CN101950365A - Multi-task super-resolution image reconstruction method based on KSVD dictionary learning - Google Patents
Multi-task super-resolution image reconstruction method based on KSVD dictionary learning Download PDFInfo
- Publication number
- CN101950365A CN101950365A CN 201010267446 CN201010267446A CN101950365A CN 101950365 A CN101950365 A CN 101950365A CN 201010267446 CN201010267446 CN 201010267446 CN 201010267446 A CN201010267446 A CN 201010267446A CN 101950365 A CN101950365 A CN 101950365A
- Authority
- CN
- China
- Prior art keywords
- dictionary
- image
- matrix
- initial
- resolution image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention discloses a multi-task super-resolution image reconstruction method based on KSVD dictionary learning, which mainly solves the problem of relatively serious quality reduction of the reconstructed image under high amplification factors in the existing method. The method mainly comprises the following steps: firstly, inputting a training image, and filtering the training image to extract features; extracting image blocks to construct a matrix M, and dividing the matrix M into K classes to acquire K pairs of initial dictionaries H1, H2...Hk and L1, L2...Lk; then, training the K pairs of initial dictionaries H1, H2...Hk and L1, L2...Lk into K pairs of new dictionaries Dh1, Dh2...Dhk and Dl1, Dl2...Dlk by utilizing a KSVD method; and finally, carrying out super-resolution reconstruction on the input low-resolution image by utilizing a multi-task algorithm and the dictionaries Dh1, Dh2...Dhk and Dl1, Dl2...Dlk to acquire a final reconstructed image. The invention can reconstruct various natural images containing non-texture images such as animals, plants, people and the like and images with stronger texture features such as buildings and the like, and can effectively improve the quality of the reconstructed image under high amplification factors.
Description
Technical field
The invention belongs to technical field of image processing, the ultra-resolution ratio reconstructing method that relates to a kind of image, promptly by the relational model between study low-resolution image and the high-definition picture, predict the high-definition picture that it is corresponding from the low-resolution image of single width input, can be used for the super-resolution reconstruction of all kinds of natural images.
Background technology
Super-resolution image reconstruction can be regarded an inverse problem that recovers high-definition picture from the one or more low-resolution image as.In order to address this problem, some traditional methods based on model are suggested: such as MAP (maximum a-posteriori) method, the maximum likelihood estimation technique, convex set sciagraphy (POCS) etc.But these traditional methods can produce level and smooth phenomenon and sawtooth effect, and the quality suppression ratio of reconstructed image is more serious under high amplification factor condition.Therefore, Freeman etc. have proposed a kind of reconstructing method based on study, it mainly is to learn relation between low-resolution image and the high-definition picture by Markov probabilistic model and priori, reconstructs its corresponding high-definition picture from a width of cloth low-resolution image.People such as Sun then expand this method, it mainly is by using some original profile prioris to remove the level and smooth phenomenon of border and details, but this method still needs a large amount of low-resolution images and high-definition picture piece to guarantee the adequacy of priori profile detailed information, calculated amount is huge, the image reconstruction time is long, causes efficient on the low side.These algorithm all is based on the restructing algorithm of single task in addition, compares with multitasked algorithm, can not carry out the information sharing between a plurality of tasks, causes image reconstruction effect deviation.
Summary of the invention
The objective of the invention is to overcome the shortcoming of above-mentioned prior art, propose a kind of multitask super-resolution image reconstruction method,, improve the efficient and the quality of reconstructed image to shorten the image reconstruction time based on the study of KSVD dictionary.
For achieving the above object, technical scheme of the present invention is at first to introduce tens various types of other training images, comprises plant, animal, people and building, and all corresponding width of cloth low-resolution image of each panel height image in different resolution; Utilize the KSVD algorithm that these images are trained to K to dictionary; Utilize the method for multitask reconstruct then, the low-resolution image of importing is reconstituted high-definition picture.Concrete steps comprise:
(1) input training image carries out filtering to it and extracts feature, extracts matrix M of 100,000 pairs of little block structures of image again, is divided into the K class, obtains K to initial dictionary H
1, H
2... H
kAnd L
1, L
2... L
k, and K cluster centre C
1, C
2... C
k
(2) utilize the KSVD algorithm to separate formula:
Subject to
To K to initial dictionary H
1, H
2... H
kAnd L
1, L
2... L
kTrain, obtain K new dictionary D
H1, D
H2... D
HkAnd D
L1, D
L2... D
Lk,
Wherein, Y is the initial dictionary of input, and D is that target is trained dictionary and is initialized as a dictionary at random, and X is the Sparse Decomposition matrix,
Be any i row, || X
i||
0Be X
i0 norm,
For finding the solution 2 norms of Y-DX, T
0Be the degree of rarefication control coefrficient;
(3) input one secondary low-resolution image Q after its filtering extraction feature, appoints a fritter q who gets characteristic image, calculates K the cluster centre C that obtains in q and the step (1) respectively
1, C
2... C
kBetween distance be: d
1, d
2... d
k, to d
1, d
2... d
kGet reciprocal and normalization, obtain K weight w
1, w
2... w
k
(4) utilize dictionary D
L1, D
L2... D
LkWith low-resolution image fritter q, find the solution dictionary D respectively
L1, D
L2... D
LkCorresponding Sparse Decomposition coefficient a
1, a
2... a
k, its solution formula is: q=D
L1A, i=1 wherein, 2....k;
(5) utilize dictionary D
H1, D
H2... D
HkWith coefficient a
1, a
2... a
k, find the solution high-definition picture fritter x respectively
1, x
2... x
k, its solution formula is x
i=D
Hia
i, i=1,2....k;
(6) utilize weight w
1, W
2... w
kTo x
1, x
2... x
kCarry out the weights addition and obtain the high-definition picture fritter:
(7) repeating step (3) is handled all input picture fritters successively to step (6), obtains initial reconstitution image Z, at last initial reconstitution image Z is carried out global optimization, obtains final reconstructed image Z
*
The present invention has the following advantages compared with prior art:
The present invention extracts the various characteristic informations of training image owing to utilize KSVD algorithm training dictionary, thereby has reduced the number of dictionary atom, shortens the image reconstruction time, has improved reconstruct efficient; Simultaneously since the present invention when utilizing multitask learning algorithm reconstructed image, can learn mutually between a plurality of tasks, thereby improved the quality of reconstructed image; Because the present invention can be reconstructed various natural images, comprise plant, animal, people, buildings in addition, thus overcome tradition based on the algorithm of model for the not strong problem of various input picture compatibility.
Experiment showed, that the present invention is applicable to the super-resolution reconstruction of various natural images, after being reconstructed by this algorithm, it is relatively good that the detail textures information of reconstructed image all keeps.
Description of drawings
Fig. 1 is a general flow chart of the present invention;
Fig. 2 is that weights of the present invention calculate sub-process figure;
Fig. 3 is the plant training image that the present invention adopts;
Fig. 4 is the animal training image that the present invention adopts;
Fig. 5 is people's training image that the present invention adopts;
Fig. 6 is the building training image that the present invention adopts;
Fig. 7 is with the reconstruct design sketch of the present invention to test Lena image;
Fig. 8 is with the reconstruct design sketch of the present invention to test Pepper image;
Fig. 9 is with the reconstruct design sketch of the present invention to test b obcat image;
Figure 10 is with the reconstruct design sketch of the present invention to test Athens image;
Figure 11 is the effect contrast figure with the present invention and other the whole bag of tricks reconstructed image.
Specific implementation method
With reference to accompanying drawing 1, concrete steps of the present invention comprise:
Step 1. pair training image carries out pre-service and classification
1a) input training image carries out filtering to it and extracts feature, and the wave filter that is adopted is f
1=[1,0,1],
f
3=[1,0 ,-2,0,1],
The training image that is adopted such as Fig. 3, Fig. 4, Fig. 5 and shown in Figure 6;
1b) randomly draw about 100,000 pairs of image fritters, construct a matrix M, utilize the K-means algorithm that the image fritter in the matrix M is divided into 5 classes, but be not limited to 5 classes, obtain 5 couples of initial dictionary H
1, H
2, H
3, H
4, H
5And L
1, L
2, L
3, L
4, L
5And 5 cluster centre C
1, C
2, C
3, C
4, C
5, but be not limited to 5 pairs of initial dictionaries and 5 cluster centres.
Step 2. utilize the KSVD algorithm to selected to initial dictionary H
1, H
2, H
3, H
4, H
5And L
1, L
2, L
3, L
4, L
5Train
This example is to selected 5 pairs of initial dictionary training, but is not limited to 5 pairs of initial dictionaries, also can be to the initial dictionary training of other number, and training step is as follows:
2a) from the KSVD algorithm, provide total optimization formula
Subject to
Wherein Y represents that the initial dictionary imported, D represent target training dictionary, and X represents the Sparse Decomposition coefficient;
2b) in total optimization formula
Be out of shape and obtain:
Wherein, Y is the initial dictionary of input, and D is target training dictionary and is initialized as a dictionary at random that X is the Sparse Decomposition matrix, d
jBe the j row atom of D,
For the j of X is capable, N is total columns of D, d
kBe the k row atom of D,
For the k of X is capable, E
kFor not using the k row atom d of D
kCarry out the error matrix that the signal Sparse Decomposition is produced;
2c) to the formula after the distortion
Multiply by matrix Ω
k, obtain the target decomposition formula
Wherein
Ω
kSize be P
*| ω
k|, P is the columns of the initial dictionary Y of input,
| ω
k| be ω
kThe mould value, and Ω
kAt (ω
k(j), j) locating is 1, and other place is 0 entirely, wherein 1≤j≤| ω
k|, ω
k(j) be ω
kThe j number;
2d) to the target decomposition formula
In error matrix
Carrying out the SVD decomposition obtains
Wherein U is, V
TBe right singular matrix, Δ is a singular value matrix;
2e) first row with left singular matrix U remove the more k row atom d of fresh target train word allusion quotation D
k
2f) repeating step 2c) to step 2e) all atoms among the D are upgraded processing, obtain 5 couples of new dictionary D
H1, D
H2, D
H3, D
H4, D
H5And D
L1, D
L2, D
L3, D
L4, D
L5
Step 3. is imported low-resolution image and is calculated the weights of each image fritter correspondence
With reference to Fig. 2, being implemented as follows of this step:
3a) input one secondary low-resolution image Q carries out filtering and feature extraction to it, obtains characteristic image, and the wave filter that is adopted is f
1=[1,0,1],
f
3=[1,0 ,-2,0,1],
3b) appoint a fritter q who gets characteristic image, its size is 3*3, calculates 5 cluster centre C that obtain in q and the step (1) respectively
1, C
2, C
3, C
4, C
5Between distance: d
1, d
2, d
3, d
4, d
5, to d
1, d
2, d
3, d
4, d
5Get inverse and obtain 1/d
1, 1/d
2, 1/d
3, 1/d
4, 1/d
5, to 1/d
1, 1/d
2, 1/d
3, 1/d
4, 1/d
5Carry out normalized and obtain 5 weight w
1, w
2, w
3, w
4, w
5
Step 4. multitask image reconstruction
4a) utilize dictionary D
L1, D
L2, D
L3, D
L4, D
L5With low-resolution image fritter q, find the solution dictionary D respectively
L1, D
L2, D
L3, D
L4, D
L5Corresponding Sparse Decomposition coefficient a
1, a
2, a
3, a
4, a
5, its solution formula is: q=D
L1A, i=1 wherein, 2,3,4,5;
4b) utilize dictionary D
H1, D
H2, D
H3, D
H4, D
H5With coefficient a
1, a
2, a
3, a
4, a
5, find the solution high-definition picture fritter x respectively
1, x
2, x
3, x
4, x
5, its solution formula is x
1=D
H1a
1, i=1,2,3,4,5;
4c) utilize weight w
1, w
2, w
3, w
4, w
5To x
1, x
2, x
3, x
4, x
5Carry out the weights addition and obtain the high-definition picture fritter:
4d) repeating step 4a) to step 4c), all input low-resolution image fritters are handled successively, obtain initial reconstitution image Z.
Step 5. couple initial reconstitution image Z carries out global optimization
By following formula initial reconstitution image Z is carried out global optimization, obtains final reconstructed image:
Wherein, Z
0Be original high resolution image, Z
*Be final reconstructed image, DH is following operation, the low-resolution image of Q for importing adopted to initial reconstitution image Z.
Effect of the present invention can further specify by following experiment:
1) experiment condition
This experiment adopts standard testing image Lena, Pepper, Bobcat, Athens, Girl as experimental data, adopts software MATLAB 7.0 as emulation tool, and computer configuration is Intel Core2/1.8G/1G.
2) experiment content
2a) utilize Bicubic interpolation algorithm, MaYi algorithm and algorithm of the present invention respectively, all kinds of input test images be reconstructed:
At first, the Lena image is reconstructed, the result as shown in Figure 7, wherein Fig. 7 (a) be that Bicubic interpolation algorithm result, Fig. 7 (c) are result of the present invention for MaYi arithmetic result, Fig. 7 (d) for input low-resolution image, Fig. 7 (b);
Secondly, the Pepper image is reconstructed, the result as shown in Figure 8, wherein Fig. 8 (a) be that Bicubic interpolation algorithm result, Fig. 8 (c) are result of the present invention for MaYi arithmetic result, Fig. 8 (d) for input low-resolution image, Fig. 8 (b);
Once more, the Bobcat image is reconstructed, the result as shown in Figure 9, wherein Fig. 9 (a) be that Bicubic interpolation algorithm result, Fig. 9 (c) are result of the present invention for MaYi arithmetic result, Fig. 9 (d) for input low-resolution image, Fig. 9 (b);
At last, the Athens image is reconstructed, the result as shown in figure 10, wherein Figure 10 (a) be that Bicubic interpolation algorithm result, Figure 10 (c) are result of the present invention for MaYi arithmetic result, Figure 10 (d) for input low-resolution image, Figure 10 (b).
2b) utilize S.Dai algorithm, MaYi algorithm, single task algorithm and the present invention that test pattern Girl is reconstructed respectively, obtain result as shown in figure 11, wherein Figure 11 (a) is that MaYi arithmetic result, Figure 11 (d) are original high-definition picture for result, Figure 11 (e) of single task algorithm for result of the present invention, Figure 11 (f) for input low-resolution image, Figure 11 (b) S.Dai arithmetic result, Figure 11 (c).
3) interpretation
From Fig. 7, Fig. 8, Fig. 9, Figure 10 as can be seen, the present invention is better than other method on the visual effect of reconstructed image, it is relatively good that the grain details information of image all keeps, and, can obtain good reconstruct effect for various types of input pictures such as Lena, Pepper, Bobcat, Athens;
No matter be to compare as can be seen from Figure 11, still compare that the present invention is better than them on visual effect with nearest MaYi algorithm based on study with traditional S.Dai algorithm based on model.
Claims (3)
1. the multitask super-resolution image reconstruction method based on the study of KSVD dictionary comprises the steps:
(1) input training image carries out filtering to it and extracts feature, extracts matrix M of 100,000 pairs of little block structures of image again, is divided into the K class, obtains K to initial dictionary H
1, H
2... H
kAnd L
1, L
2... L
k, and K cluster centre C
1, C
2... C
k
(2) utilize the KSVD algorithm to separate formula:
Subject to
To K to initial dictionary H
1, H
2... H
kAnd L
1, L
2... L
3Train, obtain K new dictionary D
H1, D
H2... D
HkAnd D
L1, D
L2... D
Lk,
Wherein, Y is the initial dictionary of input, and D is that target is trained dictionary and is initialized as a dictionary at random, and X is the Sparse Decomposition matrix,
Be any i row, || X
i|| 0 is X
i0 norm,
For finding the solution 2 norms of Y-DX, T
0Be the degree of rarefication control coefrficient;
(3) input one secondary low-resolution image Q after its filtering extraction feature, appoints a fritter q who gets characteristic image, calculates K the cluster centre C that obtains in q and the step (1) respectively
1, C
2... C
kBetween distance be: d
1, d
2... d
k, to d
1, d
2... d
kGet reciprocal and normalization, obtain K weight w
1, w
2... w
k
(4) utilize dictionary D
L1, D
L2... D
LkWith low-resolution image fritter q, find the solution dictionary D respectively
L1, D
L2... D
LkCorresponding Sparse Decomposition coefficient a
1, a
2... a
k, its solution formula is: q=D
LiA, i=1 wherein, 2....k;
(5) utilize dictionary D
H1, D
H2... D
HkWith coefficient a
1, a
2... a
k, find the solution high-definition picture fritter x respectively
1, x
2... x
k, its solution formula is x
i=D
Hia
1, i=1,2...k;
(6) utilize weight w
1, w
2... w
kTo x
1, x
2... x
kCarry out the weights addition and obtain the high-definition picture fritter:
(7) repeating step (3) is handled all input picture fritters successively to step (6), obtains initial reconstitution image Z, at last initial reconstitution image Z is carried out global optimization, obtains final reconstructed image Z
*
2. the multitask super-resolution image reconstruction method based on KSVD dictionary study according to claim 1, wherein step (2) described to K to initial dictionary H
1, H
2... H
kAnd L
1, L
2... L
kTrain, carry out as follows:
Wherein, Y is the initial dictionary of input, and D is target training dictionary and is initialized as a dictionary at random that X is the Sparse Decomposition matrix, d
jBe the j row atom of D,
For the j of X is capable, N is total columns of D, d
kBe the k row atom of D,
For the k of X is capable, E
kFor not using the k row atom d of D
kCarry out the error matrix that the signal Sparse Decomposition is produced;
2b) to the formula after the distortion
Multiply by matrix Ω
k, obtain the target decomposition formula
Wherein
Ω
kSize be P
*| ω
k|, P is the columns of the initial dictionary Y of input,
| ω
k| be ω
kThe mould value, and Ω
kAt (ω
k(j), j) locating is 1, and other place is 0 entirely, wherein 1≤j≤| ω
k|, ω
k(j) be ω
kThe j number;
2c) to the target decomposition formula
In error matrix
Carrying out the SVD decomposition obtains
Wherein U is a left singular matrix, V
TBe right singular matrix, Δ is a singular value matrix;
2d) be listed as the k row atom d that removes to upgrade D with first of left singular matrix U
k, in like manner successively the k value is upgraded processing from 1 to N to all atoms the D, obtain K to new dictionary D
H1, D
H2... D
HkAnd D
L1, D
L2... D
Lk
3. the multitask super-resolution image reconstruction method based on the study of KSVD dictionary according to claim 1, wherein step (7) is described carries out global optimization to initial reconstitution image Z, is undertaken by following formula:
Wherein, Z
0Be original high resolution image, Z
*Be final reconstructed image, DH is the down-sampling operation to initial reconstitution image Z, and Q is the low-resolution image of input.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2010102674462A CN101950365B (en) | 2010-08-30 | 2010-08-30 | Multi-task super-resolution image reconstruction method based on KSVD dictionary learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2010102674462A CN101950365B (en) | 2010-08-30 | 2010-08-30 | Multi-task super-resolution image reconstruction method based on KSVD dictionary learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101950365A true CN101950365A (en) | 2011-01-19 |
CN101950365B CN101950365B (en) | 2012-07-04 |
Family
ID=43453860
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2010102674462A Active CN101950365B (en) | 2010-08-30 | 2010-08-30 | Multi-task super-resolution image reconstruction method based on KSVD dictionary learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101950365B (en) |
Cited By (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102096819A (en) * | 2011-03-11 | 2011-06-15 | 西安电子科技大学 | Method for segmenting images by utilizing sparse representation and dictionary learning |
CN102129573A (en) * | 2011-03-10 | 2011-07-20 | 西安电子科技大学 | SAR (Synthetic Aperture Radar) image segmentation method based on dictionary learning and sparse representation |
CN102142137A (en) * | 2011-03-10 | 2011-08-03 | 西安电子科技大学 | High-resolution dictionary based sparse representation image super-resolution reconstruction method |
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 |
CN102510438A (en) * | 2011-11-21 | 2012-06-20 | 四川虹微技术有限公司 | Acquisition method of sparse coefficient vector for recovering and enhancing video image |
CN102521799A (en) * | 2011-11-21 | 2012-06-27 | 四川虹微技术有限公司 | Construction method of structural sparse dictionary for video image recovery enhancement |
CN102542549A (en) * | 2012-01-04 | 2012-07-04 | 西安电子科技大学 | Multi-spectral and panchromatic image super-resolution fusion method based on compressive sensing |
CN102800076A (en) * | 2012-07-16 | 2012-11-28 | 西安电子科技大学 | Image super-resolution reconstruction method based on double-dictionary learning |
CN102831581A (en) * | 2012-07-27 | 2012-12-19 | 中山大学 | Method for reconstructing super-resolution image |
CN103020935A (en) * | 2012-12-10 | 2013-04-03 | 宁波大学 | Self-adaption online dictionary learning super-resolution method |
CN103077511A (en) * | 2013-01-25 | 2013-05-01 | 西安电子科技大学 | Image super-resolution reconstruction method based on dictionary learning and structure similarity |
CN103136728A (en) * | 2012-12-14 | 2013-06-05 | 西安电子科技大学 | Image super-resolution method based on dictionary learning and non-local total variation |
CN103150713A (en) * | 2013-01-29 | 2013-06-12 | 南京理工大学 | Image super-resolution method of utilizing image block classification sparse representation and self-adaptive aggregation |
CN103279933A (en) * | 2013-06-07 | 2013-09-04 | 重庆大学 | Method for reconstructing single-image super-resolution based on double-layer model |
CN103455988A (en) * | 2013-09-17 | 2013-12-18 | 西安电子科技大学 | Super-resolution image reconstruction method based on structure self-similarity and sparse representation |
CN103530863A (en) * | 2013-10-30 | 2014-01-22 | 广东威创视讯科技股份有限公司 | Multistage reconstruction image super resolution method |
CN103985111A (en) * | 2014-02-21 | 2014-08-13 | 西安电子科技大学 | 4D-MRI super-resolution reconstruction method based on double-dictionary learning |
CN104517121A (en) * | 2014-12-10 | 2015-04-15 | 中国科学院遥感与数字地球研究所 | Spatial big data dictionary learning method based on particle swarm optimization |
CN105550989A (en) * | 2015-12-09 | 2016-05-04 | 西安电子科技大学 | Image super-resolution method based on nonlocal Gaussian process regression |
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 |
CN105931184A (en) * | 2016-04-18 | 2016-09-07 | 西安电子科技大学 | SAR image super-resolution method based on combined optimization |
CN106157240A (en) * | 2015-04-22 | 2016-11-23 | 南京理工大学 | Remote sensing image super resolution method based on dictionary learning |
CN106952317A (en) * | 2017-03-23 | 2017-07-14 | 西安电子科技大学 | Based on the high spectrum image method for reconstructing that structure is sparse |
CN106981047A (en) * | 2017-03-24 | 2017-07-25 | 武汉神目信息技术有限公司 | A kind of method for recovering high-resolution human face from low resolution face |
WO2018119565A1 (en) * | 2016-12-26 | 2018-07-05 | 深圳大学 | Method and device for correcting and reconstructing a barrel distorted image |
CN108961696A (en) * | 2018-06-20 | 2018-12-07 | 中国船舶重工集团公司第七〇九研究所 | A kind of early warning system and method for early warning of ocean nuclear power platform |
CN106651772B (en) * | 2016-11-25 | 2020-06-16 | 宁波大学 | Super-resolution reconstruction method of satellite cloud picture |
CN112241768A (en) * | 2020-11-25 | 2021-01-19 | 广东技术师范大学 | Fine image classification method based on deep decomposition dictionary learning |
CN112243130A (en) * | 2020-10-30 | 2021-01-19 | 西北大学 | Mobile AR application uploading energy consumption optimization method based on image super-resolution |
CN112241768B (en) * | 2020-11-25 | 2024-04-26 | 广东技术师范大学 | Fine image classification method based on deep decomposition dictionary learning |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103077505B (en) * | 2013-01-25 | 2015-12-09 | 西安电子科技大学 | Based on the image super-resolution rebuilding method of dictionary learning and documents structured Cluster |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008251029A (en) * | 2008-05-12 | 2008-10-16 | Mitsubishi Heavy Ind Ltd | Character recognition device and license plate recognition system |
WO2009085173A1 (en) * | 2007-12-21 | 2009-07-09 | Cognex Corporation | System and method for performing multi-image training for pattern recognition and registration |
CN101515329A (en) * | 2009-04-03 | 2009-08-26 | 东南大学 | Image matching method based on various features |
CN101609503A (en) * | 2009-07-16 | 2009-12-23 | 复旦大学 | People's face oversubscription image processing method based on double-current shape alignment |
-
2010
- 2010-08-30 CN CN2010102674462A patent/CN101950365B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2009085173A1 (en) * | 2007-12-21 | 2009-07-09 | Cognex Corporation | System and method for performing multi-image training for pattern recognition and registration |
JP2008251029A (en) * | 2008-05-12 | 2008-10-16 | Mitsubishi Heavy Ind Ltd | Character recognition device and license plate recognition system |
CN101515329A (en) * | 2009-04-03 | 2009-08-26 | 东南大学 | Image matching method based on various features |
CN101609503A (en) * | 2009-07-16 | 2009-12-23 | 复旦大学 | People's face oversubscription image processing method based on double-current shape alignment |
Non-Patent Citations (1)
Title |
---|
《红外》 20091231 吴艳 一种改进的IBP超分辨率重构算法 11-15 1-3 第30卷, 第12期 2 * |
Cited By (46)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102129573A (en) * | 2011-03-10 | 2011-07-20 | 西安电子科技大学 | SAR (Synthetic Aperture Radar) image segmentation method based on dictionary learning and sparse representation |
CN102142137A (en) * | 2011-03-10 | 2011-08-03 | 西安电子科技大学 | High-resolution dictionary based sparse representation image super-resolution reconstruction method |
CN102142137B (en) * | 2011-03-10 | 2012-10-24 | 西安电子科技大学 | High-resolution dictionary based sparse representation image super-resolution reconstruction method |
CN102096819A (en) * | 2011-03-11 | 2011-06-15 | 西安电子科技大学 | Method for segmenting images by utilizing sparse representation and dictionary learning |
CN102156875B (en) * | 2011-03-25 | 2013-04-03 | 西安电子科技大学 | Image super-resolution reconstruction method based on multitask KSVD (K singular value decomposition) 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 |
CN102510438A (en) * | 2011-11-21 | 2012-06-20 | 四川虹微技术有限公司 | Acquisition method of sparse coefficient vector for recovering and enhancing video image |
CN102521799A (en) * | 2011-11-21 | 2012-06-27 | 四川虹微技术有限公司 | Construction method of structural sparse dictionary for video image recovery enhancement |
CN102510438B (en) * | 2011-11-21 | 2014-05-14 | 四川虹微技术有限公司 | Acquisition method of sparse coefficient vector for recovering and enhancing video image |
CN102542549A (en) * | 2012-01-04 | 2012-07-04 | 西安电子科技大学 | Multi-spectral and panchromatic image super-resolution fusion method based on compressive sensing |
CN102542549B (en) * | 2012-01-04 | 2015-02-18 | 西安电子科技大学 | Multi-spectral and panchromatic image super-resolution fusion method based on compressive sensing |
CN102800076A (en) * | 2012-07-16 | 2012-11-28 | 西安电子科技大学 | Image super-resolution reconstruction method based on double-dictionary learning |
CN102800076B (en) * | 2012-07-16 | 2015-03-04 | 西安电子科技大学 | Image super-resolution reconstruction method based on double-dictionary learning |
CN102831581A (en) * | 2012-07-27 | 2012-12-19 | 中山大学 | Method for reconstructing super-resolution image |
CN103020935B (en) * | 2012-12-10 | 2015-09-02 | 宁波大学 | The image super-resolution method of the online dictionary learning of a kind of self-adaptation |
CN103020935A (en) * | 2012-12-10 | 2013-04-03 | 宁波大学 | Self-adaption online dictionary learning super-resolution method |
CN103136728A (en) * | 2012-12-14 | 2013-06-05 | 西安电子科技大学 | Image super-resolution method based on dictionary learning and non-local total variation |
CN103136728B (en) * | 2012-12-14 | 2015-09-02 | 西安电子科技大学 | Based on the image super-resolution method of dictionary learning and non local total variance |
CN103077511B (en) * | 2013-01-25 | 2015-04-08 | 西安电子科技大学 | Image super-resolution reconstruction method based on dictionary learning and structure similarity |
CN103077511A (en) * | 2013-01-25 | 2013-05-01 | 西安电子科技大学 | Image super-resolution reconstruction method based on dictionary learning and structure similarity |
CN103150713A (en) * | 2013-01-29 | 2013-06-12 | 南京理工大学 | Image super-resolution method of utilizing image block classification sparse representation and self-adaptive aggregation |
CN103150713B (en) * | 2013-01-29 | 2015-12-09 | 南京理工大学 | Utilize the image super-resolution method that image block classification rarefaction representation is polymerized with self-adaptation |
CN103279933B (en) * | 2013-06-07 | 2016-10-26 | 重庆大学 | A kind of single image super resolution ratio reconstruction method based on bilayer model |
CN103279933A (en) * | 2013-06-07 | 2013-09-04 | 重庆大学 | Method for reconstructing single-image super-resolution based on double-layer model |
CN103455988A (en) * | 2013-09-17 | 2013-12-18 | 西安电子科技大学 | Super-resolution image reconstruction method based on structure self-similarity and sparse representation |
CN103530863A (en) * | 2013-10-30 | 2014-01-22 | 广东威创视讯科技股份有限公司 | Multistage reconstruction image super resolution method |
CN103530863B (en) * | 2013-10-30 | 2017-01-11 | 广东威创视讯科技股份有限公司 | Multistage reconstruction image super resolution method |
CN103985111B (en) * | 2014-02-21 | 2017-07-25 | 西安电子科技大学 | A kind of 4D MRI ultra-resolution ratio reconstructing methods learnt based on doubledictionary |
CN103985111A (en) * | 2014-02-21 | 2014-08-13 | 西安电子科技大学 | 4D-MRI super-resolution reconstruction method based on double-dictionary learning |
CN104517121A (en) * | 2014-12-10 | 2015-04-15 | 中国科学院遥感与数字地球研究所 | Spatial big data dictionary learning method based on particle swarm optimization |
CN106157240A (en) * | 2015-04-22 | 2016-11-23 | 南京理工大学 | Remote sensing image super resolution method based on 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 |
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 |
CN105550989A (en) * | 2015-12-09 | 2016-05-04 | 西安电子科技大学 | Image super-resolution method based on nonlocal Gaussian process regression |
CN105550989B (en) * | 2015-12-09 | 2018-11-30 | 西安电子科技大学 | The image super-resolution method returned based on non local Gaussian process |
CN105931184B (en) * | 2016-04-18 | 2018-12-14 | 西安电子科技大学 | SAR image super-resolution method based on combined optimization |
CN105931184A (en) * | 2016-04-18 | 2016-09-07 | 西安电子科技大学 | SAR image super-resolution method based on combined optimization |
CN106651772B (en) * | 2016-11-25 | 2020-06-16 | 宁波大学 | Super-resolution reconstruction method of satellite cloud picture |
WO2018119565A1 (en) * | 2016-12-26 | 2018-07-05 | 深圳大学 | Method and device for correcting and reconstructing a barrel distorted image |
CN106952317A (en) * | 2017-03-23 | 2017-07-14 | 西安电子科技大学 | Based on the high spectrum image method for reconstructing that structure is sparse |
CN106952317B (en) * | 2017-03-23 | 2020-04-07 | 西安电子科技大学 | Hyperspectral image reconstruction method based on structure sparsity |
CN106981047A (en) * | 2017-03-24 | 2017-07-25 | 武汉神目信息技术有限公司 | A kind of method for recovering high-resolution human face from low resolution face |
CN108961696A (en) * | 2018-06-20 | 2018-12-07 | 中国船舶重工集团公司第七〇九研究所 | A kind of early warning system and method for early warning of ocean nuclear power platform |
CN112243130A (en) * | 2020-10-30 | 2021-01-19 | 西北大学 | Mobile AR application uploading energy consumption optimization method based on image super-resolution |
CN112241768A (en) * | 2020-11-25 | 2021-01-19 | 广东技术师范大学 | Fine image classification method based on deep decomposition dictionary learning |
CN112241768B (en) * | 2020-11-25 | 2024-04-26 | 广东技术师范大学 | Fine image classification method based on deep decomposition dictionary learning |
Also Published As
Publication number | Publication date |
---|---|
CN101950365B (en) | 2012-07-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101950365B (en) | Multi-task super-resolution image reconstruction method based on KSVD dictionary learning | |
CN102156875B (en) | Image super-resolution reconstruction method based on multitask KSVD (K singular value decomposition) dictionary learning | |
Yang et al. | DRFN: Deep recurrent fusion network for single-image super-resolution with large factors | |
CN103279980B (en) | Based on the Leaf-modeling method of cloud data | |
CN110390638B (en) | High-resolution three-dimensional voxel model reconstruction method | |
CN111784821B (en) | Three-dimensional model generation method and device, computer equipment and storage medium | |
CN110163801B (en) | Image super-resolution and coloring method, system and electronic equipment | |
CN107358576A (en) | Depth map super resolution ratio reconstruction method based on convolutional neural networks | |
CN105488776B (en) | Super-resolution image reconstruction method and device | |
CN102332153B (en) | Kernel regression-based image compression sensing reconstruction method | |
CN105046672A (en) | Method for image super-resolution reconstruction | |
CN107464217B (en) | Image processing method and device | |
CN103020935A (en) | Self-adaption online dictionary learning super-resolution method | |
CN106157244A (en) | A kind of QR Code Image Super-resolution Reconstruction method based on rarefaction representation | |
CN110517352B (en) | Three-dimensional reconstruction method, storage medium, terminal and system of object | |
CN103279933A (en) | Method for reconstructing single-image super-resolution based on double-layer model | |
CN110210524A (en) | A kind of training method, image enchancing method and the device of image enhancement model | |
CN106504207A (en) | A kind of image processing method | |
CN113592711A (en) | Three-dimensional reconstruction method, system and equipment for point cloud data nonuniformity and storage medium | |
CN104299201B (en) | Image reconstruction method based on heredity sparse optimization | |
CN113096015B (en) | Image super-resolution reconstruction method based on progressive perception and ultra-lightweight network | |
CN109447897B (en) | Real scene image synthesis method and system | |
CN109658508B (en) | Multi-scale detail fusion terrain synthesis method | |
CN114359039A (en) | Knowledge distillation-based image super-resolution method | |
CN113191367B (en) | Semantic segmentation method based on dense scale dynamic network |
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 |