CN103020935B - The image super-resolution method of the online dictionary learning of a kind of self-adaptation - Google Patents
The image super-resolution method of the online dictionary learning of a kind of self-adaptation Download PDFInfo
- Publication number
- CN103020935B CN103020935B CN201210535873.3A CN201210535873A CN103020935B CN 103020935 B CN103020935 B CN 103020935B CN 201210535873 A CN201210535873 A CN 201210535873A CN 103020935 B CN103020935 B CN 103020935B
- Authority
- CN
- China
- Prior art keywords
- dictionary
- sub
- image
- resolution
- low resolution
- 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.)
- Expired - Fee Related
Links
Abstract
The invention discloses the image super-resolution method of the online dictionary learning of a kind of self-adaptation, first selected one group of high resolving power and low resolution training plan image set, then on high/low training plan image set, a kind of corresponding relation is set up, provide more prior imformation by high/low resolution dictionary to for reconstructed image, under high amplification factor, also can obtain good quality reconstruction; Present invention uses SP sparse coding algorithm simultaneously, overcome the shortcoming that conventional greedy algorithm reconstruct degree of accuracy is not high, maintain lower computation complexity simultaneously; Advantage has taken the slow shortcoming of (as MOD, K-SVD etc.) calculation of complex in main flow dictionary learning algorithm instantly, training speed, shorten image reconstruction time on the whole, with existing based on learning compared with image super-resolution technology, the method that the present invention proposes has higher reconstruction accuracy and shorter algorithm time.
Description
Technical field
The present invention relates to the image super-resolution technology in signal transacting and multimedia-data procession field, especially relate to the image super-resolution method of the online dictionary learning of a kind of self-adaptation.
Background technology
Image super-resolution (super resolution, SR) refers to that single width or several low-resolution images revert to the process of high resolving power (high resolution, HR) image.Along with image is in the increasingly extensive application of all trades and professions, the requirement of people to image resolution ratio is also more and more higher, because HR image means that image has high pixel density, more details can be provided for people, and these details often play a key effect in image practical application.Current image super-resolution technology has all achieved in fields such as medical imaging, remote sensing detecting, public safeties and has applied widely, and even in some image applications field, the resolution of image has become the important indicator weighing picture quality.Therefore further investigate image super-resolution technology, there is very important practical significance.
Obtain the most direct method of high-definition picture and use high-resolution image sensors exactly, but the making of high-resolution image sensors is often subject to the restriction of technological level and cost, therefore, under the prerequisite not changing sensor, the method for software is used to go the resolution improving image to become the popular research direction in computer vision field.Image super-resolution technology can be divided into three main category: based on interpolation, based on rebuild and based on study method, wherein based on Model Reconstruction and based on study method be research direction main in recent years.The mapping model of a low-resolution image to high-definition picture is mainly built based on the method for rebuilding, reconstruct efficiency is higher, but be difficult to find the mapping model that is unified, and reconstructed image quality sharply can decline when the image super-resolution reconstruct carrying out high amplification factor.And reconstruct accurate, robustness advantages of higher based on the method for study because having, be current most popular image super-resolution technology.
Super-resolution algorithms thought based on study is proposed in 2002 by people such as Freeman the earliest, they utilize markov network to learn the relation between high and low frequency information, compared to before based on interpolation and based on rebuild method, this method of sample learning that utilizes can obtain more high-frequency information, solves because prior imformation providing capability is not enough and rebuilds the serious problem of image fault under causing high amplification factor.But the shortcoming of this method is also obvious, is exactly to require higher to the selection of training sample, and very responsive to the noise in image.The people such as Chang proposes the image super-resolution method embedded based on neighborhood subsequently, and the basic thought of this kind of method is that high-low resolution image block corresponding to hypothesis can form the stream shape with identical local geometry at their feature space.This algorithm needs less sample relatively, and has good noiseproof feature.But algorithm Problems existing is high-low resolution image block, and the more difficult neighborhood of setting up when neighborhood embeds keeps relation, in order to improve this problem, has occurred based on the training sample selection algorithm of Histogram Matching with based on methods such as local residual error embeddings.The people such as Karl propose to use support vector regression (SVR) to realize image super-resolution, and SVR, by the automatic selection to sample, employs less training set, but the contrast of image is declined relatively.2010, the people such as Yang are under compressed sensing (CS) framework, sparse representation theory is adopted to propose a kind of image super-resolution reconstructing method based on study, they learn one group of rarefaction representation base from the low resolution training image of one group of high-definition picture and correspondence thereof, this group set of bases forms a complete dictionary of mistake, make each image block in training set can cross complete dictionary rarefaction representation by this by linear programming, subsequently in super-resolution image reconstruction process, first obtain original low-resolution image and cross the rarefaction representation coefficient under complete dictionary, then high-definition picture is reconstructed with this group rarefaction representation coefficient weighting.This algorithm initiative CS theory is used for image super-resolution technology, overcome the select permeability for Size of Neighborhood in neighborhood embedding grammar, namely when solving rarefaction representation, without the need to specifying the number of the required base of reconstruct, it represents that coefficient and base number are obtained by linear programming for solution simultaneously.But this algorithm exists, and training sample is excessive, dictionary is too complicated to process of establishing, dictionary selects not have the defects such as adaptivity.In the same year, Pu sword etc. proposes again the algorithm employing BP sparse coding and K-SVD dictionary updating in dictionary learning, achieves than the former better super-resolution efect; But this algorithm still also exists the defects such as training sample time length.
Summary of the invention
It is short that technical matters to be solved by this invention is to provide a kind of training sample time, the image super-resolution method of the online dictionary learning of the self-adaptation that picture quality is high.
The present invention solves the problems of the technologies described above adopted technical scheme: the image super-resolution method of the online dictionary learning of a kind of self-adaptation, comprises the following steps:
1. one group of low-resolution image of one group of high-definition picture and correspondence thereof is chosen as training sample;
2. the high-frequency characteristic of training sample is extracted, obtain one group of low resolution sample characteristics image of one group of high resolving power sample characteristics image and its correspondence, Q the high resolving power sample characteristics image fritter randomly drawed in high resolving power sample characteristics image forms matrix M, extract low resolution characteristic image fritter corresponding with the high resolving power sample characteristics image fritter extracted in low resolution sample characteristics image form matrix M ', wherein Q is more than or equal to 30,000 and is less than or equal to 100,000, by matrix M and matrix M ' be divided into k class, wherein k>=2, obtain matrix M ' k cluster centre m
1, m
2, m
3..., m
kand initial sub-dictionary set { (D
l1, D
h1), (D
l2, D
h2), (D
l3, D
h3) ..., (D
lk, D
hk), wherein D
l1, D
l2, D
l3..., D
lkrepresent k the sub-dictionary of initial low resolution, D
h1, D
h2, D
h3..., D
hkrepresent k the sub-dictionary of initial high resolution,
3. utilize on-line Algorithm to be optimized initial sub-dictionary set, obtain sub-the dictionary set { (D of optimal objective
l1-best, D
h1-best), (D
l2-best, D
h2-best), (D
l3-best, D
h3-best) ..., (D
lk-best, D
hk-best), wherein D
l1-best, D
l2-best, D
l3-best..., D
lk-bestrepresent k the sub-dictionary of optimum low resolution target, D
h1-best, D
h2-best, D
h3-best..., D
hk-bestrepresent k the sub-dictionary of optimum high resolving power target;
4. input needs the low-resolution image X carrying out super-resolution amplification, extracts the high-frequency characteristic of low-resolution image X, obtains the low resolution characteristic image X' that low-resolution image X is corresponding, then choose q the image fritter X of low resolution characteristic image X'
q, q>=1, image fritter X
qcorresponding matrix is designated as x
q, compute matrix x respectively
qwith cluster centre m
1, m
2, m
3..., m
keuclidean distance, compare x
qwith the size of the Euclidean distance of each cluster centre, obtain the cluster centre m that Euclidean distance is minimum
n, 1≤n≤k, selects with m
nthe sub-dictionary of optimum low resolution target that the sub-dictionary of initial low resolution for cluster centre is corresponding, is denoted as D
lq-best;
5. SP algorithm compute matrix x is utilized
qat D
lq-bestunder rarefaction representation factor alpha
q, α
q=argmin||x
q-D
lq-bestα
q||
2+ λ || α
q||
1, α
q=SP (D
lq-best, x
q), λ represents regularization coefficient and 0< λ <1, and concrete steps are as follows:
5.-1 by D
lq-bestin with matrix x
qthe row index of the K row atom that correlativity is maximum is designated as
represent D
lp-bestin row number be
former molecular matrix,
representing matrix x
q?
on projection,
Wherein
* the transposition of representing matrix;
5.-2 initialization: definition original state projection
initial residual vector be r
0,
x' under original state
qthe row index of K sequence atom corresponding to middle element maximal value is designated as I
0,
represent D
lp-bestin row number be I
0former molecular matrix;
5.-3 set current iteration number of times as ω, ω>=1, project in current iteration
residual vector be r
ω, order
X ' in current iteration
pthe row index of K sequence atom corresponding to middle element maximal value is I
ω, in conjunction with formula
{ D
lq-bestin with r
ω-1the row index of the K row atom that correlativity is maximum } and
upgrade r
ω,
and I
ω, r
ω-1represent projection
residual vector in ω-1 iteration,
represent
in row number be I
ωformer molecular matrix,
represent D
lp-bestin row number be
former molecular matrix;
5.-4 compare r
ωwith r
ω-1if, || r
ω||
2>||r
ω-1||
2, then iteration terminates, otherwise, 5. carry out iteration renewal in-3 using returning step as current iteration number of times after ω adds 1;
5., after-5 iteration complete, least square method is used to try to achieve x
qat dictionary D
lq-bestoptimum rarefaction representation factor alpha
q;
6. select and D
lq-bestthe corresponding sub-dictionary D of high resolving power target
hq-best, utilize rarefaction representation factor alpha
qand D
hq-bestsolve x
qat D
hq-besthigh-definition picture reconstruct fritter y under corresponding
q=D
hq-bestα
q;
7. according to step 4. ~ method 6., process by all image fritters of " it " font to low resolution characteristic image X', obtain initial high-resolution reconstruction image
8. to high-resolution reconstruction image
carry out block process and obtain final high-resolution reconstruction image Y.
The concrete steps that 3. described step is optimized initial sub-dictionary set are as follows:
3.-1 couple of sub-dictionary D of low resolution
l1be optimized, concrete steps are:
A, suppose that the total iterations optimized is T, in the t time iteration, input any one the characteristic image block f in low resolution sample characteristics image
l, 1≤t≤T;
B, fix the sub-dictionary of target that t-1 iteration obtains
subspace back tracking method is used to solve
λ represents regularization coefficient and 0< λ <1, and wherein, argmin represents the minimum value solving functional, || || represent and solve norm, obtain characteristic image block f in the t time iteration
lat the sub-dictionary of target
under sparse decomposition coefficients Λ
t;
C, fixing sparse decomposition coefficients Λ
tif, the sub-dictionary D of low resolution
l1there is p atom, order
I=1,2 ... t, a
jrepresent A
tmiddle jth row, b
jrepresent B
tmiddle jth row, a
jand b
jbe the matrix of p × 1,1≤j≤p;
D, establish the sub-dictionary D of low resolution
l1a jth atom of the corresponding sub-dictionary of target is d
j, to d
jbe optimized, then
represent the sub-dictionary D of low resolution
l1the sub-dictionary of the target upgraded, A
jjrepresent a
jthe value of middle jth row, max represents the maximal value of solved function;
E, upgrade low resolution sub-dictionary D according to steps d
l1p atom, complete the t time iteration, obtain the sub-dictionary D of low resolution
l1the sub-dictionary of target after the t time iteration
F, general
substitute into formula
0< λ <1, obtains the sub-dictionary of target that the t time circulation upgrades
G, the rest may be inferred, and completing input picture is characteristic image block f
ltime, the sub-dictionary D of low resolution
l1t iteration, obtain characteristic image block f
lthe sub-dictionary of target of corresponding optimization
Except f in h, successively input low resolution sample characteristics image
lother all characteristic image blocks in addition, the principle identical according to step a ~ g is trained, and completes the sub-dictionary D of initial low resolution
l1training, last is taken turns the sub-dictionary of updated target as the sub-dictionary D of initial low resolution
l1the sub-dictionary D of optimal objective
l1-best;
3.-2 use the sub-dictionary D of low resolution
l1the same principle be optimized is respectively to D
l2, D
l3..., D
lk, D
h1, D
h2, D
h3..., D
hkbe optimized, obtain D
l2, D
l3..., D
lk, D
h1, D
h2, D
h3..., D
hkthe corresponding sub-dictionary of optimal objective, finally obtains sub-the dictionary set { (D of optimal objective
l1-best, D
h1-best), (D
l2-best, D
h2-best), (D
l3-best, D
h3-best) ..., (D
lk-best, D
hk-best).
Described step 8. in go block disposal route to be get average to the pixel of lap after each iteration.
Compared with prior art, the invention has the advantages that and overcome traditional images super-resolution problem such as reconstruction quality decline and algorithm time length under high amplification factor well:
1) compare with the image super-resolution technology based on model based on interpolation with existing, the method that the present invention proposes overcomes the former can not provide the defect that maybe can not provide enough prior imformations, first selected one group of high resolving power and low resolution training plan image set, then on high/low training plan image set, a kind of corresponding relation is set up, provide more prior imformation by high/low resolution dictionary to for reconstructed image, under high amplification factor, also can obtain good quality reconstruction;
2) with existing based on learning compared with image super-resolution technology, the method that the present invention proposes has higher reconstruction accuracy and shorter algorithm time, present invention uses SP sparse coding algorithm, overcome the shortcoming that conventional greedy algorithm reconstruct degree of accuracy is not high, maintain lower computation complexity simultaneously; And online dictionary learning algorithm, overcome the shortcoming that (as MOD, K-SVD etc.) calculation of complex in main flow dictionary learning algorithm instantly, training speed are slow, therefore further shorten image reconstruction time on the whole.
Accompanying drawing explanation
The process flow diagram of Fig. 1 the inventive method;
Fig. 2 (a) original high resolution cloud atlas image;
The cloud atlas image that Fig. 2 (b) adopts bilinear interpolation method to reconstruct;
The cloud atlas image that Fig. 2 (c) adopts Yang method to reconstruct;
The cloud atlas image that Fig. 2 (d) adopts the inventive method to reconstruct;
Fig. 3 (a) original high resolution Cat image;
The Cat image that Fig. 3 (b) adopts bilinear interpolation method to reconstruct;
The Cat image that Fig. 3 (c) adopts Yang method to reconstruct;
The Cat image that Fig. 3 (d) adopts the inventive method to reconstruct;
Fig. 4 (a) original high resolution Building image;
The Building image that Fig. 4 (b) adopts bilinear interpolation method to reconstruct;
The Building image that Fig. 4 (c) adopts Yang method to reconstruct;
The Building image that Fig. 4 (d) adopts the inventive method to reconstruct.
Embodiment
Below in conjunction with accompanying drawing embodiment, the present invention is described in further detail.
As shown in Figure 1, the image super-resolution method of the online dictionary learning of a kind of self-adaptation, is characterized in that comprising the following steps:
1. one group of low-resolution image of one group of high-definition picture and correspondence thereof is chosen as training sample;
2. the high-frequency characteristic of training sample is extracted, obtain one group of low resolution sample characteristics image of one group of high resolving power sample characteristics image and its correspondence, Q the high resolving power sample characteristics image fritter randomly drawed in high resolving power sample characteristics image forms matrix M, extract low resolution characteristic image fritter corresponding with the high resolving power sample characteristics image fritter extracted in low resolution sample characteristics image form matrix M ', wherein Q is more than or equal to 30,000 and is less than or equal to 100,000, by matrix M and matrix M ' be divided into k class, wherein k>=2, obtain matrix M ' k cluster centre m
1, m
2, m
3..., m
kand initial sub-dictionary set { (D
l1, D
h1), (D
l2, D
h2), (D
l3, D
h3) ..., (D
lk, D
hk), wherein D
l1, D
l2, D
l3..., D
lkrepresent k the sub-dictionary of initial low resolution, D
h1, D
h2, D
h3..., D
hkrepresent k the sub-dictionary of initial high resolution,
3. utilize on-line Algorithm to be optimized initial sub-dictionary set, obtain sub-the dictionary set { (D of optimal objective
l1-best, D
h1-best), (D
l2-best, D
h2-best), (D
l3-best, D
h3-best) ..., (D
lk-best, D
hk-best), wherein D
l1-best, D
l2-best, D
l3-best..., D
lk-bestrepresent k the sub-dictionary of optimum low resolution target, D
h1-best, D
h2-best, D
h3-best..., D
hk-bestrepresent k the sub-dictionary of optimum high resolving power target; Concrete steps are as follows:
3.-1 couple of sub-dictionary D of low resolution
l1be optimized, concrete steps are:
A, suppose that the total iterations optimized is T, in the t time iteration, input any one the characteristic image block f in low resolution sample characteristics image
l, 1≤t≤T;
B, fix the sub-dictionary of target that t-1 iteration obtains
subspace back tracking method is used to solve
λ represents regularization coefficient and 0< λ <1, and wherein, argmin represents the minimum value solving functional, || || represent and solve norm, obtain characteristic image block f in the t time iteration
lat the sub-dictionary of target
under sparse decomposition coefficients Λ
t;
C, fixing sparse decomposition coefficients Λ
tif, the sub-dictionary D of low resolution
l1there is p atom, order
I=1,2 ... t, a
jrepresent A
tmiddle jth row, b
jrepresent B
tmiddle jth row, a
jand b
jbe the matrix of p × 1,1≤j≤p;
D, establish the sub-dictionary D of low resolution
l1a jth atom of the corresponding sub-dictionary of target is d
j, to d
jbe optimized, then
represent the sub-dictionary D of low resolution
l1the sub-dictionary of the target upgraded, A
jjrepresent a
jthe value of middle jth row, max represents the maximal value of solved function;
E, upgrade low resolution sub-dictionary D according to steps d
l1p atom, complete the t time iteration, obtain the sub-dictionary D of low resolution
l1the sub-dictionary of target after the t time iteration
F, general
substitute into formula
0< λ <1, obtains the sub-dictionary of target that the t time circulation upgrades
G, the rest may be inferred, and completing input picture is characteristic image block f
ltime, the sub-dictionary D of low resolution
l1t iteration, obtain characteristic image block f
lthe sub-dictionary of target of corresponding optimization
Except f in h, successively input low resolution sample characteristics image
lother all characteristic image blocks in addition, the principle identical according to step a ~ g is trained, and completes the sub-dictionary D of initial low resolution
l1training, last is taken turns the sub-dictionary of updated target as the sub-dictionary D of initial low resolution
l1the sub-dictionary D of optimal objective
l1-best;
3.-2 use the sub-dictionary D of low resolution
l1the same principle be optimized is respectively to D
l2, D
l3..., D
lk, D
h1, D
h2, D
h3..., D
hkbe optimized, obtain D
l2, D
l3..., D
lk, D
h1, D
h2, D
h3..., D
hkthe corresponding sub-dictionary of optimal objective, finally obtains sub-the dictionary set { (D of optimal objective
l1-best, D
h1-best), (D
l2-best, D
h2-best), (D
l3-best, D
h3-best) ..., (D
lk-best, D
hk-best);
4. input needs the low-resolution image X carrying out super-resolution amplification, extracts the high-frequency characteristic of low-resolution image X, obtains the low resolution characteristic image X' that low-resolution image X is corresponding, then choose q the image fritter X of low resolution characteristic image X'
q, q>=1, image fritter X
qcorresponding matrix is designated as x
q, compute matrix x respectively
qwith cluster centre m
1, m
2, m
3..., m
keuclidean distance, compare x
qwith the size of the Euclidean distance of each cluster centre, obtain the cluster centre m that Euclidean distance is minimum
n, 1≤n≤k, selects with m
nthe sub-dictionary of optimum low resolution target that the sub-dictionary of initial low resolution for cluster centre is corresponding, is denoted as D
lq-best;
5. SP algorithm compute matrix x is utilized
qat D
lq-bestunder rarefaction representation factor alpha
q, α
q=argmin||x
q-D
lq-bestα
q||
2+ λ || α
q||
1, α
q=SP (D
lq-best, x
q), λ represents regularization coefficient and 0< λ <1, and concrete steps are as follows:
5.-1 by D
lq-bestin with matrix x
qthe row index of the K row atom that correlativity is maximum is designated as
represent D
lp-bestin row number be
former molecular matrix,
representing matrix x
q?
on projection,
Wherein
* the transposition of representing matrix;
5.-2 initialization: definition original state projection
initial residual vector be r
0,
x' under original state
qthe row index of K sequence atom corresponding to middle element maximal value is designated as I
0,
represent D
lp-bestin row number be I
0former molecular matrix;
5.-3 set current iteration number of times as ω, ω>=1, project in current iteration
residual vector be r
ω, order
X ' in current iteration
pthe row index of K sequence atom corresponding to middle element maximal value is I
ω, in conjunction with formula
{ D
lq-bestin with r
ω-1the row index of the K row atom that correlativity is maximum } and
upgrade r
ω,
and I
ω, r
ω-1represent projection
residual vector in ω-1 iteration,
represent
in row number be I
ωformer molecular matrix,
represent D
lp-bestin row number be
former molecular matrix;
5.-4 compare r
ωwith r
ω-1if, || r
ω||
2>||r
ω-1||
2, then iteration terminates, otherwise, 5. carry out iteration renewal in-3 using returning step as current iteration number of times after ω adds 1;
5., after-5 iteration complete, least square method is used to try to achieve x
qat dictionary D
lq-bestoptimum rarefaction representation factor alpha
q;
6. select and D
lq-bestthe corresponding sub-dictionary D of high resolving power target
hq-best, utilize rarefaction representation factor alpha
qand D
hq-bestsolve x
qat D
hq-besthigh-definition picture reconstruct fritter y under corresponding
q=D
hq-bestα
q;
7. according to step 4. ~ method 6., process by all image fritters of " it " font to low resolution characteristic image X', obtain initial high-resolution reconstruction image
;
8. to high-resolution reconstruction image
carry out block process and obtain final high-resolution reconstruction image Y, wherein go block disposal route to be get average to the pixel of lap after each iteration.
The validity of simulating, verifying method of the present invention by experiment.Experiment simulation carries out on Matlab7.0 platform.Select three 512 × 512 high resolution gray images as original image in experiment altogether, be respectively the original high resolution remote sensing satellite cloud atlas shown in Fig. 2 (a), the original high resolution Cat image shown in Fig. 3 (a) and the original high resolution Building image shown in Fig. 4 (a).First to three width original images by four times of down-samplings, fuzzy and add process of making an uproar and obtain corresponding low-resolution image, then four times of super-resolution amplifying and reconfigurations are made respectively by the low-resolution image that bilinear interpolation method, Yang method and the inventive method are corresponding to three width original images, image reconstruction quality and algorithm time are compared, draws simulation result.Extract 50,000 characteristic image fritters respectively in high resolving power sample characteristics image and low resolution sample characteristics image and form initial dictionary, namely Q equals 50,000, and Image Reconstruction chooses 3 × 3 image blocks, and lap is 1 pixel.Wherein, adopt the cloud atlas image of bilinear interpolation method reconstruct as shown in Fig. 2 (b); Adopt the cloud atlas image of Yang method reconstruct as shown in Fig. 2 (c); Adopt the cloud atlas image of the inventive method reconstruct as shown in Fig. 2 (d); Adopt the Cat image of bilinear interpolation method reconstruct as shown in Fig. 3 (b); Adopt the Cat image of Yang method reconstruct as shown in Fig. 3 (c); Adopt the Cat image of the inventive method reconstruct as shown in Fig. 3 (d); Adopt the Building image of bilinear interpolation method reconstruct as shown in Fig. 4 (b); Adopt the Building image of Yang method reconstruct as shown in Fig. 4 (c); Shown in Building image graph Fig. 4 (d) adopting the inventive method to reconstruct.Reconstructed image quality adopts to be passed judgment on the Y-PSNR (PSNR) of former full resolution pricture:
In formula (1), f (i, j) represents the i-th row and the j row pixel of original high-resolution image, f'(i, j) represent degrade after the i-th row of super-resolution reconstruction image and j row pixel, f
maxrepresent image max pixel value, M × N is image size.Institute the methodical time with second (s) for unit.Three width image simulation data results are as shown in Table 1 and Table 2:
The lower three width reconstructed image PSNR (dB) of table 1 distinct methods
Table 2 Yang method and the inventive method required time (sample training time+reconstitution time (s))
Claims (3)
1. an image super-resolution method for the online dictionary learning of self-adaptation, is characterized in that comprising the following steps:
1. one group of low-resolution image of one group of high-definition picture and correspondence thereof is chosen as training sample;
2. the high-frequency characteristic of training sample is extracted, obtain one group of low resolution sample characteristics image of one group of high resolving power sample characteristics image and its correspondence, Q the high resolving power sample characteristics image fritter randomly drawed in high resolving power sample characteristics image forms matrix M, extract low resolution characteristic image fritter corresponding with the high resolving power sample characteristics image fritter extracted in low resolution sample characteristics image form matrix M ', wherein Q is more than or equal to 30,000 and is less than or equal to 100,000, by matrix M and matrix M ' be divided into k class, wherein k>=2, obtain matrix M ' k cluster centre m
1, m
2, m
3..., m
kand initial sub-dictionary set { (D
l1, D
h1), (D
l2, D
h2), (D
l3, D
h3) ..., (D
lk, D
hk), wherein D
l1, D
l2, D
l3..., D
lkrepresent k the sub-dictionary of initial low resolution, D
h1, D
h2, D
h3..., D
hkrepresent k the sub-dictionary of initial high resolution,
3. utilize on-line Algorithm to be optimized initial sub-dictionary set, obtain sub-the dictionary set { (D of optimal objective
l1-best, D
h1-best), (D
l2-best, D
h2-best), (D
l3-best, D
h3-best) ..., (D
lk-best, D
hk-best), wherein D
l1-best, D
l2-best, D
l3-best..., D
lk-bestrepresent k the sub-dictionary of optimum low resolution target, D
h1-best, D
h2-best, D
h3-best..., D
hk-bestrepresent k the sub-dictionary of optimum high resolving power target;
4. input needs the low-resolution image X carrying out super-resolution amplification, extracts the high-frequency characteristic of low-resolution image X, obtains the low resolution characteristic image X' that low-resolution image X is corresponding, then choose q the image fritter X of low resolution characteristic image X'
q, q>=1, image fritter X
qcorresponding matrix is designated as x
q, compute matrix x respectively
qwith cluster centre m
1, m
2, m
3..., m
keuclidean distance, compare x
qwith the size of the Euclidean distance of each cluster centre, obtain the cluster centre m that Euclidean distance is minimum
n, 1≤n≤k, selects with m
nthe sub-dictionary of optimum low resolution target that the sub-dictionary of initial low resolution for cluster centre is corresponding, is denoted as D
lq-best;
5. SP algorithm compute matrix x is utilized
qat D
lq-bestunder rarefaction representation factor alpha
q, α
q=argmin||x
q-D
lq-bestα
q||
2+ λ || α
q||
1, α
q=SP (D
lq-best, x
q), λ represents regularization coefficient and 0< λ <1, and concrete steps are as follows:
5.-1 by D
lq-bestin with matrix x
qthe row index of the K row atom that correlativity is maximum is designated as
represent D
lp-bestin row number be
former molecular matrix,
representing matrix x
q?
on projection,
Wherein
* the transposition of representing matrix;
5.-2 initialization: definition original state projection
initial residual vector be r
0,
x' under original state
qthe row index of K sequence atom corresponding to middle element maximal value is designated as I
0,
represent D
lp-bestin row number be I
0former molecular matrix;
5.-3 set current iteration number of times as ω, ω>=1, project in current iteration
residual vector be r
ω, order
X ' in current iteration
pthe row index of K sequence atom corresponding to middle element maximal value is I
ω, in conjunction with formula
with
Upgrade r
ω,
and I
ω, r
ω-1represent projection
residual vector in ω-1 iteration,
represent D
lp-bestin row number be I
ωformer molecular matrix,
represent D
lp-bestin row number be
former molecular matrix;
5.-4 compare r
ωwith r
ω-1if, || r
ω||
2>||r
ω-1||
2, then iteration terminates, otherwise, 5. carry out iteration renewal in-3 using returning step as current iteration number of times after ω adds 1;
5., after-5 iteration complete, least square method is used to try to achieve x
qat dictionary D
lq-bestoptimum rarefaction representation factor alpha
q;
6. select and D
lq-bestthe corresponding sub-dictionary D of high resolving power target
hq-best, utilize rarefaction representation factor alpha
qand D
hq-bestsolve x
qat D
hq-besthigh-definition picture reconstruct fritter y under corresponding
q=D
hq-bestα
q;
7. according to step 4. ~ method 6., process by all image fritters of " it " font to low resolution characteristic image X', obtain initial high-resolution reconstruction image
8. to high-resolution reconstruction image
carry out block process and obtain final high-resolution reconstruction image Y.
2. the image super-resolution method of the online dictionary learning of a kind of self-adaptation according to claim 1, is characterized in that the concrete steps that 3. described step is optimized initial sub-dictionary set are as follows:
3.-1 couple of sub-dictionary D of low resolution
l1be optimized, concrete steps are:
A, suppose that the total iterations optimized is T, in the t time iteration, input any one the characteristic image block f in low resolution sample characteristics image
l, 1≤t≤T;
B, fix the sub-dictionary of target that t-1 iteration obtains
subspace back tracking method is used to solve
λ represents regularization coefficient and 0< λ <1, and wherein, argmin represents the minimum value solving functional, || || represent and solve norm, obtain characteristic image block f in the t time iteration
lat the sub-dictionary of target
under sparse decomposition coefficients Λ
t;
C, fixing sparse decomposition coefficients Λ
tif, the sub-dictionary D of low resolution
l1there is p atom, order
A
jrepresent A
tmiddle jth row, b
jrepresent B
tmiddle jth row, a
jand b
jbe the matrix of p × 1,1≤j≤p;
D, establish the sub-dictionary D of low resolution
l1a jth atom of the corresponding sub-dictionary of target is d
j, to d
jbe optimized, then
represent the sub-dictionary D of low resolution
l1the sub-dictionary of the target upgraded, A
jjrepresent a
jthe value of middle jth row, max represents the maximal value of solved function;
E, upgrade low resolution sub-dictionary D according to steps d
l1p atom, complete the t time iteration, obtain the sub-dictionary D of low resolution
l1the sub-dictionary of target after the t time iteration
F, general
substitute into formula
Obtain the sub-dictionary of target that the t time circulation upgrades
G, the rest may be inferred, and completing input picture is characteristic image block f
ltime, the sub-dictionary D of low resolution
l1t iteration, obtain characteristic image block f
lthe sub-dictionary of target of corresponding optimization
Except f in h, successively input low resolution sample characteristics image
lother all characteristic image blocks in addition, the principle identical according to step a ~ g is trained, and completes the sub-dictionary D of initial low resolution
l1training, last is taken turns the sub-dictionary of updated target as the sub-dictionary D of initial low resolution
l1the sub-dictionary D of optimal objective
l1-best;
3.-2 use the sub-dictionary D of low resolution
l1the same principle be optimized is respectively to D
l2, D
l3..., D
lk, D
h1, D
h2, D
h3..., D
hkbe optimized, obtain D
l2, D
l3..., D
lk, D
h1, D
h2, D
h3..., D
hkthe corresponding sub-dictionary of optimal objective, finally obtains the sub-dictionary set of optimal objective
{(D
l1-best,D
h1-best),(D
l2-best,D
h2-best),(D
l3-best,D
h3-best),…,(D
lk-best,D
hk-best)}。
3. the image super-resolution method of the online dictionary learning of a kind of self-adaptation according to claim 1, is characterized in that going block disposal route to be get average to the pixel of lap after each iteration during described step 8..
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210535873.3A CN103020935B (en) | 2012-12-10 | 2012-12-10 | The image super-resolution method of the online dictionary learning of a kind of self-adaptation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210535873.3A CN103020935B (en) | 2012-12-10 | 2012-12-10 | The image super-resolution method of the online dictionary learning of a kind of self-adaptation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103020935A CN103020935A (en) | 2013-04-03 |
CN103020935B true CN103020935B (en) | 2015-09-02 |
Family
ID=47969502
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210535873.3A Expired - Fee Related CN103020935B (en) | 2012-12-10 | 2012-12-10 | The image super-resolution method of the online dictionary learning of a kind of self-adaptation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103020935B (en) |
Families Citing this family (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103356238B (en) * | 2013-04-11 | 2015-02-11 | 汕头大学 | High resolution ultrasonic imaging method |
CN103295196B (en) * | 2013-05-21 | 2015-09-30 | 西安电子科技大学 | Based on the image super-resolution rebuilding method of non local dictionary learning and biregular item |
CN103745437B (en) * | 2013-12-30 | 2016-08-17 | 华中科技大学 | A kind of method generating high-resolution cloud atlas based on low resolution weather nephogram |
CN103903240B (en) * | 2014-04-09 | 2016-11-02 | 西安电子科技大学 | Image super-resolution method based on multi output Least square support vector regression |
EP3191797B1 (en) * | 2014-09-10 | 2018-08-01 | Siemens Energy, Inc. | Gas turbine sensor failure detection utilizing a sparse coding methodology |
CN104574336B (en) * | 2015-01-19 | 2017-08-01 | 上海交通大学 | Super-resolution image reconstruction system based on adaptive sub- mould dictionary selection |
CN106157240B (en) * | 2015-04-22 | 2020-06-26 | 南京理工大学 | Remote sensing image super-resolution method based on dictionary learning |
CN105957092B (en) * | 2016-05-31 | 2018-10-30 | 福州大学 | Breast molybdenum target characteristics of image self study extracting method for computer-aided diagnosis |
WO2018027584A1 (en) * | 2016-08-09 | 2018-02-15 | 深圳大学 | Method and system for restoring image using target attribute assisted compression perception |
CN106792504A (en) * | 2016-11-16 | 2017-05-31 | 北华大学 | One kind is used to follow the trail of stolen communication terminal control system based on mobile terminal |
CN106815806B (en) * | 2016-12-20 | 2020-01-10 | 浙江工业大学 | Single image SR reconstruction method based on compressed sensing and SVR |
WO2018120043A1 (en) * | 2016-12-30 | 2018-07-05 | 华为技术有限公司 | Image reconstruction method and apparatus |
CN107239781B (en) * | 2017-05-03 | 2020-07-28 | 北京理工大学 | Hyperspectral reflectivity reconstruction method based on RGB image |
CN108154499B (en) * | 2017-12-08 | 2021-10-08 | 东华大学 | Woven fabric texture flaw detection method based on K-SVD learning dictionary |
CN108734675B (en) * | 2018-05-17 | 2021-09-28 | 西安电子科技大学 | Image restoration method based on mixed sparse prior model |
CN110097503B (en) * | 2019-04-12 | 2024-01-19 | 浙江师范大学 | Super-resolution method based on neighborhood regression |
Citations (2)
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 |
CN102629373A (en) * | 2012-02-27 | 2012-08-08 | 天津大学 | Super-resolution image acquisition method based on sparse representation theory |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070103595A1 (en) * | 2005-10-27 | 2007-05-10 | Yihong Gong | Video super-resolution using personalized dictionary |
-
2012
- 2012-12-10 CN CN201210535873.3A patent/CN103020935B/en not_active Expired - Fee Related
Patent Citations (2)
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 |
CN102629373A (en) * | 2012-02-27 | 2012-08-08 | 天津大学 | Super-resolution image acquisition method based on sparse representation theory |
Non-Patent Citations (1)
Title |
---|
过完备字典稀疏表示的云图超分辨率算法;金炜等;《遥感学报》;20120430;第16卷(第2期);280-285 * |
Also Published As
Publication number | Publication date |
---|---|
CN103020935A (en) | 2013-04-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103020935B (en) | The image super-resolution method of the online dictionary learning of a kind of self-adaptation | |
CN105931179B (en) | A kind of image super-resolution method and system of joint sparse expression and deep learning | |
CN101950365B (en) | Multi-task super-resolution image reconstruction method based on KSVD dictionary learning | |
CN111047515A (en) | Cavity convolution neural network image super-resolution reconstruction method based on attention mechanism | |
CN103472419B (en) | Magnetic resonance fast imaging method and system thereof | |
CN109919864A (en) | A kind of compression of images cognitive method based on sparse denoising autoencoder network | |
CN109783910B (en) | Structure optimization design method for accelerating by using generation countermeasure network | |
CN111275171B (en) | Small target detection method based on parameter sharing multi-scale super-division reconstruction | |
CN110245683B (en) | Residual error relation network construction method for less-sample target identification and application | |
CN107341776A (en) | Single frames super resolution ratio reconstruction method based on sparse coding and combinatorial mapping | |
CN109214989A (en) | Single image super resolution ratio reconstruction method based on Orientation Features prediction priori | |
CN105550649A (en) | Extremely low resolution human face recognition method and system based on unity coupling local constraint expression | |
CN105844635A (en) | Sparse representation depth image reconstruction algorithm based on structure dictionary | |
CN111833261A (en) | Image super-resolution restoration method for generating countermeasure network based on attention | |
CN109949217A (en) | Video super-resolution method for reconstructing based on residual error study and implicit motion compensation | |
CN111210382A (en) | Image processing method, image processing device, computer equipment and storage medium | |
Son et al. | SAUM: Symmetry-aware upsampling module for consistent point cloud completion | |
CN114138919A (en) | Seismic data reconstruction method based on non-local attention convolution neural network | |
CN111667412A (en) | Method and device for reconstructing image super-resolution based on cross learning network | |
CN104091364B (en) | Single-image super-resolution reconstruction method | |
CN114010180B (en) | Magnetic resonance rapid imaging method and device based on convolutional neural network | |
CN102930573B (en) | A kind of image rebuilding method based on the sparse model of two-dimension analysis and training dictionary thereof | |
CN114663880A (en) | Three-dimensional target detection method based on multi-level cross-modal self-attention mechanism | |
CN115984949B (en) | Low-quality face image recognition method and equipment with attention mechanism | |
CN113689382A (en) | Tumor postoperative life prediction method and system based on medical images and pathological images |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150902 Termination date: 20181210 |
|
CF01 | Termination of patent right due to non-payment of annual fee |