CN111325697B - Color image restoration method based on tensor eigen transformation - Google Patents

Color image restoration method based on tensor eigen transformation Download PDF

Info

Publication number
CN111325697B
CN111325697B CN202010144793.XA CN202010144793A CN111325697B CN 111325697 B CN111325697 B CN 111325697B CN 202010144793 A CN202010144793 A CN 202010144793A CN 111325697 B CN111325697 B CN 111325697B
Authority
CN
China
Prior art keywords
tensor
matrix
column
pixel
eigen
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.)
Active
Application number
CN202010144793.XA
Other languages
Chinese (zh)
Other versions
CN111325697A (en
Inventor
刘静
苏立玉
黄开宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian Jiaotong University
Original Assignee
Xian Jiaotong University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xian Jiaotong University filed Critical Xian Jiaotong University
Priority to CN202010144793.XA priority Critical patent/CN111325697B/en
Publication of CN111325697A publication Critical patent/CN111325697A/en
Application granted granted Critical
Publication of CN111325697B publication Critical patent/CN111325697B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/77Retouching; Inpainting; Scratch removal
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10024Color image
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20048Transform domain processing
    • G06T2207/20056Discrete and fast Fourier transform, [DFT, FFT]

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a color image restoration method based on tensor eigen transformation, which utilizes designed tensor eigen transformation to directly obtain the structural characteristics of an image to be restored and better reserve the internal association between image pixels. The image restoration method is better in the aspect of keeping the internal relation of the pixels, so that the method can restore the detailed characteristics of the damaged pixels and can be used for restoring the damaged natural color images.

Description

Color image restoration method based on tensor eigen transformation
[ technical field ] A
The invention belongs to the technical field of image processing, and relates to a color image restoration method based on tensor eigen transformation.
[ background ] A method for producing a semiconductor device
In the modern society, in the era of data explosion, the development of computer technology is promoted by data collection and processing, however, unlike the past, in the era of big data, the collected data has a more complex structure, and the data can be well characterized by using a high-dimensional multi-linear structure. In the receiving and transmitting process of data, the obtained data is likely to be partially damaged due to environmental interference, and even if the data is received and transmitted under ideal conditions, it is desirable to compress the data to improve the utilization rate of resources. Based on the low rank matrix completion model, we can adopt fewer samples to mine possible values of other unknown samples, and this technique has been applied to various recommendation systems. In real life, if an attempt is made to mine an unknown sample, the influence factors are likely to be more, and therefore, the efficiency of solving the unknown sample by using the matrix is not high. The tensor is a high-dimensional multi-linear structure which can well reflect the internal connection between high-order data. On the basis of a low-rank matrix completion model, the low-rank tensor completion model is widely applied to the fields of computer vision, machine learning, data mining, neuroscience and the like.
Image processing is an important direction of research in computer vision, where image inpainting techniques aim to recover with a high probability damaged pixel values in an image. Under a low-rank tensor completion model, a color image can be represented as a third-order tensor, and how to mine the low-rank property of the tensor becomes an important problem of color image completion. The low rank property of the tensor is generally defined by various tensor decomposition methods, and currently, the common tensor decomposition methods include: 1) TUCKER Decomposition method 2) CANDECOMP-PARAFAC (CP) Decomposition method 3) Tensor column Decomposition method (sensor Train Decomposition) 4) Tensor Singular Value Decomposition method (sensor Singular Value Decomposition) and the like. LIU et al (the article is named as tension Completion for Estimating Missing Values in Visual Data) utilizes a TUCKER decomposition method to respectively expand tensors into mode matrixes according to different modes, and utilizes the rank of the mode matrixes to define the low rank of original tensors, but the method has great relevance damage to the Data in the original tensors. Under the definition of the CP decomposition method, the problem of NP difficulty in Tensor resolution is solved, and the CP rank of the Bayesian factor estimation Tensor is introduced by ZHAO et al (the article is named Bayesian Robust test factor Factorization for incorporated Multi way Data), so that the low rank of the original Tensor is defined, but the complexity of the calculation process of the method is high. Bengua et al (thesis entitled Efficient Tensor composition for Color Image and Video Recovery) defines a new Tensor generating matrix method by using traditional Tensor column decomposition, and further excavates the low-rank property of the original Tensor according to the rank of the generating matrix under the new method. ZHANG et al (article titled Novel Methods for Multilinear Data Completion and De-noised base on sensor-SVD) defines TUBAL rank of Tensor Based on Tensor singular value decomposition method, and the method does not rely on Tensor development, well preserves Data relevance of Tensor, but TUBAL rank has the possibility of large description error in describing Tensor low rank. LI (paper title is Low Rank document Completion with Total Variation for Visual Data Inpainting) and other people propose embedding a Total Variation method into a Tensor Completion process without the help of Tensor development to define Low Rank, but the principle process of the method is complex, and the applicability to the image with larger damage is not strong.
[ summary of the invention ]
The invention aims to solve the problems in the prior art and provides a color image restoration method based on tensor eigen transformation, which can better save the relevance among color pixels in color image restoration, thereby obtaining a clearer restoration result and achieving the effect that human eyes cannot easily perceive restoration traces.
In order to achieve the purpose, the invention adopts the following technical scheme to realize the purpose:
a color image restoration method based on tensor eigen transformation comprises the following steps:
step 1, obtaining damaged image, namely to-be-compensated tensor
Figure BDA0002400360220000031
Determining a set of all missing pixels corresponding to the damaged region
Figure BDA0002400360220000032
Setting preset parameters epsilon, beta, r e ,r c Setting remodeling parameters rho 12 Determining a set error requirement and a maximum iteration requirement;
step 2, obtaining the full tensor to be compensated by utilizing the tensor eigen transformation tau
Figure BDA0002400360220000033
The corresponding eigen-matrix E, noted:
Figure BDA0002400360220000034
step 3, using a threshold operator D ε,β Updating the intrinsic matrix E in the step 2, and recording the updated intrinsic matrix as E n
E n =D ε,β (E)
Step 4, introducing auxiliary tensor
Figure BDA0002400360220000035
Using inverse tensor eigentransformations τ -1 Determining an updated eigen matrix E n Corresponding tensor
Figure BDA0002400360220000036
Recording as follows:
Figure BDA0002400360220000037
step 5, determining the update tensor
Figure BDA0002400360220000038
If the update tensor pixel exists in the pixel damaged area
Figure BDA0002400360220000039
Order to
Figure BDA00024003602200000310
If the update tensor pixel is not in the pixel damage area
Figure BDA00024003602200000311
Order to
Figure BDA00024003602200000312
Step 6, judging the relative error
Figure BDA00024003602200000313
Whether the set error requirement is met or not, or whether the iteration frequency reaches the maximum iteration requirement or not; if the error requirement or the maximum iteration requirement is met, outputting the latest tensor
Figure BDA00024003602200000314
Namely the repaired image; otherwise make
Figure BDA00024003602200000315
And returning to the step 2 to enter an iterative loop.
The invention further improves the following steps:
in step 1, a set of all missing pixels corresponding to the damaged area is determined
Figure BDA00024003602200000316
The specific method comprises the following steps:
step 1.1, reading all pixel points of an image to be restored, enabling all the points with pixel values not being 0 to be known pixel points, and recording the positions of the known pixel points as a set omega;
step 1.2, all the points with the pixel values of 0 are made to be unknown pixel points, and the position set of the unknown pixel points is recorded to be
Figure BDA0002400360220000041
In the step 2, the tensor to be compensated is obtained by utilizing the tensor eigen transformation tau
Figure BDA0002400360220000042
The specific method of the corresponding eigen matrix E is as follows:
step 2.1, using improved tensor column decomposition to complete tensor to be compensated
Figure BDA0002400360220000043
Decomposed into tensor column kernels
Figure BDA0002400360220000044
The concrete expression is as follows:
Figure BDA0002400360220000045
in the above-mentioned formula, the compound has the following structure,
Figure BDA0002400360220000046
representing the coordinate in the tensor to be complemented as (i) c ,j c ,k c ) The value of the pixel of (a) is,
Figure BDA0002400360220000047
indicating the amount of tension to be compensated
Figure BDA0002400360220000048
The tensor of the reshaped intermediate medium,
Figure BDA0002400360220000049
a b-th front tangent matrix representing an a-th tensor column core;
step 2.2, carrying out tensor singular value decomposition on one tensor column core in the step:
Figure BDA00024003602200000410
in the above equation, a tensor column kernel is decomposed into the form of the product of three tensors, where
Figure BDA00024003602200000411
Called f-diagonal tensor, taking initial value a =1;
step 2.3, in the Fourier domain, the tensor column in the previous step is centered
Figure BDA00024003602200000412
Corresponding f-diagonal tensor
Figure BDA00024003602200000413
The values in (1) are mapped into a matrix E according to coordinates, and the corresponding coordinate relationship is expressed as:
Figure BDA00024003602200000414
in the above formula, the first and second carbon atoms are,
Figure BDA00024003602200000415
representing tensor column kernels
Figure BDA00024003602200000416
F-diagonal tensor in Fourier domain, ζ denotes tensor column core pointer, ξ denotes eigenmatrix pointer, I a Representing the tensor of the intermediate medium to be complemented
Figure BDA00024003602200000417
The a-th dimension; the specific value of the tensor column core pointer zeta is zeta =1 when a =1 or a =3, and zeta = i in other cases; the specific values of the intrinsic matrix pointers are:
Figure BDA0002400360220000051
in the above formula, r e And r c Respectively representing the edge rank and the center rank in the tensor eigen transformation, wherein the edge rank is always set as r e =1;
Step 2.4, if a<3, taking the intermediate tensor to be compensated
Figure BDA0002400360220000052
A +1 th tensor column core of
Figure BDA0002400360220000053
I.e. let a = a +1, return to step 2.3 and enter iteration, otherwise determine tensor
Figure BDA0002400360220000054
The eigenmatrix of (a) is E.
The specific method of the improved tensor column decomposition is as follows:
step 2.1.1, first, the tensor corresponding to the color image is calculated
Figure BDA0002400360220000055
Remodel into
Figure BDA0002400360220000056
Wherein the setting parameter p is utilized 12 The remodeling relationship of (A) is that,
Figure BDA0002400360220000057
step 2.1.2, introducing an auxiliary temporary tensor
Figure BDA0002400360220000058
Order to
Figure BDA0002400360220000059
Tensor is expressed
Figure BDA00024003602200000510
Reshaped into a corresponding matrix
Figure BDA00024003602200000511
Step 2.1.3, remodeling the matrix obtained in the step 2.1.2
Figure BDA00024003602200000512
Decomposition according to matrix singular values:
C=U·S·V T (5)
wherein, the first and the second end of the pipe are connected with each other,
Figure BDA00024003602200000513
respectively called left and right singular matrices of the matrix C,
Figure BDA00024003602200000514
is a diagonal matrix;
step 2.1.4, get matrix
Figure BDA00024003602200000515
Front r of c The columns form a new matrix
Figure BDA00024003602200000516
Get matrix
Figure BDA00024003602200000517
Front r of c Column forming a new matrix
Figure BDA00024003602200000518
Get matrix
Figure BDA00024003602200000519
Front r of c Row and r c Columns forming a new matrix
Figure BDA00024003602200000520
Step 2.1.5, matrix
Figure BDA00024003602200000521
Remodelling into first volumetric core
Figure BDA00024003602200000522
Determining updated matrices
Figure BDA00024003602200000523
Step 2.1.6, matrix
Figure BDA00024003602200000524
Remolding into a new matrix
Figure BDA00024003602200000525
And is obtained according to the singular value decomposition of the matrix, i.e. the decomposition in equation (5)
Figure BDA00024003602200000526
Get matrix
Figure BDA00024003602200000527
Front r of c Column forming a new matrix
Figure BDA0002400360220000061
Get matrix
Figure BDA0002400360220000062
Front r of c The columns form a new matrix
Figure BDA0002400360220000063
Get matrix
Figure BDA0002400360220000064
Front r of (2) c Row and r c Columns forming a new matrix
Figure BDA0002400360220000065
Step 2.1.7, matrix
Figure BDA0002400360220000066
Reshaping to a second tensor column core
Figure BDA0002400360220000067
Determining updated matrices
Figure BDA0002400360220000068
C is to be d Remodeled to a third tensor column core
Figure BDA0002400360220000069
In step 3, the specific method of tensor singular value decomposition is as follows:
step 2.2.1, get a quantitative core
Figure BDA00024003602200000610
Performing three-dimensional Fourier transform to obtain tensor column core in corresponding Fourier domain
Figure BDA00024003602200000611
Taking an initial value s =1;
step 2.2.2, take tensor column core
Figure BDA00024003602200000612
And recording the matrix as the s-th front section matrix
Figure BDA00024003602200000613
Namely have
Figure BDA00024003602200000614
To pair
Figure BDA00024003602200000615
Performing singular value decomposition of the matrix to obtain left and right singular matrices thereof
Figure BDA00024003602200000616
And diagonal matrix
Figure BDA00024003602200000617
Namely that
Figure BDA00024003602200000618
Step 2.2.3, create tensor
Figure BDA00024003602200000619
Setting the initial value of the newly-built tensor to be 0, and setting the left and right singular matrixes in the previous step
Figure BDA00024003602200000620
And diagonal matrix
Figure BDA00024003602200000621
The s-th front tangent plane matrix given to the newly created tensor, i.e.
Figure BDA00024003602200000622
Step 2.2.4, if s<I 3 And (3) returning to the step 2.2.2 to enter a loop by making s = s +1, otherwise, determining three tensors
Figure BDA00024003602200000623
Step 2.2.5, for
Figure BDA00024003602200000624
Respectively carrying out three-dimensional inverse Fourier transform to obtain tensors of real number domain
Figure BDA00024003602200000625
To sum up, a tensor column core is obtained
Figure BDA00024003602200000626
Singular value decomposition, i.e. having
Figure BDA00024003602200000627
The threshold operator D in step 3 ε,β The concrete expression is as follows:
Figure BDA00024003602200000628
where sign (x) is a sign function, parameter c 0 ,c 1 ,c 2 Comprises the following steps:
Figure BDA0002400360220000071
wherein epsilon and beta are preset parameters input in advance, and a symbol D is defined ε,β (X) represents the thresholding operation on all elements in matrix X.
In said step 4, the inverse tensor eigen-transform τ -1 The specific method comprises the following steps:
step 4.1, in the Fourier domain, a tensor eigen transformation method is adopted, and a plurality of corresponding tensor column cores are obtained through calculation of the eigen matrix E
Figure BDA0002400360220000072
F-diagonal tensor of
Figure BDA0002400360220000073
Taking an initial value a =1;
step 4.2, mixing
Figure BDA0002400360220000074
Is obtained by inverse Fourier transform
Figure BDA0002400360220000075
From the f-diagonal tensor in the real domain
Figure BDA0002400360220000076
And corresponding left and right singular tensors
Figure BDA0002400360220000077
Calculating to obtain tensor column core
Figure BDA0002400360220000078
Figure BDA0002400360220000079
In the above formula, the symbol "+" represents the tensor product;
step 4.3, if a<3, the a +1 f-diagonal tensor is taken
Figure BDA00024003602200000710
Making a = a +1, returning to the step 4.2 to enter iteration, and otherwise, entering the next step;
step 4.4, according to the obtained tensor column cores
Figure BDA00024003602200000711
Calculating to obtain the updated tensor corresponding to the intrinsic matrix E
Figure BDA00024003602200000712
Figure BDA00024003602200000713
In the above formula, subscripts i, j, k represent pixel points in tensor
Figure BDA00024003602200000714
The position in (1); will update the tensor
Figure BDA00024003602200000715
Reshaped into an original image
Figure BDA00024003602200000716
Tensor of equal size
Figure BDA00024003602200000717
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a novel tensor eigen-transformation, which is not subjected to any tensor development matrix to define the low rank of the tensor, but directly excavates the low rank of the tensor by decomposing the structural characteristics of the tensor. Compared with the prior art, the method has the advantages that based on tensor eigentransformation, the low-rank property of the tensor to be complemented can be solved in an iterative manner, and meanwhile, the relevance among tensor elements is greatly saved; in addition, under a low-rank tensor completion model, the proposed tensor eigen transformation recovers damaged pixels with higher probability by utilizing the relevance between known pixels and the damaged pixels, and the method is better at exploring the tensor internal relation, so that a more accurate repaired image can be obtained, and the effect that the repaired trace is not easily distinguished in the aspect of image detail repair can be achieved.
[ description of the drawings ]
Fig. 1 is a flowchart of a color image restoration method based on tensor eigen transformation according to the present invention;
FIG. 2 is a diagram of a color image defect area according to the present invention
Figure BDA0002400360220000081
And a schematic diagram of a known region Ω, wherein the black region is used to illustrate the damaged missing region;
FIG. 3 is a schematic diagram of the tensor eigen-transform of the present invention;
fig. 4 is a comparison graph of the application effect of the present invention and the prior art, which shows the original image of a color image, a damaged image and an image repaired by each method, and the repaired image has a relative error of recovery attached.
[ detailed description ] embodiments
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments, and are not intended to limit the scope of the present disclosure. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Various structural schematics according to the disclosed embodiments of the invention are shown in the drawings. The figures are not drawn to scale, wherein certain details are exaggerated and some details may be omitted for clarity of presentation. The shapes of the various regions, layers and their relative sizes, positional relationships are shown in the drawings as examples only, and in practice deviations due to manufacturing tolerances or technical limitations are possible, and a person skilled in the art may additionally design regions/layers with different shapes, sizes, relative positions, according to the actual needs.
In the context of the present disclosure, when a layer/element is referred to as being "on" another layer/element, it can be directly on the other layer/element or intervening layers/elements may be present. In addition, if a layer/element is "on" another layer/element in one orientation, then that layer/element may be "under" the other layer/element when the orientation is reversed.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The invention is described in further detail below with reference to the accompanying drawings:
in the prior art, the relation between known and unknown pixels cannot be utilized to the maximum extent, various generating modes are generally adopted when low rank is defined, the relevance among the pixels is greatly damaged, and the recovered image has certain distortion in visual effect. Therefore, we propose tensor eigen transformation to overcome the defect, as shown in fig. 1, in an embodiment of the present invention, a tensor eigen transformation-based color image restoration method does not need to define the low rank property of the original tensor by means of a tensor matrix-generating approach, directly obtains the low rank property of the original tensor by using the inherent structural features of the tensor eigen transformation, greatly utilizes and saves the inherent correlation between pixels of the color image, overcomes the defect of insufficient storage of pixel correlation in the prior art, and makes the restored color image more accurate and have greater generalization.
Referring to fig. 1, the color image restoration method based on tensor eigen transformation of the present invention includes the following steps:
step 1, obtaining damaged image (i.e. to-be-compensated tensor)
Figure BDA0002400360220000101
) With a pixel of 256, i.e. corresponding to the dimension of the tensor to be compensated
Figure BDA0002400360220000102
Determining a set of all missing pixels corresponding to the damaged region
Figure BDA0002400360220000103
Setting proper preset parameters epsilon, beta and r c Wherein the edge rank of the tensor eigen-transform is always set to r e =1; setting remodeling parameters rho 12 Determining a set error requirement and a maximum iteration requirement; in this embodiment, the parameters are set to e =0.3, β =100 c =20; remodeling parameter ρ 1 =4,ρ 2 =4, the maximum number of iterations is 500, and the error requirement is less than 1 × 10 -3 The missing pixel ratio is set to 70%, i.e. 70% of the color image pixels are missing or damaged;
as shown in FIG. 2, to identify the pixel positions to be repaired, a set of all missing pixels corresponding to the damaged area is first determined
Figure BDA0002400360220000104
The concrete setting is as follows:
step 1.1, reading all pixel points of an image to be restored, enabling all the points with pixel values not being 0 to be known pixel points, and recording the positions of the known pixel points as a set omega;
step 1.2, all the points with the pixel values of 0 are made to be unknown pixel points, and the position set of the unknown pixel points is recorded to be
Figure BDA0002400360220000105
Step 2, obtaining the tensor to be compensated by utilizing the tensor eigen transformation tau
Figure BDA0002400360220000106
The corresponding eigen-matrix E, denoted
Figure BDA0002400360220000107
As shown in FIG. 3, the method uses tensor eigen transformation tau to obtain the tensor to be compensated
Figure BDA0002400360220000108
The corresponding intrinsic matrix E specifically comprises the following steps:
step 2.1, the tensor to be compensated is decomposed by using the improved tensor column
Figure BDA0002400360220000109
Decomposed into tensor column kernels
Figure BDA00024003602200001010
The concrete expression is as follows:
Figure BDA00024003602200001011
in the above-mentioned formula, the compound has the following structure,
Figure BDA0002400360220000111
representing the coordinate in the tensor to be complemented as (i) c ,j c ,k c ) The value of the pixel of (a) is,
Figure BDA0002400360220000112
indicating the amount of tension to be compensated
Figure BDA0002400360220000113
The tensor of the reshaped intermediate medium,
Figure BDA0002400360220000114
a b-th Frontal Slice matrix (front Slice) representing an a-th Tensor column Core (sensor Train Core);
specifically, the improved tensor column decomposition described in the tensor eigentransform has the following steps:
step 2.1.1, in order to ensure the reconstruction precision, firstly, the tensor corresponding to the color image
Figure BDA0002400360220000115
Remodel into
Figure BDA0002400360220000116
Wherein use is made of a set parameter p 12 The re-shaping relationship of (1) is that,
Figure BDA0002400360220000117
step 2.1.2, introduce the auxiliary temporary tensor
Figure BDA0002400360220000118
Order to
Figure BDA0002400360220000119
Will tensor
Figure BDA00024003602200001110
Reshaped into a corresponding matrix
Figure BDA00024003602200001111
Step 2.1.3, remodeling the matrix obtained in the step 2.1.2
Figure BDA00024003602200001112
The matrix singular value decomposition can be specifically expressed as:
C=U·S·V T (2)
wherein
Figure BDA00024003602200001113
Left and right singular matrices referred to as matrix C respectively,
Figure BDA00024003602200001114
is a diagonal matrix;
step 2.1.4, get matrix
Figure BDA00024003602200001115
Front r of (2) c The columns form a new matrix
Figure BDA00024003602200001116
Get matrix
Figure BDA00024003602200001117
Front r of c The columns form a new matrix
Figure BDA00024003602200001118
Get matrix
Figure BDA00024003602200001119
Front r of (2) c Row and r c Columns forming a new matrix
Figure BDA00024003602200001120
Step 2.1.5, matrix
Figure BDA00024003602200001121
Remodelling into first volumetric core
Figure BDA00024003602200001122
Determining updated matrices
Figure BDA00024003602200001123
Step 2.1.6, matrix
Figure BDA00024003602200001124
Remolding into a new matrix
Figure BDA00024003602200001125
And is obtained according to the singular value decomposition of the matrix, i.e. the decomposition in equation (2)
Figure BDA00024003602200001126
Get matrix
Figure BDA00024003602200001127
Front r of (2) c Column forming a new matrix
Figure BDA00024003602200001128
Get matrix
Figure BDA00024003602200001129
Front r of c Column forming a new matrix
Figure BDA00024003602200001130
Get matrix
Figure BDA0002400360220000121
Front r of c Row and r c Columns forming a new matrix
Figure BDA0002400360220000122
Step 2.1.7, matrix
Figure BDA0002400360220000123
Reshaping to a second tensor column core
Figure BDA0002400360220000124
Determining updated matrices
Figure BDA0002400360220000125
C is to be d Remoulds intoCore of three tensor columns
Figure BDA0002400360220000126
Step 2.2, carrying out tensor singular value decomposition on one tensor column core in the step, wherein the tensor singular value decomposition is specifically represented as follows:
Figure BDA0002400360220000127
in the above equation, a tensor column kernel is decomposed into the form of the product of three tensors, where
Figure BDA0002400360220000128
Called f-diagonal Tensor (f-diagonal Tensor), taking the initial value a =1;
the tensor singular value decomposition in the tensor eigentransformation specifically comprises the following steps:
step 2.2.1, get a quantitative core
Figure BDA0002400360220000129
Performing three-dimensional Fourier transform to obtain tensor column core in corresponding Fourier domain
Figure BDA00024003602200001210
Taking an initial value s =1;
step 2.2.2, get tensor column core
Figure BDA00024003602200001211
And recording the matrix as the s-th front section matrix
Figure BDA00024003602200001212
Namely have
Figure BDA00024003602200001213
For is to
Figure BDA00024003602200001214
Performing singular value decomposition of the matrix to obtain left and right singular matrices thereof
Figure BDA00024003602200001215
And diagonal matrix
Figure BDA00024003602200001216
Namely that
Figure BDA00024003602200001217
Step 2.2.3 creating tensors
Figure BDA00024003602200001218
Setting the initial value of the newly-built tensor to be 0, and setting the left and right singular matrixes in the previous step
Figure BDA00024003602200001219
And diagonal matrix
Figure BDA00024003602200001220
The s-th front tangent plane matrix given to the newly created tensor, i.e.
Figure BDA00024003602200001221
Step 2.2.4, if s<I 3 Let s = s +1, return to step 2.2.2 to enter a loop, otherwise determine the three tensors
Figure BDA00024003602200001222
Step 2.2.5, for
Figure BDA00024003602200001223
Respectively carrying out three-dimensional inverse Fourier transform to obtain tensors of real number domain
Figure BDA00024003602200001224
To sum up, a tensor column core is obtained
Figure BDA00024003602200001225
Singular value decomposition, i.e. having
Figure BDA00024003602200001226
Step 2.3, in the Fourier domain, the tensor column in the previous step is centered
Figure BDA00024003602200001227
Corresponding f-diagonal tensor
Figure BDA00024003602200001228
The values in (1) are mapped into a matrix E according to coordinates, and the corresponding coordinate relationship can be expressed as:
Figure BDA0002400360220000131
in the above formula, the first and second carbon atoms are,
Figure BDA0002400360220000132
representing tensor column core
Figure BDA0002400360220000133
F-diagonal tensor in the Fourier domain, ζ denotes the tensor column core pointer, ξ denotes the eigenmatrix pointer, I a Representing the tensor of the intermediate medium to be complemented
Figure BDA0002400360220000134
The a-th dimension; the specific value of the tensor column core pointer zeta is zeta =1 when a =1 or a =3, and zeta = i in other cases; the specific value of the intrinsic matrix pointer is
Figure BDA0002400360220000135
In the above formula, r e And r c Respectively representing the edge rank and the center rank in the tensor eigen transformation, wherein the edge rank of the method is always set as r e =1;
Step 2.4, if a<3, taking the intermediate tensor to be compensated
Figure BDA0002400360220000136
A +1 st tensor column core of
Figure BDA0002400360220000137
I.e. let a = a +1, return to step 2.3 and enter iteration, otherwise determine tensor
Figure BDA0002400360220000138
The eigenmatrix of (a) is E.
Step 3, using a threshold operator D ε,β Updating the intrinsic matrix E in the step 2, and recording the updated intrinsic matrix as E n I.e. E n =D ε,β (E);
The threshold operator D described in this step ε,β The method specifically comprises the following steps:
Figure BDA0002400360220000139
where sign (x) is a sign function, parameter c 0 ,c 1 ,c 2 Is required to be determined as
Figure BDA00024003602200001310
Epsilon and beta are preset parameters input in advance, and a symbol D is defined ε,β (X) represents the thresholding operation performed on all elements in matrix X.
Step 4, introducing auxiliary tensor
Figure BDA0002400360220000141
Using inverse tensor eigentransformations tau -1 Determining an updated eigen matrix E n Corresponding tensor
Figure BDA0002400360220000142
Record as
Figure BDA0002400360220000143
Inverse tensor eigentransform τ in this step -1 Is the inverse process of the tensor eigen-transform tau, it is emphasized that the inverse tensor eigen-transform tau -1 Subject to τ, otherwise τ -1 Will become meaningless; inverse tensor eigentransform τ -1 The method comprises the following specific steps:
step 4.1, in the Fourier domain, referring to the tensor eigen transformation method in the formulas (4) and (5), calculating the corresponding tensor column cores by the eigen matrix E
Figure BDA0002400360220000144
F-diagonal tensor of
Figure BDA0002400360220000145
Taking an initial value a =1;
step 4.2, mixing
Figure BDA0002400360220000146
Is obtained by inverse Fourier transform
Figure BDA0002400360220000147
From the f-diagonal tensor in the real domain
Figure BDA0002400360220000148
And corresponding left and right singular tensors
Figure BDA0002400360220000149
Calculating to obtain tensor column core
Figure BDA00024003602200001410
The expression is as follows:
Figure BDA00024003602200001411
the symbol "+" in the above formula represents the tensor product;
step 4.3, if a<3, the a +1 f-diagonal tensor is taken
Figure BDA00024003602200001412
I.e. let a = a +1, return to step 4.2 to enter iteration, otherwise enter the next step.
Step 4.4, according to the obtained plurality of tensor column cores
Figure BDA00024003602200001413
Calculating to obtain the updated tensor corresponding to the intrinsic matrix E
Figure BDA00024003602200001414
The concrete expression is as follows:
Figure BDA00024003602200001415
subscript i, j, k in the above formula represents the tensor of the pixel point
Figure BDA00024003602200001416
The position of (1); in addition, the tensor will be updated
Figure BDA00024003602200001417
Reshaped into an original image
Figure BDA00024003602200001418
Tensor of equal size
Figure BDA00024003602200001419
Step 5, determining the update tensor
Figure BDA00024003602200001420
If the update tensor pixel exists in the pixel damaged area
Figure BDA00024003602200001421
Order to
Figure BDA00024003602200001422
If the update tensor pixel is not in the pixel damage area
Figure BDA00024003602200001423
Order to
Figure BDA00024003602200001424
Step 6, judging relative error
Figure BDA00024003602200001425
Whether the set error requirement is met or not, or whether the iteration frequency reaches the maximum iteration requirement or not; if the error requirement or the maximum iteration requirement is met, outputting the latest tensor
Figure BDA0002400360220000151
(i.e., the repaired image), otherwise let
Figure BDA0002400360220000152
And returning to the step 2 to enter an iterative loop.
As shown in fig. 4, the present embodiment recovers the color image by a tensor eigen transformation-based color image recovery method, and the recovery effect of the recovered image is still better even under an extremely high damage rate, i.e., 70% of the pixels are damaged, and compared with the original image, an accurate recovery result is obtained. For comparison, a low-rank tensor total variation method and a tensor nuclear norm method are respectively set according to default algorithms; the relative error of the recovery of the method of the invention is 10.2%, which is superior to 12.6% and 12.8% of the prior art, and the recovery result of the prior art is visually seen to have errors in brightness and detail. The experimental results show that the method provided by the invention has better performance no matter in objective index evaluation or subjective visual effect.
In the embodiment, the low rank property is defined without any method for expanding the tensor into the matrix, but the proposed tensor eigen transformation is directly utilized to form the framework, so that the low rank property of the tensor can be iteratively obtained under the framework, and meanwhile, the relevance among pixels is ensured and an effective recovery image is obtained.
With reference to this embodiment, an algorithm of a color image restoration method based on tensor eigen transformation is given as follows:
inputting: spoiled colour images
Figure BDA0002400360220000153
Suitable preset parameters epsilon, beta, r c Wherein r is e =1; setting remodeling parameters rho 12 Determining a set error requirement tol and a maximum iteration requirement K;
step 1, initializing a damaged color image
Figure BDA0002400360220000154
Initializing iteration parameter i =1, initializing relative error
Figure BDA0002400360220000155
Step 2, judging whether the maximum iteration requirement or the specified error requirement is met, if i is less than or equal to K or error i >tol proceeds to the next step, otherwise let
Figure BDA0002400360220000156
And terminate the algorithm;
step 3, obtaining tensor based on the eigentransformation of tensor
Figure BDA0002400360220000157
The eigen matrix E of (a);
step 4, updating the intrinsic matrix E through formulas (6) and (7) to obtain E n
Step 5, obtaining an updated eigen matrix E based on the inverse eigen transformation of the tensor n Corresponding tensor of
Figure BDA0002400360220000158
And step 6, updating the damaged color image,
Figure BDA0002400360220000161
obtaining the color image restored in this step
Figure BDA0002400360220000162
Calculating the relative error of the iteration
Figure BDA0002400360220000163
Step 7, enabling the iteration parameter i = i +1; update the damaged color image
Figure BDA0002400360220000164
And returning to the step 2;
and (3) outputting: repairing color images
Figure BDA0002400360220000165
The parameters and related mathematical symbols involved in the algorithm are the same as the partial parameters and symbols in the invention, so that repeated definition of the parameters and the mathematical symbols is avoided.
The color image restoration method based on tensor eigen transformation comprises the steps of firstly reading a damaged color image, identifying and defining a set of known pixels and unknown pixels, and creating a premise for restoring the image by utilizing internal relevance between the known pixels and the unknown pixels; in addition, based on the proposed tensor eigentransformation, corresponding tensor low-rank performance is mined directly according to the structure of the color image, the method greatly preserves pixel relevance, and damaged pixels can be repaired iteratively through simple transformation under the framework of tensor eigentransformation, so that missing pixels can be recovered more accurately.
In this embodiment, a computer device is provided, which may be a terminal. The computing device generally includes a processor, a memory, a network interface, and an input-output device. The processor of the computer device provides computing support for the method of the invention; the memorizer provides a built-in operating system, a running environment of the program and a stored computer program for the method; the network interface provides network connection and communication exchange functions for the method; the input device is used for inputting an image to be restored, and may be a keyboard, a mouse or the like; the output device is used for presenting the repaired image, and may be specifically a display screen or the like. More specifically, the software platform of the present embodiment uses MATLAB R2015a; the hardware platform uses INTEL CORE CPU and memory 4GB; the experimental method is the method, the low-rank tensor total variation method and the tensor nuclear norm method.
The above-mentioned contents are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modification made on the basis of the technical idea of the present invention falls within the protection scope of the claims of the present invention.

Claims (3)

1. A color image restoration method based on tensor eigen transformation is characterized by comprising the following steps:
step 1, obtaining damaged image, namely to-be-compensated tensor
Figure FDA0003746501930000011
Determining a set omega of all missing pixels corresponding to the damaged region Setting preset parameters epsilon, beta and r e ,r c Setting remodeling parameters rho 12 Determining a set error requirement and a maximum iteration requirement;
step 2, obtaining the full tensor to be compensated by utilizing the tensor eigen transformation tau
Figure FDA0003746501930000012
The corresponding eigen-matrix E, noted:
Figure FDA0003746501930000013
the specific method comprises the following steps:
step 2.1, using improved tensor column decomposition to complete tensor to be compensated
Figure FDA0003746501930000014
Decomposed into tensor column kernels
Figure FDA0003746501930000015
The concrete expression is as follows:
Figure FDA0003746501930000016
in the above formula, the first and second carbon atoms are,
Figure FDA0003746501930000017
representing the coordinate in the tensor to be complemented as (i) c ,j c ,k c ) The value of the pixel of (a) is,
Figure FDA0003746501930000018
indicating the amount of tension to be compensated
Figure FDA0003746501930000019
The tensor of the reshaped intermediate medium,
Figure FDA00037465019300000110
a b-th front tangent matrix representing an a-th tensor column core;
the specific method of the improved tensor column decomposition is as follows:
step 2.1.1, first, the tensor corresponding to the color image
Figure FDA00037465019300000111
Is reshaped into
Figure FDA00037465019300000112
Wherein the setting parameter p is utilized 12 The remodeling relationship of (A) is that,
Figure FDA00037465019300000113
step 2.1.2, introduce the auxiliary temporary tensor
Figure FDA00037465019300000114
Order to
Figure FDA00037465019300000115
Will tensor
Figure FDA00037465019300000116
Reshaped into a corresponding matrix
Figure FDA00037465019300000117
Step 2.1.3, remodeling the matrix obtained in the step 2.1.2
Figure FDA00037465019300000118
Decomposition according to matrix singular values:
C=U·S·V T (4)
wherein, the first and the second end of the pipe are connected with each other,
Figure FDA00037465019300000119
left and right singular matrices referred to as matrix C respectively,
Figure FDA0003746501930000021
is a diagonal matrix;
step 2.1.4, get matrix
Figure FDA0003746501930000022
Front r of c The columns form a new matrix
Figure FDA0003746501930000023
Get matrix
Figure FDA0003746501930000024
Front r of (2) c The columns form a new matrix
Figure FDA0003746501930000025
Get matrix
Figure FDA0003746501930000026
Front r of c Row and r c Columns forming a new matrix
Figure FDA0003746501930000027
Step 2.1.5, matrix
Figure FDA0003746501930000028
Remodelling into first volumetric core
Figure FDA0003746501930000029
Determining updated matrices
Figure FDA00037465019300000210
Step 2.1.6, matrix
Figure FDA00037465019300000211
Remolding into a new matrix
Figure FDA00037465019300000212
And is obtained according to the singular value decomposition of the matrix, i.e. the decomposition in equation (5)
Figure FDA00037465019300000213
Get matrix
Figure FDA00037465019300000214
Front r of c Column forming a new matrix
Figure FDA00037465019300000215
Get matrix
Figure FDA00037465019300000216
Front r of (2) c The columns form a new matrix
Figure FDA00037465019300000217
Get matrix
Figure FDA00037465019300000218
Front r of (2) c Row and r c Columns forming a new matrix
Figure FDA00037465019300000219
Step 2.1.7, matrix
Figure FDA00037465019300000220
Remodeled to a second tensor column core
Figure FDA00037465019300000221
Determining updated matrices
Figure FDA00037465019300000222
Will C d Reshaping to a third tensor column core
Figure FDA00037465019300000223
Step 2.2, carrying out tensor singular value decomposition on one tensor column core in the step:
Figure FDA00037465019300000224
in the above equation, a tensor column core is decomposed into the form of the product of three tensors, where
Figure FDA00037465019300000225
Called f-diagonal tensor, taking initial value a =1;
the specific method of tensor singular value decomposition is as follows:
step 2.2.1, get a quantitative core
Figure FDA00037465019300000226
Performing three-dimensional Fourier transform to obtain tensor column core in corresponding Fourier domain
Figure FDA00037465019300000227
Taking an initial value s =1;
step 2.2.2, get tensor column core
Figure FDA00037465019300000228
Of (2) and recording the matrix as the s-th front section matrix
Figure FDA00037465019300000229
Namely have
Figure FDA00037465019300000230
To pair
Figure FDA00037465019300000231
Performing singular value decomposition of the matrix to obtain left and right singular matrices thereof
Figure FDA00037465019300000232
And diagonal matrix
Figure FDA00037465019300000233
Namely, it is
Figure FDA00037465019300000234
Step 2.2.3, create tensor
Figure FDA0003746501930000031
Setting the initial value of the newly-built tensor to be 0, and setting the left and right singular matrixes in the previous step
Figure FDA0003746501930000032
And diagonal matrix
Figure FDA0003746501930000033
The s-th front tangent matrix to the newly created tensor, i.e.
Figure FDA0003746501930000034
Step 2.2.4, if s is less than I 3 Let s = s +1, return to step 2.2.2 to enter a loop, otherwise determine the three tensors
Figure FDA0003746501930000035
Step 2.2.5, for
Figure FDA0003746501930000036
Respectively carrying out three-dimensional inverse Fourier transform to obtain tensors of real number domain
Figure FDA0003746501930000037
To sum up, a tensor column core is obtained
Figure FDA0003746501930000038
Singular value decomposition of, i.e. having
Figure FDA0003746501930000039
Step 2.3, in the Fourier domain, the tensor column in the previous step is centered
Figure FDA00037465019300000310
Corresponding f-diagonal tensor
Figure FDA00037465019300000311
The values in (b) are mapped into a matrix E according to coordinates, and the corresponding coordinate relationship is expressed as:
Figure FDA00037465019300000312
in the above formula, the first and second carbon atoms are,
Figure FDA00037465019300000313
representing tensor column kernelsHeart with heart-shaped
Figure FDA00037465019300000314
F-diagonal tensor in the Fourier domain, ζ denotes the tensor column core pointer, ξ denotes the eigenmatrix pointer, I a Representing the tensor of the intermediate to be complemented
Figure FDA00037465019300000315
The a-th dimension; the specific value of the tensor column core pointer zeta is zeta =1 when a =1 or a =3, and zeta = i in other cases; the specific values of the eigen matrix pointers are:
Figure FDA00037465019300000316
in the above formula, r e And r c Respectively representing the edge rank and the center rank in the tensor eigen transformation, wherein the edge rank needs to be always set as r e =1;
Step 2.4, if a is less than 3, the intermediate tensor to be compensated is taken
Figure FDA00037465019300000317
A +1 th tensor column core of
Figure FDA00037465019300000318
I.e. let a = a +1, return to step 2.3 and enter iteration, otherwise determine tensor
Figure FDA00037465019300000319
The intrinsic matrix of (a) is E;
step 3, using a threshold operator D ε,β Updating the intrinsic matrix E in the step 2, and recording the updated intrinsic matrix as E n
E n =D ε,β (E)
Step 4, introducing auxiliary tensor
Figure FDA0003746501930000041
Using inverse tensor eigentransformations tau -1 Determining an updated eigen matrix E n Corresponding tensor
Figure FDA0003746501930000042
Recording as follows:
Figure FDA0003746501930000043
inverse tensor eigentransform τ -1 The specific method comprises the following steps:
step 4.1, in the Fourier domain, a tensor eigen transformation method is adopted, and a plurality of corresponding tensor column cores are obtained through calculation of the eigen matrix E
Figure FDA0003746501930000044
F-diagonal tensor of
Figure FDA0003746501930000045
Taking an initial value a =1;
step 4.2, mixing
Figure FDA0003746501930000046
Is subjected to inverse Fourier transform to obtain
Figure FDA0003746501930000047
From the f-diagonal tensor in the real domain
Figure FDA0003746501930000048
And corresponding left and right singular tensors
Figure FDA0003746501930000049
Calculating to obtain tensor column core
Figure FDA00037465019300000410
Figure FDA00037465019300000411
In the above formula, the symbol "+" represents the tensor product;
step 4.3, if a is less than 3, the a +1 f-diagonal tensor is taken
Figure FDA00037465019300000412
If a = a +1, returning to the step 4.2 to enter iteration, otherwise, entering the next step;
step 4.4, according to the obtained tensor column cores
Figure FDA00037465019300000413
Calculating to obtain the updated tensor corresponding to the intrinsic matrix E
Figure FDA00037465019300000414
Figure FDA00037465019300000415
In the above formula, subscript i, j, k represents the tensor of the pixel point
Figure FDA00037465019300000416
The position in (1); will update the tensor
Figure FDA00037465019300000417
Reshaped into an original image
Figure FDA00037465019300000418
Tensor of equal size
Figure FDA00037465019300000419
Step 5, determining the update tensor
Figure FDA00037465019300000420
If the update tensor pixel exists in the pixel damaged area omega Let us order
Figure FDA00037465019300000421
If the update tensor pixel is not in the pixel damaged area omega Let us order
Figure FDA00037465019300000422
Step 6, judging relative error
Figure FDA00037465019300000423
Whether the set error requirement is met or not, or whether the iteration frequency reaches the maximum iteration requirement or not; if the error requirement or the maximum iteration requirement is met, outputting the latest tensor
Figure FDA0003746501930000051
Namely the repaired image; otherwise make the instruction
Figure FDA0003746501930000052
And returning to the step 2 to enter an iterative loop.
2. The tensor eigentransform-based color image restoration method according to claim 1, wherein in step 1, a set Ω of all missing pixels corresponding to a damaged area is determined The specific method comprises the following steps:
step 1.1, reading all pixel points of an image to be restored, enabling all the points with pixel values not being 0 to be known pixel points, and recording the positions of the known pixel points as a set omega;
step 1.2, all the points with the pixel value of 0 are set as unknown pixel points, and the position set of the unknown pixel points is recorded to be omega
3. The tensor eigentransform-based color image restoration method according to claim 1, characterized in that the threshold operator D in step 3 ε,β The concrete expression is as follows:
Figure FDA0003746501930000053
where sign (x) is a sign function, parameter c 0 ,c 1 ,c 2 Comprises the following steps:
Figure FDA0003746501930000054
wherein epsilon and beta are preset parameters input in advance, and a symbol D is defined ε,β (X) represents the thresholding operation performed on all elements in matrix X.
CN202010144793.XA 2020-03-04 2020-03-04 Color image restoration method based on tensor eigen transformation Active CN111325697B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010144793.XA CN111325697B (en) 2020-03-04 2020-03-04 Color image restoration method based on tensor eigen transformation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010144793.XA CN111325697B (en) 2020-03-04 2020-03-04 Color image restoration method based on tensor eigen transformation

Publications (2)

Publication Number Publication Date
CN111325697A CN111325697A (en) 2020-06-23
CN111325697B true CN111325697B (en) 2022-10-25

Family

ID=71173085

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010144793.XA Active CN111325697B (en) 2020-03-04 2020-03-04 Color image restoration method based on tensor eigen transformation

Country Status (1)

Country Link
CN (1) CN111325697B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112241938B (en) * 2020-08-21 2024-02-13 浙江工业大学 Image restoration method based on smooth Tak decomposition and high-order tensor Hakking
CN112381725B (en) * 2020-10-16 2024-02-02 广东工业大学 Image restoration method and device based on depth convolution countermeasure generation network
CN114119426B (en) * 2022-01-26 2022-07-01 之江实验室 Image reconstruction method and device by non-local low-rank conversion domain and full-connection tensor decomposition

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107392107A (en) * 2017-06-24 2017-11-24 天津大学 A kind of face feature extraction method based on isomery tensor resolution
CN109886884A (en) * 2019-01-21 2019-06-14 长沙理工大学 A kind of vision data complementing method based on the low-rank tensor estimation for limiting nuclear norm

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7369699B1 (en) * 2003-08-29 2008-05-06 Apple Inc. Methods and apparatuses for restoring color and enhancing electronic images
JP6327922B2 (en) * 2014-04-25 2018-05-23 キヤノン株式会社 Image processing apparatus, image processing method, and program
CN107016649A (en) * 2017-02-24 2017-08-04 同济大学 A kind of vision data complementing method estimated based on local low-rank tensor
CN109241491A (en) * 2018-07-28 2019-01-18 天津大学 The structural missing fill method of tensor based on joint low-rank and rarefaction representation
CN109191404B (en) * 2018-09-07 2020-06-26 西安交通大学 Hyperspectral image restoration method based on E-3DTV regularization
CN109978783A (en) * 2019-03-19 2019-07-05 上海交通大学 A kind of color image restorative procedure
CN110298798B (en) * 2019-06-20 2021-02-19 浙江工业大学 Image restoration method based on low-rank tensor completion and discrete total variation

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107392107A (en) * 2017-06-24 2017-11-24 天津大学 A kind of face feature extraction method based on isomery tensor resolution
CN109886884A (en) * 2019-01-21 2019-06-14 长沙理工大学 A kind of vision data complementing method based on the low-rank tensor estimation for limiting nuclear norm

Also Published As

Publication number Publication date
CN111325697A (en) 2020-06-23

Similar Documents

Publication Publication Date Title
Zhang et al. Nonlocal low-rank tensor completion for visual data
CN110298798B (en) Image restoration method based on low-rank tensor completion and discrete total variation
CN111325697B (en) Color image restoration method based on tensor eigen transformation
Wang et al. Haze concentration adaptive network for image dehazing
CN112115783A (en) Human face characteristic point detection method, device and equipment based on deep knowledge migration
CN113240596A (en) Color video recovery method and system based on high-order tensor singular value decomposition
Cao et al. New architecture of deep recursive convolution networks for super-resolution
CN112184547B (en) Super resolution method of infrared image and computer readable storage medium
Muhammad et al. Multi-scale Xception based depthwise separable convolution for single image super-resolution
Ding et al. Tensor completion via nonconvex tensor ring rank minimization with guaranteed convergence
Wang et al. End-to-end trainable network for superpixel and image segmentation
Shao et al. Generative image inpainting with salient prior and relative total variation
Wang et al. Joint depth map super-resolution method via deep hybrid-cross guidance filter
Xu et al. Image compressive sensing recovery via group residual based nonlocal low-rank regularization
CN109902720B (en) Image classification and identification method for depth feature estimation based on subspace decomposition
CN115147426B (en) Model training and image segmentation method and system based on semi-supervised learning
CN116778164A (en) Semantic segmentation method for improving deep V &lt; 3+ &gt; network based on multi-scale structure
Wei et al. 3D face image inpainting with generative adversarial nets
CN116258877A (en) Land utilization scene similarity change detection method, device, medium and equipment
Guo et al. Blind single-image-based thin cloud removal using a cloud perception integrated fast Fourier convolutional network
Yang et al. Face inpainting via learnable structure knowledge of fusion network
Meng et al. Siamese CNN-based rank learning for quality assessment of inpainted images
Ye et al. A sparsity-promoting image decomposition model for depth recovery
Huan et al. Remote sensing image reconstruction using an asymmetric multi-scale super-resolution network
CN113763313A (en) Text image quality detection method, device, medium and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant