocks to obtain G low resolution image blocks P to be processedl(i),i=1,...,G;
(3) 5 high-resolution training images and corresponding 5 low-resolution training images are input, and 5 high-resolution dictionaries D are constructed by using the training imagesh1,Dh2,...,Dh5And corresponding 5 low resolution dictionaries Dl1,Dl2,...,Dl5;
(4) In the 1 st pair of high-resolution and low-resolution dictionaries (D)h1,Dl1) Next, a high-resolution estimated image X of 2m × 2n in size is reconstructedH1:
4a) Extracting a low resolution image block P to be processedl(i) Initializing Pl(i) The label of (a) is 1;
4b) calculating the low resolution image block P to be processed by using the following formulal(i) And low resolution dictionary Dl1DIST1(t) of elements:
DIST1(t)=|Pl(i)-Dl1(t)|2,
wherein Dl1(T), T1, 2., T denotes the tth low-resolution dictionary element, T denotes the total number of low-resolution dictionary elements, i.e., T20000 | · linear2Represents an absolute value squaring operation of (-);
4c) recording 5 low-resolution dictionary elements corresponding to the first 5 smallest results in the distance DIST1(t) as Dl1(k) K 1.., 5, by low resolution dictionary Dl1And high resolution dictionary Dh1Corresponding relation between them, finding out high-resolution dictionary Dh1Corresponding 5 high resolution dictionary elements Dh1(k),k=1,...,5;
4d) Calculating 5 low resolution dictionary elements D by using local weight formulal1(k) Reconstructing an image block Pl(i) K ═ 1,.., 5;
4e) the reconstruction coefficient w (k) is compared with the 5 high-resolution dictionary elements D searched in the step 4c)h1(k) Summing to obtain high-resolution image block Ph(i) The calculation formula is as follows:
4f) setting a mark i to i +1, judging whether a condition i > G is met, and if so, obtaining a reconstructed high-resolution estimated image XH1Executing the step (5), otherwise, returning to the stepStep 4 b);
(5) respectively obtaining dictionary pairs (D) by the same method as the step (4)h2,Dl2),(Dh3,Dl3),…,(Dh5,Dl5) High resolution estimate image X ofH2,XH3,XH4,XH5;
(6) Using low-resolution images X to be processedLConstruct a pair of high and low frequency dictionaries Df={Dhf,Dlf};
(7) Let neighbor parameter A equal to 5, in high and low frequency dictionary Df={Dhf,DlfLower reconstruction size of 2m 2n high resolution estimated image XH6:
7a) Low resolution image X to be processed by utilizing imresize function in matlab softwareLPre-amplifying by a magnification factor of 2 to obtain a pre-amplified image XL *The image size is 2m × 2 n;
7b) for pre-amplified image XL *Performing 3 × 3 block division, and overlapping adjacent blocks by 2 pixels to obtain a pre-magnified image block Pl(j)*,j=1,...,S;
7c) Calculating a pre-enlarged image block P using the following formulal(j)*And a low frequency dictionary DlfDIST2(u) of elements:
DIST2(u)=|Pl(j)*-Dlf(u)|2,
wherein Dlf(U), U1, 2., U denotes the U-th low-frequency dictionary element, U denotes the total number of low-frequency dictionary elements, | U · luminance2Represents a squaring operation taking the absolute value of (-) and;
7d) recording A low-frequency dictionary elements corresponding to the first A smallest results in the distance DIST2(u) as Dlf(r), r ═ 1, 2.. a, by low frequency dictionary DlfAnd high resolution dictionary DhfFinding a high-frequency dictionary DhfCorresponding A high-frequency dictionary elements Dhf(r),r=1,...,A;
7e) Calculating A low-frequency dictionary elements D by using local weight formulalf(r) reconstructing a pre-amplified image block Pl(j)*The reconstruction coefficient of (a), (c) (r), r 1., a;
7f) the reconstruction coefficient c (r) and the A high-frequency dictionary elements D searched in the step 7D) are comparedhf(r) summing to obtain reconstructed high frequency image block Ph(j)*:
7g) The obtained high-frequency image block Ph(j)*And pre-magnified image block Pl(j)*Adding to obtain a reconstructed high-resolution image block Xh(j)*;
7h) Setting a mark j as j +1, judging whether a condition j is more than S is met, and if so, obtaining a high-resolution image X amplified by 2 timesH6Executing the step (8), otherwise, returning to the step 7 c);
(8) respectively setting the neighbor parameters in the step (7) as neighbor parameters A-4, A-3, A-2 and A-1 in the step (7), and repeating the step (7) to obtain the high-resolution estimated image XH7,XH8,XH9,XH10;
(9) 10 high-resolution estimated images X to be acquiredH1,XH2,...,XH10All the high-dimensional data X are pulled into columns to form high-dimensional data X, and low-rank decomposition is carried out on the high-dimensional data X by using a low-rank decomposition algorithm to obtain a low-rank matrix L and a sparse matrix S of the X;
(10) restoring each column in the low-rank matrix L into an image form through a reshape function in matlab software to obtain 10 low-rank images L (z), wherein z is 1.
(11) Carrying out mean value processing on 10 low-rank images L (z) according to the following formula to obtain a final clear image XH:
Compared with the prior art, the invention has the following advantages:
according to the invention, the external high-low resolution dictionary 5 and the internal high-low resolution dictionary 1 are utilized to carry out super-resolution reconstruction on the low-resolution image, external detail information is introduced, and the high-frequency information of the image is kept. Simulation experiments show that the method can effectively perform super-resolution reconstruction on the low-resolution image, increase the detail information of the image and improve the definition of the reconstructed image.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a diagram of 5 high resolution training images used in the present invention to build a high resolution dictionary in a simulation experiment;
FIG. 3 is a diagram of 5 low resolution training images used in the invention to build a low resolution dictionary in a simulation experiment;
FIG. 4 is a Lena low resolution test image used in a simulation experiment of the present invention;
FIG. 5 is a Lena high resolution reconstructed image obtained in a simulation experiment according to the present invention;
FIG. 6 is a Lena high-resolution reconstructed image obtained in an experiment based on a neighborhood embedding method in the prior art;
fig. 7 is a Lena high-resolution reconstructed image obtained in an experiment by a conventional sparse representation dictionary learning-based method.
Detailed Description
Referring to fig. 1, the specific implementation steps of the present invention are as follows:
step 1, inputting a low-resolution image X to be processedLAs shown in fig. 4, the image size is m × n, where m is the number of image rows and n is the number of image columns, the magnification is set to 2, and the low resolution image X to be processed is processedL3 × 3 blocks are divided, 2 pixels are overlapped between adjacent blocks to obtain G low resolution image blocks P to be processedl(i),i=1,...,G。
Step 2, inputting 5 high-resolution training images and 5 corresponding low-resolution training images, wherein 5 high-resolution training images are shown in figure 2, 5 low-resolution training images are shown in figure 3, and constructing 5 high-resolution dictionaries D by using the training imagesh1,Dh2,...,Dh5And corresponding 5 low resolution dictionaries Dl1,Dl2,...,Dl5。
2a) For inputDividing the 5 high-resolution training images into 6 × 6 blocks, overlapping 4 pixels between adjacent blocks to obtain Y high-resolution training image blocks HyY is 1,2, 9, Y, wherein Y is 100000 ≦ 30000;
2b) dividing the input 5 low-resolution training images into 3 x 3 blocks, overlapping 2 pixels between adjacent blocks to obtain Y low-resolution training image blocks LyY is 1,2, 9, Y, wherein Y is 100000 ≦ 30000;
2c) from Y high resolution image blocks HyExtract 10 ten thousand high resolution image blocks HqQ 1, 2., 100000, corresponding from Y low resolution training image blocks LyExtract 10 ten thousand low resolution image blocks Lq,q=1,2,...,100000;
2d) 10 ten thousand high resolution image blocks H to be extracted respectivelyqAnd 10 ten thousand low resolution image blocks LqRandomly dividing into 5 groups to obtain 5 high-resolution dictionaries Dh1,Dh2,...,Dh5And corresponding 5 low resolution dictionaries Dl1,Dl2,...,Dl5。
Step 3, in the 1 st pair of high-resolution and low-resolution dictionaries (D)h1,Dl1) High resolution image X with lower reconstruction size of 2m X2 nH1。
3a) Extracting a low resolution image block P to be processedl(i) Initializing Pl(i) The label of (a) is 1;
3b) calculating the low resolution image block P to be processed by using the following formulal(i) And low resolution dictionary Dl1DIST1(t) of elements:
DIST1(t)=|Pl(i)-Dl1(t)|2,
wherein Dl1(T), T1, 2., T denotes the tth low-resolution dictionary element, T denotes the total number of low-resolution dictionary elements, i.e., T20000 | · linear2Represents an absolute value squaring operation of (-);
3c) will be at a distance DThe 5 low resolution dictionary elements corresponding to the smallest first 5 results in IST1(t) are denoted as Dl1(k) K 1.., 5, by low resolution dictionary Dl1And high resolution dictionary Dh1Corresponding relation between them, finding out high-resolution dictionary Dh1Corresponding 5 high resolution dictionary elements Dh1(k),k=1,...,5;
3d) Calculating 5 low resolution dictionary elements D by using local weight formulal1(k) Reconstructing an image block Pl(i) The reconstruction coefficient w (k), k being 1,.., 5, the calculation formula is as follows:
w(k)=((Pl(i)-Dl1(k))T×(Pl(i)-Dl1(k))/Ik)/c,
wherein the normalization factor <math>
<mrow>
<mi>c</mi>
<mo>=</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>5</mn>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>P</mi>
<mi>l</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mi>D</mi>
<mrow>
<mi>l</mi>
<mn>1</mn>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>)</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>×</mo>
<mrow>
<mo>(</mo>
<msub>
<mi>P</mi>
<mi>l</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mi>D</mi>
<mrow>
<mi>l</mi>
<mn>1</mn>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>)</mo>
</mrow>
<mo>/</mo>
<msub>
<mi>I</mi>
<mi>k</mi>
</msub>
<mo>,</mo>
</mrow>
</math> IkIs a full 1 matrix of size 5x1 (.)TThe operation represents a matrix transpose operation;
3e) the reconstruction coefficient w (k) and the 5 high-resolution dictionary elements D searched in the step 3c) are comparedh1(k) Summing to obtain high-resolution image block Ph(i):
3f) Setting a mark i to i +1, judging whether a condition i > G is met, and if so, obtaining a reconstructed high-resolution estimated image XH1And executing the step 4, otherwise, returning to the step 3 b).
Step 4, respectively obtaining dictionary pairs (D) by the same method as the step 3h2,Dl2),(Dh3,Dl3),…,(Dh5,Dl5) High resolution estimate image X ofH2,XH3,XH4,XH5。
Step 5, utilizing the low resolution image X to be processedLConstruct a pair of high and low frequency dictionaries Df={Dhf,Dlf}。
5a) Low resolution image X to be processedLCarrying out Gaussian high-pass filtering processing to obtain a to-be-processed low-resolution image XLHigh frequency component X ofH0And a low frequency component XL0;
5b) For high frequency component X respectivelyH0And a low frequency component XL0Partitioning with size of 3 × 3, overlapping adjacent blocks by 2 pixels to obtain 1 pair of high and low frequency dictionaries Df={Dhf,Dlf}。
Step 6, setting the neighbor parameter A to 5, and setting the neighbor parameter A to be 5 in a high-low frequency dictionary Df={Dhf,DlfLower reconstruction size of 2m 2n high resolution estimated image XH6。
6a) Low resolution image X to be processed by utilizing imresize function in matlab softwareLPre-amplifying by a magnification factor of 2 to obtain a pre-amplified image XL *The image size is 2m × 2 n;
6b) for pre-amplified image XL *Performing 3 × 3 block division, and overlapping adjacent blocks by 2 pixels to obtain a pre-magnified image block Pl(j)*,j=1,...,S;
6c) Calculating the pre-amplified image block P using the following formulal(j)*And a low frequency dictionary DlfDIST2(u) of elements:
DIST2(u)=|Pl(j)*-Dlf(u)|2,
wherein Dlf(U), U1, 2., U denotes the U-th low-frequency dictionary element, U denotes the total number of low-frequency dictionary elements, | U · luminance2Represents a squaring operation taking the absolute value of (-) and;
6d) recording A low-frequency dictionary elements corresponding to the first A smallest results in the distance DIST2(u) as Dlf(r), r ═ 1, 2.. a, by low frequency dictionary DlfAnd high resolution dictionary DhfFinding a high-frequency dictionary DhfCorresponding A high-frequency dictionary elements Dhf(r),r=1,...,A;
6e) Calculating A low-frequency dictionary elements D by using local weight formulalf(r) reconstructing a pre-amplified image block Pl(j)*The local weight calculation formula of (a) is:
c(r)=((Pl(j)*-Dlf(r))T×(Pl(j)*-Dlf(r))/Ir)/h,
wherein the normalization factor <math>
<mrow>
<mi>h</mi>
<mo>=</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>r</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>A</mi>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>P</mi>
<mi>l</mi>
</msub>
<msup>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<mo>*</mo>
</msup>
<mo>-</mo>
<msub>
<mi>D</mi>
<mi>lf</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>r</mi>
<mo>)</mo>
</mrow>
<mo>)</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>×</mo>
<mrow>
<mo>(</mo>
<msub>
<mi>P</mi>
<mi>l</mi>
</msub>
<msup>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<mo>*</mo>
</msup>
<mo>-</mo>
<msub>
<mi>D</mi>
<mi>lf</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>r</mi>
<mo>)</mo>
</mrow>
<mo>)</mo>
</mrow>
<mo>/</mo>
<msub>
<mi>I</mi>
<mi>r</mi>
</msub>
<mo>,</mo>
</mrow>
</math> IrIs a full 1 matrix of size Ax 1(·)TThe operation represents a matrix transpose operation;
6f) the reconstruction coefficient c (r) and the A high-frequency dictionary elements D searched in the step 6D) are comparedhf(r) summing to obtain reconstructed high frequency image block Ph(j)*:
6g) The obtained high-frequency image block Ph(j)*And pre-magnified image block Pl(j)*Adding to obtain a reconstructed high-resolution image block Xh(j)*;
6h) Setting a mark j as j +1, judging whether a condition j is more than S is met, and if so, obtaining a high-resolution image X amplified by 2 timesH6Step 7 is executed, otherwise step 6c) is returned to.
And 7, respectively setting the neighbor parameters A and A in the step 6 to be 4, A to be 3, A to be 2 and A to be 1, and repeating the step 6 to obtain the high-resolution estimated image XH7,XH8,XH9,XH10。
Step 8, obtaining 10 high-resolution reconstruction images XH1,XH2,...,XH10And all the high-dimensional data X are drawn into columns to form high-dimensional data X, and low-rank decomposition is carried out on the high-dimensional data X by using a low-rank decomposition algorithm to obtain a low-rank matrix L and a sparse matrix S of the high-dimensional data X.
The above-mentioned low-rank decomposition of the high-dimensional data X by using the low-rank decomposition algorithm is implemented by the existing low-rank decomposition method, which is proposed in 2009 by Emmanuel candes and Yi Ma et al, see document "Robust Principal Component Analysis" Computing Research reproduction-CORR, vol.
8a) Initializing the iteration time t =0, and the iteration error epsilon is 0.0001;
8b) setting t = t +1, generating a random gaussian matrix M by using a randn function in matlab software, and obtaining 3 intermediate variable matrices according to the following formula:
G1=X×M,G2=XT×G1,G3=X×G2;
8c) computing a low rank matrix L in the t-th iterationtAnd a sparse matrix St:
Lt=G3×(G1 T×G3)-1G2 T,
St=PΩ|X-Lt|,
Wherein (·)TThe operation represents a matrix transpose operation, (-)-1Representing a matrix inversion operation, PΩ(. cndot.) represents taking the maximum first omega values in (. cndot.), wherein omega takes 30000 in the present invention;
8d) judging an iteration termination condition: if it isIf true, the iteration is stopped and the matrix L is appliedtSet as the low rank matrix L, matrix S soughttSetting the sparse matrix S as the sparse matrix, otherwise returning to step 8b),
Step 9, obtaining 10 low-rank images L (z) by using the low-rank matrix L, wherein z is 1,2H。
9a) Restoring each column in the low-rank matrix L into an image by using a reshape function in matlab software to obtain 10 low-rank images L (z), wherein z is 1, 2.
9b) Carrying out mean processing on a low-rank image L (z), wherein z is 1,2, 10 according to the following formula to obtain a final high-resolution reconstructed image XH:
The effects of the present invention can be specifically illustrated by the following experiments:
1. the experimental conditions are as follows: the CPU of the microcomputer used for the experiment is Intel Core2 Duo 2.33GHz, the internal memory is 2GB, and the programming platform is Matlab R2009 a. The images used in the experiment are from a standard image library, and are Lena, House and Girl, which are 256 × 256 respectively.
2. Content of the experiment
The experiment is divided into three experiments:
experiment one: the super-resolution reconstruction is carried out on the low-resolution image by using the method, and the result is shown in figure 5;
experiment two: performing super-resolution reconstruction on the low-resolution image by using the existing neighborhood embedding-based method, wherein the result is shown in fig. 6;
experiment three: the existing sparse representation dictionary learning-based method is used for performing super-resolution reconstruction on the low-resolution image, and the result is shown in fig. 7.
In a simulation experiment, a peak signal-to-noise ratio (PSNR) evaluation index is applied to evaluate the quality of a restoration result, wherein the PSNR is defined as:
wherein f is a clear image, x is a reconstructed image, and M and N are the number of pixel rows and the number of pixel columns of the clear image f.
The invention and the prior field-based embedding method and sparse representation dictionary learning method are used for respectively carrying out super-resolution reconstruction simulation on the images Lena, House and Girl. The reconstructed result graph is evaluated by applying the peak signal-to-noise ratio (PSNR), and the evaluation result is shown in table 1, wherein Alg1 is the method, Alg2 is the method based on the field embedding, and Alg3 is the method based on the sparse representation dictionary learning.
TABLE 1 PSNR values (in dB) obtained in simulation experiments for the present invention and two comparative methods
3. Analysis of Experimental results
As can be seen from FIG. 5, the reconstruction result of Lena obtained by the invention not only effectively supplements high-frequency detail information, makes the image edge clear, but also has better visual effect;
as can be seen from fig. 6, the reconstruction result obtained by the existing domain-based embedding method is too smooth, the detail information is lacking, and the image is blurred;
as can be seen from fig. 7, the image edge obtained by the existing method based on sparse representation dictionary learning has noise and is poor in visual effect;
as can be seen from Table 1, the present invention has higher PSNR values than the other two comparative methods, and can reconstruct a high resolution image more effectively.
Claims (6)
1. An image super-resolution reconstruction method based on double-dictionary learning comprises the following steps:
(1) inputting a low-resolution image X to be processedLThe image size is mxn, and the magnification of the image is set to be 2;
(2) low resolution image X to be processedL3 × 3 blocks are divided, 2 pixels are overlapped between adjacent blocks to obtain G low resolution image blocks P to be processedl(i),i=1,...,G;
(3) Inputting 5 high-resolution training images and corresponding 5 low-resolution trainingImage, constructing 5 high-resolution dictionaries D by using training imageh1,Dh2,...,Dh5And corresponding 5 low resolution dictionaries Dl1,Dl2,...,Dl5;
(4) In the 1 st pair of high-resolution and low-resolution dictionaries (D)h1,Dl1) Next, a high-resolution estimated image X of 2m × 2n in size is reconstructedH1:
4a) Extracting a low resolution image block P to be processedl(i) Initializing Pl(i) The label of (a) is 1;
4b) calculating the low resolution image block P to be processed by using the following formulal(i) And low resolution dictionary Dl1DIST1(t) of elements:
DIST1(t)=|Pl(i)-Dl1(t)|2,
wherein Dl1(T), T1, 2., T denotes the tth low-resolution dictionary element, T denotes the total number of low-resolution dictionary elements, i.e., T20000 | · linear2Represents an absolute value squaring operation of (-);
4c) recording 5 low-resolution dictionary elements corresponding to the first 5 smallest results in the distance DIST1(t) as Dl1(k) K 1.., 5, by low resolution dictionary Dl1And high resolution dictionary Dh1Corresponding relation between them, finding out high-resolution dictionary Dh1Corresponding 5 high resolution dictionary elements Dh1(k),k=1,...,5;
4d) Calculating 5 low resolution dictionary elements D by using local weight formulal1(k) Reconstructing an image block Pl(i) K ═ 1,.., 5;
4e) the reconstruction coefficient w (k) is compared with the 5 high-resolution dictionary elements D searched in the step 4c)h1(k) Summing to obtain high-resolution image block Ph(i) The calculation formula is as follows:
4f) setting a mark i to i +1, judging whether a condition i > G is met, and if so, obtaining a reconstructed high-resolution estimated image XH1Executing the step (5), otherwise, returning to the step 4 b);
(5) respectively obtaining dictionary pairs (D) by the same method as the step (4)h2,Dl2),(Dh3,Dl3),…,(Dh5,Dl5) High resolution estimate image X ofH2,XH3,XH4,XH5;
(6) Using low-resolution images X to be processedLConstruct a pair of high and low frequency dictionaries Df={Dhf,Dlf};
(7) Let neighbor parameter A equal to 5, in high and low frequency dictionary Df={Dhf,DlfLower reconstruction size of 2m 2n high resolution estimated image XH6:
7a) Low resolution image X to be processed by utilizing imresize function in matlab softwareLPre-amplifying by a magnification factor of 2 to obtain a pre-amplified image XL *The image size is 2m × 2 n;
7b) for pre-amplified image XL *Performing 3 × 3 block division, and overlapping adjacent blocks by 2 pixels to obtain a pre-magnified image block Pl(j)*,j=1,...,S;
7c) Calculating a pre-enlarged image block P using the following formulal(j)*And a low frequency dictionary DlfDIST2(u) of elements:
DIST2(u)=|Pl(j)*-Dlf(u)|2,
wherein Dlf(U), U1, 2, said, U representing the U-th low frequency dictionary element,u represents the total number of low-frequency dictionary elements, | · non-woven2Represents a squaring operation taking the absolute value of (-) and;
7d) recording A low-frequency dictionary elements corresponding to the first A smallest results in the distance DIST2(u) as Dlf(r), r ═ 1, 2.. a, by low frequency dictionary DlfAnd high resolution dictionary DhfFinding a high-frequency dictionary DhfCorresponding A high-frequency dictionary elements Dhf(r),r=1,...,A;
7e) Calculating A low-frequency dictionary elements D by using local weight formulalf(r) reconstructing a pre-amplified image block Pl(j)*The reconstruction coefficient of (a), (c) (r), r 1., a;
7f) the reconstruction coefficient c (r) and the A high-frequency dictionary elements D searched in the step 7D) are comparedhf(r) summing to obtain reconstructed high frequency image block Ph(j)*:
7g) The obtained high-frequency image block Ph(j)*And pre-magnified image block Pl(j)*Adding to obtain a reconstructed high-resolution image block Xh(j)*;
7h) Setting a mark j as j +1, judging whether a condition j is more than S is met, and if so, obtaining a high-resolution image X amplified by 2 timesH6Executing the step (8), otherwise, returning to the step 7 c);
(8) respectively setting the neighbor parameters in the step (7)And (4) repeating the step (7) to obtain the high-resolution estimation image X, wherein the neighbor parameters A in the step (7) are 4, A is 3, A is 2 and A is 1H7,XH8,XH9,XH10;
(9) 10 high-resolution estimated images X to be acquiredH1,XH2,...,XH10All the high-dimensional data X are pulled into columns to form high-dimensional data X, and low-rank decomposition is carried out on the high-dimensional data X by using a low-rank decomposition algorithm to obtain a low-rank matrix L and a sparse matrix S of the X;
(10) restoring each column in the low-rank matrix L into an image form through a reshape function in matlab software to obtain 10 low-rank images L (z), wherein z is 1.
(11) Carrying out mean value processing on 10 low-rank images L (z) according to the following formula to obtain a final clear image XH:
2. The image super-resolution reconstruction method based on dual-dictionary learning as claimed in claim 1, wherein said step (3) of constructing 5 high-resolution dictionaries D by using training imagesh1,Dh2,...,Dh5And corresponding 5 low resolution dictionaries Dl1,Dl2,...,Dl5The method comprises the following implementation steps:
3a) dividing the input 5 high-resolution training images into 6 x 6 blocks, overlapping 4 pixels between adjacent blocks to obtain Y high-resolution training image blocks HyY is 1,2, 9, Y, wherein Y is 100000 ≦ 30000;
3b) for 5 input framesThe low resolution training image is divided into 3 multiplied by 3 blocks, and 2 pixels are overlapped between adjacent blocks to obtain Y low resolution training image blocks LyY is 1,2, 9, Y, wherein Y is 100000 ≦ 30000;
3c) from Y high resolution image blocks HyExtract 10 ten thousand high resolution image blocks HqQ 1, 2., 100000, corresponding from Y low resolution training image blocks LyExtract 10 ten thousand low resolution image blocks Lq,q=1,2,...,100000;
3d) 10 ten thousand high resolution image blocks H to be extracted respectivelyqAnd 10 ten thousand low resolution image blocks LqRandomly dividing into 5 groups to obtain 5 high-resolution dictionaries Dh1,Dh2,...,Dh5And corresponding 5 low resolution dictionaries Dl1,Dl2,...,Dl5。
3. The image super-resolution reconstruction method based on dual dictionary learning of claim 1, wherein said step 4D) uses local weight formula to calculate 5 low-resolution dictionary elements Dl1(k) Reconstructing an image block Pl(i) The reconstruction coefficient w (k), k being 1,.., 5, is calculated by the following formula:
w(k)=((Pl(i)-Dl1(k))T×(Pl(i)-Dl1(k))/Ik)/g,
wherein the normalization factor <math>
<mrow>
<mi>g</mi>
<mo>=</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>5</mn>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>P</mi>
<mi>l</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mi>D</mi>
<mrow>
<mi>l</mi>
<mn>1</mn>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>)</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>×</mo>
<mrow>
<mo>(</mo>
<msub>
<mi>P</mi>
<mi>l</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mi>D</mi>
<mrow>
<mi>l</mi>
<mn>1</mn>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>)</mo>
</mrow>
<mo>/</mo>
<msub>
<mi>I</mi>
<mi>k</mi>
</msub>
<mo>,</mo>
</mrow>
</math> IkIs a full 1 matrix of size 5x1 (.)TThe operation represents a matrix transpose operation.
4. The image super-resolution reconstruction method based on dual dictionary learning of claim 1, wherein the step (6) of utilizing the low resolution image X to be processedLConstruct a pair of high and low frequency dictionaries Df={Dhf,DlfThe implementation steps are as follows:
6a) low resolution image X to be processedLCarrying out Gaussian high-pass filtering processing to obtain a to-be-processed low-resolution image XLHigh frequency component X ofH0And a low frequency component XL0;
6b) For high frequency component X respectivelyH0And a low frequency component XL0Partitioning with size of 3 × 3, overlapping adjacent blocks by 2 pixels to obtain 1 pair of high and low frequency dictionaries Df={Dhf,Dlf}。
5. The image super-resolution reconstruction method based on dual dictionary learning of claim 1, wherein the step 7e) of calculating a low frequency dictionary elements D by using local weight formulalf(r) reconstructing a pre-amplified image block Pl(j)*The reconstruction coefficient c (r), r 1, a, is calculated by the following formula:
c(r)=((Pl(j)*-Dlf(r))T×(Pl(j)*-Dlf(r))/Ir)/h,
wherein the normalization factor <math>
<mrow>
<mi>h</mi>
<mo>=</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>r</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>A</mi>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>P</mi>
<mi>l</mi>
</msub>
<msup>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<mo>*</mo>
</msup>
<mo>-</mo>
<msub>
<mi>D</mi>
<mi>lf</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>r</mi>
<mo>)</mo>
</mrow>
<mo>)</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>×</mo>
<mrow>
<mo>(</mo>
<msub>
<mi>P</mi>
<mi>l</mi>
</msub>
<msup>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<mo>*</mo>
</msup>
<mo>-</mo>
<msub>
<mi>D</mi>
<mi>lf</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>r</mi>
<mo>)</mo>
</mrow>
<mo>)</mo>
</mrow>
<mo>/</mo>
<msub>
<mi>I</mi>
<mi>r</mi>
</msub>
<mo>,</mo>
</mrow>
</math> IrIs a full 1 matrix of size Ax 1(·)TThe operation represents a matrix transpose operation.
6. The image super-resolution reconstruction method based on dual-dictionary learning of claim 1, wherein in the step (9), the low-rank decomposition algorithm is used for performing low-rank decomposition on the high-dimensional data X to obtain a low-rank matrix L and a sparse matrix S of X, and the implementation steps are as follows:
9a) initializing the iteration time t =0, and the iteration error epsilon is 0.0001;
9b) setting t = t +1, generating a random gaussian matrix M by using a randn function in matlab software, and obtaining 3 intermediate variable matrices according to the following formula:
G1=X×M,G2=XT×G1,G3=X×G2;
9c) computing a low rank matrix L in the t-th iterationtAnd a sparse matrix St:
Lt=G3×(G1 T×G3)-1G2 T,
St=PΩ|X-Lt|,
Wherein (·)TThe operation represents a matrix transpose operation, (-)-1Representing a matrix inversion operation, PΩ(. cndot.) represents taking the maximum first omega values in (. cndot.), wherein omega takes 30000 in the present invention;
9d) judging an iteration termination condition: if it isIf true, the iteration is stopped and the matrix L is appliedtSet as the low rank matrix L, matrix S soughttSetting the sparse matrix S as the sparse matrix, otherwise returning to step 9b),
wherein,representing the square of the norm of the matrix 2.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210245530.3A CN102800076B (en) | 2012-07-16 | 2012-07-16 | Image super-resolution reconstruction method based on double-dictionary learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210245530.3A CN102800076B (en) | 2012-07-16 | 2012-07-16 | Image super-resolution reconstruction method based on double-dictionary learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102800076A true CN102800076A (en) | 2012-11-28 |
CN102800076B CN102800076B (en) | 2015-03-04 |
Family
ID=47199175
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210245530.3A Active CN102800076B (en) | 2012-07-16 | 2012-07-16 | Image super-resolution reconstruction method based on double-dictionary learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102800076B (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103093430A (en) * | 2013-01-25 | 2013-05-08 | 西安电子科技大学 | Heart magnetic resonance imaging (MRI) image deblurring method based on sparse low rank and dictionary learning |
CN103093444A (en) * | 2013-01-17 | 2013-05-08 | 西安电子科技大学 | Image super-resolution reconstruction method based on self-similarity and structural information constraint |
CN103295197A (en) * | 2013-05-21 | 2013-09-11 | 西安电子科技大学 | Image super-resolution rebuilding method based on dictionary learning and bilateral holomorphy |
CN104123707A (en) * | 2014-08-07 | 2014-10-29 | 重庆大学 | Local rank priori based single-image super-resolution reconstruction method |
CN104794694A (en) * | 2015-04-23 | 2015-07-22 | 中南民族大学 | Image interpolation system and image interpolation method based on adaptive low-rank regularization |
CN105590296A (en) * | 2015-12-07 | 2016-05-18 | 天津大学 | Dual-dictionary learning-based single-frame image super-resolution reconstruction method |
CN105741252A (en) * | 2015-11-17 | 2016-07-06 | 西安电子科技大学 | Sparse representation and dictionary learning-based video image layered reconstruction method |
CN105844589A (en) * | 2016-03-21 | 2016-08-10 | 深圳市未来媒体技术研究院 | Method for realizing light field image super-resolution based on mixed imaging system |
CN106204451A (en) * | 2016-07-08 | 2016-12-07 | 西安电子科技大学 | The Image Super-resolution Reconstruction method embedded based on the fixing neighborhood of constraint |
CN106558020A (en) * | 2015-09-29 | 2017-04-05 | 北京大学 | A kind of image rebuilding method and system based on network image block retrieval |
CN107341765A (en) * | 2017-05-05 | 2017-11-10 | 西安邮电大学 | A kind of image super-resolution rebuilding method decomposed based on cartoon texture |
CN111582048A (en) * | 2020-04-16 | 2020-08-25 | 昆明理工大学 | Undersampled signal high-resolution reconstruction method based on dictionary learning and sparse representation |
CN112819740A (en) * | 2021-02-02 | 2021-05-18 | 南京邮电大学 | Medical image fusion method based on multi-component low-rank dictionary learning |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101950365A (en) * | 2010-08-30 | 2011-01-19 | 西安电子科技大学 | Multi-task super-resolution image reconstruction method based on KSVD dictionary learning |
KR101037023B1 (en) * | 2009-10-05 | 2011-05-25 | 인하대학교 산학협력단 | High resolution interpolation method and apparatus using high frequency synthesis based on clustering |
CN102156875A (en) * | 2011-03-25 | 2011-08-17 | 西安电子科技大学 | Image super-resolution reconstruction method based on multitask KSVD (K singular value decomposition) dictionary learning |
-
2012
- 2012-07-16 CN CN201210245530.3A patent/CN102800076B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101037023B1 (en) * | 2009-10-05 | 2011-05-25 | 인하대학교 산학협력단 | High resolution interpolation method and apparatus using high frequency synthesis based on clustering |
CN101950365A (en) * | 2010-08-30 | 2011-01-19 | 西安电子科技大学 | Multi-task super-resolution image reconstruction method based on KSVD dictionary learning |
CN102156875A (en) * | 2011-03-25 | 2011-08-17 | 西安电子科技大学 | Image super-resolution reconstruction method based on multitask KSVD (K singular value decomposition) dictionary learning |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103093444A (en) * | 2013-01-17 | 2013-05-08 | 西安电子科技大学 | Image super-resolution reconstruction method based on self-similarity and structural information constraint |
CN103093444B (en) * | 2013-01-17 | 2015-05-20 | 西安电子科技大学 | Image super-resolution reconstruction method based on self-similarity and structural information constraint |
CN103093430A (en) * | 2013-01-25 | 2013-05-08 | 西安电子科技大学 | Heart magnetic resonance imaging (MRI) image deblurring method based on sparse low rank and dictionary learning |
CN103093430B (en) * | 2013-01-25 | 2015-07-15 | 西安电子科技大学 | Heart magnetic resonance imaging (MRI) image deblurring method based on sparse low rank and dictionary learning |
CN103295197A (en) * | 2013-05-21 | 2013-09-11 | 西安电子科技大学 | Image super-resolution rebuilding method based on dictionary learning and bilateral holomorphy |
CN103295197B (en) * | 2013-05-21 | 2016-01-20 | 西安电子科技大学 | Based on the image super-resolution rebuilding method of dictionary learning and bilateral canonical |
CN104123707A (en) * | 2014-08-07 | 2014-10-29 | 重庆大学 | Local rank priori based single-image super-resolution reconstruction method |
CN104123707B (en) * | 2014-08-07 | 2017-05-10 | 重庆大学 | Local rank priori based single-image super-resolution reconstruction method |
CN104794694A (en) * | 2015-04-23 | 2015-07-22 | 中南民族大学 | Image interpolation system and image interpolation method based on adaptive low-rank regularization |
CN104794694B (en) * | 2015-04-23 | 2017-08-01 | 中南民族大学 | Image interpolation system and method based on adaptive low-rank regularization |
CN106558020A (en) * | 2015-09-29 | 2017-04-05 | 北京大学 | A kind of image rebuilding method and system based on network image block retrieval |
CN106558020B (en) * | 2015-09-29 | 2019-08-30 | 北京大学 | A kind of image rebuilding method and system based on network image block retrieval |
CN105741252B (en) * | 2015-11-17 | 2018-11-16 | 西安电子科技大学 | Video image grade reconstruction method based on rarefaction representation and dictionary learning |
CN105741252A (en) * | 2015-11-17 | 2016-07-06 | 西安电子科技大学 | Sparse representation and dictionary learning-based video image layered reconstruction method |
CN105590296A (en) * | 2015-12-07 | 2016-05-18 | 天津大学 | Dual-dictionary learning-based single-frame image super-resolution reconstruction method |
CN105590296B (en) * | 2015-12-07 | 2019-01-29 | 天津大学 | A kind of single-frame images Super-Resolution method based on doubledictionary study |
CN105844589B (en) * | 2016-03-21 | 2018-12-21 | 深圳市未来媒体技术研究院 | A method of the realization light field image super-resolution based on hybrid imaging system |
CN105844589A (en) * | 2016-03-21 | 2016-08-10 | 深圳市未来媒体技术研究院 | Method for realizing light field image super-resolution based on mixed imaging system |
CN106204451A (en) * | 2016-07-08 | 2016-12-07 | 西安电子科技大学 | The Image Super-resolution Reconstruction method embedded based on the fixing neighborhood of constraint |
CN106204451B (en) * | 2016-07-08 | 2019-04-23 | 西安电子科技大学 | Based on the Image Super-resolution Reconstruction method for constraining fixed neighborhood insertion |
CN107341765A (en) * | 2017-05-05 | 2017-11-10 | 西安邮电大学 | A kind of image super-resolution rebuilding method decomposed based on cartoon texture |
CN107341765B (en) * | 2017-05-05 | 2020-04-28 | 西安邮电大学 | Image super-resolution reconstruction method based on cartoon texture decomposition |
CN111582048A (en) * | 2020-04-16 | 2020-08-25 | 昆明理工大学 | Undersampled signal high-resolution reconstruction method based on dictionary learning and sparse representation |
CN111582048B (en) * | 2020-04-16 | 2022-09-23 | 昆明理工大学 | Undersampled signal high-resolution reconstruction method based on dictionary learning and sparse representation |
CN112819740A (en) * | 2021-02-02 | 2021-05-18 | 南京邮电大学 | Medical image fusion method based on multi-component low-rank dictionary learning |
CN112819740B (en) * | 2021-02-02 | 2023-05-12 | 南京邮电大学 | Medical image fusion method based on multi-component low-rank dictionary learning |
Also Published As
Publication number | Publication date |
---|---|
CN102800076B (en) | 2015-03-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102800076B (en) | Image super-resolution reconstruction method based on double-dictionary learning | |
CN110119780B (en) | Hyper-spectral image super-resolution reconstruction method based on generation countermeasure network | |
Guo et al. | Deep wavelet prediction for image super-resolution | |
Remez et al. | Deep convolutional denoising of low-light images | |
CN104050653B (en) | Hyperspectral image super-resolution method based on non-negative structure sparse | |
CN103093433B (en) | Natural image denoising method based on regionalism and dictionary learning | |
CN105631807B (en) | The single-frame image super-resolution reconstruction method chosen based on sparse domain | |
CN110060204B (en) | Single image super-resolution method based on reversible network | |
CN103593825B (en) | Based on the non-local constraint of improvement and the image super-resolution method of local self-similarity | |
CN104299193B (en) | Image super-resolution reconstruction method based on high-frequency information and medium-frequency information | |
CN107154064A (en) | Natural image compressed sensing method for reconstructing based on depth sparse coding | |
CN104252703A (en) | Wavelet preprocessing and sparse representation-based satellite remote sensing image super-resolution reconstruction method | |
CN105590296B (en) | A kind of single-frame images Super-Resolution method based on doubledictionary study | |
Zou et al. | Joint wavelet sub-bands guided network for single image super-resolution | |
CN110288529B (en) | Single image super-resolution reconstruction method based on recursive local synthesis network | |
Wu et al. | Lightweight asymmetric convolutional distillation network for single image super-resolution | |
Li | Image super-resolution using attention based densenet with residual deconvolution | |
CN114549300A (en) | Image dictionary generation method, image reconstruction method and related device | |
CN106296583A (en) | Based on image block group sparse coding and the noisy high spectrum image ultra-resolution ratio reconstructing method mapped in pairs | |
Wang et al. | Lightweight image denoising network with four-channel interaction transform | |
CN103903239A (en) | Video super-resolution reconstruction method and system based on sparse principal component analysis and continued fraction interpolation technology | |
CN102156967B (en) | Multiscale-based local image interpolation method | |
CN113077403B (en) | Color image reconstruction method based on local data block tensor enhancement technology | |
Tang et al. | Image denoising using K-SVD and non-local means | |
Mehri et al. | SRFormer: Efficient yet powerful transformer network for single image super resolution |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |