CN103208109A - Local restriction iteration neighborhood embedding-based face hallucination method - Google Patents

Local restriction iteration neighborhood embedding-based face hallucination method Download PDF

Info

Publication number
CN103208109A
CN103208109A CN2013101476203A CN201310147620A CN103208109A CN 103208109 A CN103208109 A CN 103208109A CN 2013101476203 A CN2013101476203 A CN 2013101476203A CN 201310147620 A CN201310147620 A CN 201310147620A CN 103208109 A CN103208109 A CN 103208109A
Authority
CN
China
Prior art keywords
image
resolution
definition picture
piece
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.)
Granted
Application number
CN2013101476203A
Other languages
Chinese (zh)
Other versions
CN103208109B (en
Inventor
胡瑞敏
江俊君
董小慧
韩镇
陈军
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.)
Wuhan University WHU
Original Assignee
Wuhan University WHU
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 Wuhan University WHU filed Critical Wuhan University WHU
Priority to CN201310147620.3A priority Critical patent/CN103208109B/en
Publication of CN103208109A publication Critical patent/CN103208109A/en
Application granted granted Critical
Publication of CN103208109B publication Critical patent/CN103208109B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Image Processing (AREA)

Abstract

The invention relates to a local restriction iteration neighborhood embedding-based face hallucination method. The method comprises the following steps of: establishing high-resolution and low-resolution image block sets to be used as high-resolution and low-resolution image block dictionaries; sampling on inputted image blocks of a low-resolution face image to obtain estimation high-resolution image blocks, seeking K nearest image blocks at the corresponding position in the high-resolution image block dictionary, and expressing the inputted low-resolution image blocks by using the corresponding K low-resolution image blocks to acquire a weight coefficient; reconstructing K neighbor high-resolution image blocks by utilizing the weight coefficient to form new estimation high-resolution image blocks, and performing the operation repeatedly until the most satisfied estimation high-resolution image blocks are obtained; and integrating into a high-resolution image according to the positional relations of the low-resolution image blocks. According to the method, two manifold structures are considered simultaneously on the basis of position apriority and local manifold restriction, and K neighbor points and reconstruction weights are updated continuously in an iteration form on the basis of a result of last reconstruction to achieve a high-quality reconstruction effect which is close to the real condition.

Description

A kind of unreal structure method of people's face that embeds based on local restriction iteration neighborhood
Technical field
The present invention relates to the image super-resolution field, be specifically related to a kind of unreal structure method of people's face that embeds based on local restriction iteration neighborhood.
Background technology
In in the past 20 years, face recognition technology has obtained development rapidly.Simultaneously because video monitoring system has the network bandwidth limited, restrictions such as server stores cause the face-image resolution that photographs low, make that people's face information that can provide is very limited, and this becomes in the biological identification technology one of challenging problem of tool.Recently, super-resolution technique has been used to handle low resolution (Low-Resolution, LR) image, it can provide more high resolving power (High-Resolution, HR) image of multiaspect portion details for follow-up identification process from a sequence of low resolution pictures or energy of single frames low-resolution image generation.
Baker in 2000 and Kanade are at document 1(S.Baker and T.Kanade.Hallucinating faces.In FG, Grenoble, France, Mar.2000,83-88.) in the method for the unreal structure of a kind of people's face (face hallucination) has been proposed, utilize the prior imformation of facial image in the training set, obtain the high-resolution human face image of low resolution facial image correspondence by the method for study.This is the initiative work of the unreal structure technical field of people's face.After this, many diverse ways and model are introduced into, wherein the most representative technology is that people such as Chang are at document 2(H.Chang, D.Yeung, and Y.Xiong.Super-resolution through neighbor embedding[A] .In Proc.IEEE CVPR ' 04[C] .Washington, 2004.275 – 282.) the middle a kind of method based on manifold learning that proposes, they suppose that the high-definition picture piece has identical local geometry with the low-resolution image piece, and then (locally linear embedding LLE) learns the corresponding relation that high low-resolution image piece flows shape to utilize local linear the embedding.Human face analysis studies show that with the correlation theory of synthesizing, the positional information of facial image human face analysis with synthetic in extremely important, inspired by this, people such as Ma are at document 3(X.Ma, J.P Zhang, and C.Qi.Hallucinating face by position-patch.Pattern Recognition, 43 (6): 3178 – 3194,2010.) and document 4(X.Ma, J.Zhang, and C.Qi, " Position-based face hallucination method, " in Proc.IEEE Conf.on Multimedia and Expo (ICME), 2009, pp.290 – 293.) proposed a kind of unreal structure method of people's face of position-based piece in, it is synthetic that the image block of the given low resolution facial image position image block by all same positions in the training set facial image is carried out linearity.Yet because this method adopts least square method to find the solution, when the number of image in the training sample was bigger than the dimension of image block, the expression coefficient of image block was not unique.For this reason, people such as Jung were at document 5(C.Jung in 2011, L.Jiao, B.Liu, and M.Gong, " Position-Patch Based Face Hallucination Using Convex Optimization; " IEEE Signal Process.Lett., vol.18, no.6, pp.367 – 370,2011.) utilize sparse regularization method to obtain the optimal reconstruction weight of the unreal structure of people's face in.Recently, patent 1(Hu Ruimin, Jiang Junjun, Wang Bing, Han Zhen, Huang Kebin, Lu Tao, Wang Yimin, a kind of human face super-resolution method for reconstructing of representing based on local restriction, number of patent application: the unreal structure method of people's face of further having improved the position-based piece 201110421452.3), image block being carried out retrain the sparse constraint of having replaced in the document 5 with the local geometric that flows shape in the process of reconstruction, make reconstructed results have sparse property and locality simultaneously.Up to the present, the unreal structure method of people's face represented of this local restriction is effect the best way.
No matter be to use rarefaction representation or local restriction, above mentioned method all is by exploring rational priori, seeking the most representative image block and obtain optimal weights and carry out the unreal structure of people's face.Therefore, how to seek rational K neighbour's sample image piece and to obtain optimal weights be two links of most critical in the unreal structure technology of people's face.Above-mentioned all methods have all only been considered low-resolution image piece stream shape, and have ignored the geometry information of high-definition picture piece, make reconstructed results lack reliability and identification.
Summary of the invention
The object of the invention is to provide a kind of unreal structure method of people's face that embeds based on local restriction iteration neighborhood.Utilize whole training sample image piece as dictionary, considered the local geometry feature of low resolution manifold structure and high resolving power manifold structure simultaneously, remedied the deficiency of in the past only considering a certain manifold structure, through iterative step repeatedly, make and rebuild effect further near the original high resolution image simultaneously.
For achieving the above object, the technical solution used in the present invention is a kind of unreal structure method of people's face that embeds based on local restriction iteration neighborhood, comprises the steps:
Step 1, low resolution facial image to input carries out up-sampling and obtains estimating the high-resolution human face image, to the low resolution facial image of input, estimate all low resolution people face sample images in high-resolution human face image, the low resolution training set and all the high-resolution human face sample images in the high resolving power training set are divided overlapped image block respectively;
Step 2 for each image block in the low resolution facial image of input, is carried out following steps and is obtained reconstruct high-definition picture piece,
Step 2.1 is got the image block of each low resolution people face sample image relevant position in the low resolution training set as sample point, sets up low resolution people face sample block space; Get the image block of each high-resolution human face sample image relevant position in the high resolving power training set as sample point, set up high-resolution human face sample block space; Get the image block of estimating high-resolution human face image relevant position, obtain estimating the high-definition picture piece;
Step 2.2, calculate the current K of reconstruct high-definition picture piece on high-resolution human face sample block space of last iteration gained nearest image block, seek K the image block of this K image block in low resolution people face sample block space, adopt during execution in step 2.2 step 2.1 gained to estimate the high-definition picture piece as current reconstruct high-definition picture piece first; And utilize K image block in the low resolution people face sample block space that the low-resolution image piece of importing is carried out linear reconstruction, obtain optimum weights coefficient; Utilize K image block on optimum weights coefficient and the high-resolution human face sample block space, linear reconstruction obtains the reconstruct high-definition picture piece of this iteration; K is default value;
Step 2.3, the reconstruct high-definition picture piece current according to step 2.2 gained returns repeating step 2.2, reaches the value that sets in advance up to iterations;
Step 3 divides other corresponding reconstruct high-definition picture piece to superpose according to the position all images piece in the low resolution facial image of input, divided by the overlapping number of times of each location of pixels, reconstructs the high-resolution human face image then.
And, establish the low resolution facial image X to input tDividing gained image block collection is
Figure BDA00003105196300031
Estimate high-resolution human face image Y t(0) dividing gained image block collection is
Figure BDA00003105196300037
All high-resolution human face sample images in the high resolving power training set are divided respectively obtain high-definition picture piece collection Y={y Ij| 1≤i≤N, 1≤j≤M} divides respectively all low resolution people face sample images in the low resolution training set and to obtain low-resolution image piece collection X={x Ij| 1≤i≤N, 1≤j≤M}; Wherein, sign i represents the sequence number of low resolution people face sample image in the sequence number of high resolving power training set middle high-resolution people face sample image and the low resolution training set, piece position number on the sign j presentation video;
Figure BDA00003105196300032
Be to estimate high-resolution human face image Y t(1) image block at position j place,
Figure BDA00003105196300033
Be the low resolution facial image X of input tThe image block at j place, position; y IjBe that i opens the image block at j place, picture position in the high resolving power training set, x IjBe that i opens the image block at j place, picture position in the low resolution training set; The number of the number of low resolution people face sample image and high resolving power training set middle high-resolution people face sample image all is designated as N in the low resolution training set, and M is the piece number of every width of cloth image partitioned image piece;
In the step 2, to arbitrary image block in the low resolution facial image of input
Figure BDA00003105196300038
Carry out following substep,
Step 2.1, the initial value that makes iterations p is 1; Image block to the arbitrary position in the low resolution facial image of input
Figure BDA00003105196300039
Set up low resolution people face sample block space X j={ x Ij| 1≤i≤N} sets up high-resolution human face sample block space Y as low-resolution image piece dictionary j={ y Ij| 1≤i≤N} seeks the relevant position and estimates the high-definition picture piece as high-definition picture piece dictionary
Figure BDA00003105196300034
Wherein { y j t ( 1 ) = Bicubic ( x j t ) | 1 ≤ j ≤ M } ;
Step 2.2, the reconstruct high-definition picture piece that execution in step 2.2 obtains when utilizing last iteration calculates the reconstruct high-definition picture piece of this iteration, comprises following substep:
Step 2.2.1 is according to current reconstruct high-definition picture piece
Figure BDA00003105196300036
Calculate the high-definition picture piece dictionary Y with the relevant position j={ y Ij| the distance of each image block among 1≤i≤N}, and it is as follows to seek K minimum image block of distance,
dist ( p ) = | | y j t ( p ) - y ij | | 2 , i = 1 , · · · , N
N K ( y j t ( p ) ) = support ( dist | K )
Wherein, dist (p) ∈ R N, dist (p) expression reconstruct high-definition picture piece
Figure BDA00003105196300043
With each image block y in the high-definition picture piece dictionary IjDistance, R NExpression N dimension real number space; Dist| KK value of minimum among the expression dist (p),
Figure BDA00003105196300044
It is current high-definition picture piece Index set with K image block of high-definition picture piece dictionary middle distance minimum;
For the first time during execution in step 2.2.1, current reconstruct high-definition picture piece
Figure BDA00003105196300046
The high-definition picture piece is estimated in employing
Figure BDA00003105196300047
Afterwards during execution in step 2.2.1, current reconstruct high-definition picture piece
Figure BDA00003105196300048
The reconstruct high-definition picture piece that execution in step 2.2.3 obtains during for last iteration;
Step 2.2.2 seeks the set of step 2.2.1 gained
Figure BDA00003105196300049
Middle K image block y kCorrespondence image piece x in low-resolution image piece dictionary respectively k, and to image block
Figure BDA000031051963000410
Carry out linear reconstruction, obtain optimum weights coefficient
Figure BDA000031051963000411
As shown in the formula,
Figure BDA000031051963000412
Wherein,
Figure BDA000031051963000413
Return the value about function w (p) when obtaining minimum value of weights coefficient w (p), w k(p) corresponding x among the expression weights coefficient w (p) kComponent, τ is the regularization parameter that balance is rebuild the sum of errors local restriction;
Step 2.2.3 rebuilds the reconstruct high-definition picture piece of this iteration by following formula,
y j t ( p + 1 ) = Σ y k ∈ N K ( y j t ( p ) ) w ^ k ( p ) y k
Wherein,
Figure BDA000031051963000415
It is the optimum weights coefficient of step 2.2.2 gained
Figure BDA000031051963000416
Middle correspondence image piece y kComponent;
Step 2.3 is judged whether iterations reaches the value that sets in advance, otherwise is made p=p+1, carries out next iteration according to returning repeating step 2.2 at step 2.2.3 gained reconstruct high-definition picture piece in this iteration; Be with in this iteration in the reconstruct high-definition picture piece of step 2.2.3 gained reconstruct high-definition picture piece as final gained, finishing iteration.
A kind of unreal structure method of people's face that embeds based on local restriction iteration neighborhood that the present invention proposes, only considered the method for the manifold structure of low-resolution image before being different from, increased the constraint of high-definition picture manifold structure to reconstructed coefficients, when disclosing high low resolution people's face stream shape space immanent structure similarity, also utilized the essential difference in two kinds of stream shape spaces, made reconstructed results have stronger identification; Method by iteration is constantly upgraded rebuilding weight and neighbour point, selects more can represent neighbour's point and the reconstructed coefficients of target high-definition picture piece, finally obtains the high-definition picture more approaching with truth.This method has been improved traditional neighborhood embedding grammar, makes the expression coefficient of input picture piece more accurate, finally obtains higher-quality high-resolution human face image.
Description of drawings
Fig. 1 is the process flow diagram of the embodiment of the invention.
Embodiment
Technical solution of the present invention can adopt software engineering to realize the automatic flow operation.Below in conjunction with drawings and Examples technical solution of the present invention is further described.Referring to Fig. 1, embodiment of the invention concrete steps are as follows:
Step 1, low resolution facial image to input carries out initialization, be that the Bicubic up-sampling obtains estimating the high-resolution human face image, to the low resolution facial image of input, estimate all low resolution people face sample images in high-resolution human face image, the low resolution training set and all the high-resolution human face sample images in the high resolving power training set are divided overlapped image block in the same way;
Low resolution training set and high resolving power training set provide predefined training sample right, comprise low resolution people face sample image in the low resolution training set, comprise the high-resolution human face sample image in the high resolving power training set.Among the embodiment, all high-resolution human face sample images are the facial image (manual alignment eyes or face position in advance) through the alignment registration, and pixel size is 112 * 100.Each low resolution people face sample image is obtained with 4 * 4 smothing filterings and 4 times of down-samplings by a high-resolution human face sample image in the high resolving power training set in the low resolution training set, and the low-resolution image pixel size is 28 * 25.Accordingly, the low resolution facial image pixel size of input is 28 * 25, also can be in advance and people's face aligned in position registration of high-resolution human face sample image, and estimating the high-resolution human face image pixel size is 112 * 100.Overlapping division belongs to this area common technology, and when specifically implementing, those skilled in the art can specify the overlaid pixel size.The embodiment unification is decided to be 12 * 12 with all high-resolution human face sample images and the high-definition picture block size of estimating the high-resolution human face image, the overlaid pixel value is made as 4, the low-resolution image block size of the low resolution facial image of all low resolution people face sample images and input is 3 * 3, and the overlaid pixel value is 1.
Among the embodiment, to the low resolution facial image X of input tDividing the image block collection that constitutes behind the overlapped image block is
Figure BDA00003105196300051
M is the image block number.Input low resolution facial image is carried out the Bicubic up-sampling, obtain estimating high-resolution human face image Y t(1)=Bicubic (X t), it is divided with identical method obtain behind the overlapped image block estimating high-resolution human face image block collection with low-resolution image piece set pair is answered
Figure BDA00003105196300052
Obtain high-definition picture piece collection Y={y after people's face sample image in the high-resolution and low-resolution training set divided overlapped image block respectively with identical method Ij| 1≤i≤N, 1≤j≤M} and low-resolution image piece collection X={x Ij| 1≤i≤N, 1≤j≤M}, wherein, sign i represents the sequence number of low resolution people face sample image in the sequence number of high resolving power training set middle high-resolution people face sample image and the low resolution training set, sign j represents the piece position number on every image. Be to estimate high-resolution human face image Y t(1) image block at position j place,
Figure BDA00003105196300062
Be the low resolution facial image X of input tThe image block at j place, position, y Ij, x IjBe respectively that i opens the image block at j place, picture position in the high-resolution and low-resolution training set, the number of the number of low resolution people face sample image and high resolving power training set middle high-resolution people face sample image all is designated as N in the low resolution training set, and M is the piece number of every width of cloth image partitioned image piece;
Step 2 is for arbitrary image block in the low resolution facial image of input
Figure BDA00003105196300063
Carry out following substep and obtain corresponding reconstruct high-definition picture piece:
Step 2.1, get the image block of each low resolution people face sample image relevant position in the low resolution training set as sample point, set up low resolution people face sample block space, get the image block of each high-resolution human face sample image relevant position in the high resolving power training set as sample point, set up high-resolution human face sample block space, get the image block of estimating high-resolution human face image relevant position, the high-definition picture piece that obtains estimating; The initial value that makes iterations p is 1;
Among the embodiment, to certain the position image block in the low resolution facial image of input Set up low resolution people face sample block space X j={ x Ij| 1≤i≤N} is as low-resolution image piece dictionary, high-resolution human face sample block space Y j={ y Ij| 1≤i≤N} seeks the relevant position and estimates the high-definition picture piece as high-definition picture piece dictionary
Figure BDA00003105196300065
Wherein { y j t ( 1 ) = Bicubic ( x j t ) | 1 ≤ j ≤ M } ;
Step 2.2, the reconstruct high-definition picture piece that execution in step 2.2 obtains when utilizing last iteration calculates this iterative target of its correspondence, i.e. and the reconstruct high-definition picture piece of this iteration comprises following substep:
Step 2.2.1 is according to current reconstruct high-definition picture piece Calculate the high-definition picture piece dictionary Y of itself and relevant position j={ y Ij| the distance of each image block among 1≤i≤N}, and seek K image block of its middle distance minimum, i.e. K arest neighbors, method is as follows,
dist ( p ) = | | y j t ( p ) - y ij | | 2 , i = 1 , · · · , N
N K ( y j t ( p ) ) = support ( dist | K )
Wherein, dist (p) ∈ R N, dist (p) expression reconstruct high-definition picture piece With each image block y in the high-definition picture piece dictionary IjDistance, R NExpression N dimension real number space; Dist| KK value of minimum among the expression dist (p), || || 2Represent two norms,
Figure BDA000031051963000611
It is current reconstruct high-definition picture piece
Figure BDA000031051963000612
With the index set of K image block of high-definition picture piece dictionary middle distance minimum, p is current iterations.K can be by those skilled in the art's default value, and in the present embodiment, K is made as 150.
For the first time during execution in step 2.2.1, current reconstruct high-definition picture piece
Figure BDA00003105196300071
Employing is to the image block of input picture
Figure BDA00003105196300072
What obtain estimates high-resolution human face image Y t(0) the corresponding high-definition picture piece of estimating in
Figure BDA00003105196300073
Afterwards during execution in step 2.2.1, current reconstruct high-definition picture piece
Figure BDA00003105196300074
The reconstruct high-definition picture piece that execution in step 2.2.3 obtains when being last iteration.
Step 2.2.2 seeks the set of step 2.2.1 gained
Figure BDA00003105196300075
Middle K high-resolution image block be the image block of corresponding low resolution in low-resolution image piece dictionary respectively, and utilizes them to image block
Figure BDA00003105196300076
Carry out linear reconstruction, obtain the optimum weights coefficient of reconstruct
Figure BDA00003105196300077
Method is as follows:
Figure BDA00003105196300078
Wherein, Return the value about function w (p) when obtaining minimum value of weights coefficient w (p), i.e. desired optimum weights coefficient
Figure BDA000031051963000710
x kBe one of K high-definition picture piece y kThe image block of corresponding low resolution, w k(p) corresponding x among the expression weights coefficient w (p) kComponent, the inner product operation between two vectors of " ο " expression,
Figure BDA000031051963000711
Expression is to two norms || || 2The result ask square, τ is the regularization parameter that balance is rebuild the sum of errors local restriction, τ suggestion value 1e-5.
Step 2.2.3 is obtaining optimum weights coefficient
Figure BDA000031051963000712
After, can rebuild the reconstruct high-definition picture piece of this iteration by following formula, i.e. new current reconstruct high-definition picture piece,
y j t ( p + 1 ) = Σ y k ∈ N K ( y j t ( p ) ) w ^ k ( p ) y k
Wherein,
Figure BDA000031051963000714
It is the optimum weights coefficient that execution in step 2.2.2 asks in this iteration
Figure BDA000031051963000715
Middle corresponding some high-resolution image block y kComponent.
Step 2.3 is judged whether iterations reaches the value that sets in advance, otherwise is made p=p+1, carries out next iteration according to returning repeating step 2.2 at step 2.2.3 gained reconstruct high-definition picture piece in this iteration; Be with in this iteration in the reconstruct high-definition picture piece of step 2.2.3 gained reconstruct high-definition picture piece as final gained, finishing iteration;
Step 3, the high-definition picture piece that all weightings are reconstructed superposes according to the position, divided by the overlapping number of times of each location of pixels, reconstructs the high-resolution human face image then.
Relate generally to three parameters in the embodiment of the invention, i.e. projection recently count K, regularization parameter τ and iterations.Experiment shows, when K gets 150, can obtain reconstruct effect preferably; When regularization parameter τ was between 1e-6~1e-3, our method can obtain stable performance, and is as far as possible little in order to guarantee reconstruction error simultaneously, parameter τ is decided to be 1e-5 obtains best effect; Along with the increase of iterations, experiment gained PSNR value also in continuous increase, when iterations increased all to a certain degree, PSNR value convergence was stable, the reduction computation complexity advises that iterations is decided to be 6 when obtaining best effects as far as possible.
In order to verify validity of the present invention, adopt extensive Chinese face database (the document 6:W.Gao of CAS-PEAL-R1, B.Cao, S.Shan, X.Chen, et al.The CAS-PEAL Large-Scale Chinese Face Database and Baseline Evaluations[J] .IEEE Trans.SMC (Part A), 2008,38 (1): 149-161) experimentize, select the neutrality expression of all 1040 individualities, the front face image under the normal illumination for use.Take human face region and it be cut into 112 * 100 pixels, more manual demarcate the people on the face five unique points (two centers, nose and two corners of the mouths) and carry out the affined transformation alignment, obtain original high-resolution human face image.The low resolution facial image by 4 times of Bicubic down-samplings of high-resolution human face image after again 4 times of Bicubic up-samplings obtain.Select 1000 at random as training sample, will remain 40 as test pattern.The reconstruct effect that we obtain the present invention and the overall face method (document 7 of Wang, X.Wang and X.Tang, " Hallucinating face by eigentransformation; " IEEE Trans.Systems, Man, and Cybernetics.Part C, vol.35, no.3, pp.425 – 434,2005.) and some methods based on the piece position compare, for example neighborhood embedding grammar (NE, document 2), least square method (LSR, document 3), rarefaction representation method (SR, document 5) and local constraint representation method (LcR, patent 1) etc.
Y-PSNR is adopted in experiment, and (Peak Signal to Noise Ratio PSNR) weighs the quality that contrasts algorithm, and SSIM then is the index of weighing two width of cloth figure similarities, and its value illustrates that more close to 1 the effect of image reconstruction is more good.Above method is handled mean P SNR and the SSIM value that obtains to whole 40 test patterns, overall face, and neighborhood embeds, least square, rarefaction representation, local restriction represent etc. that the mean P SNR value of method and the inventive method is followed successively by 26.53,27.90,28.17,28.27,28.84,29.33; Overall situation face, neighborhood embeds, least square, rarefaction representation, the average SSIM value of method such as local restriction and the inventive method is followed successively by 0.8247,0.8868,0.8975,0.8968,0.9083,0.9140.The inventive method improves 0.49 dB and 0.006 respectively than best algorithm (patent 1) in control methods on PSNR and SSIM value.This shows that the inventive method is compared than other existent method, effect has had significant raising.
Specific embodiment described herein only is that the present invention's spirit is illustrated.Those skilled in the art can make various modifications or replenish or adopt similar mode to substitute described specific embodiment, but can't depart from spirit of the present invention or surmount the defined scope of appended claims.

Claims (2)

1. the unreal structure method of people's face that embeds based on local restriction iteration neighborhood is characterized in that, comprises the steps:
Step 1, low resolution facial image to input carries out up-sampling and obtains estimating the high-resolution human face image, to the low resolution facial image of input, estimate all low resolution people face sample images in high-resolution human face image, the low resolution training set and all the high-resolution human face sample images in the high resolving power training set are divided overlapped image block respectively;
Step 2 for each image block in the low resolution facial image of input, is carried out following steps and is obtained reconstruct high-definition picture piece,
Step 2.1 is got the image block of each low resolution people face sample image relevant position in the low resolution training set as sample point, sets up low resolution people face sample block space; Get the image block of each high-resolution human face sample image relevant position in the high resolving power training set as sample point, set up high-resolution human face sample block space; Get the image block of estimating high-resolution human face image relevant position, obtain estimating the high-definition picture piece;
Step 2.2, calculate the current K of reconstruct high-definition picture piece on high-resolution human face sample block space of last iteration gained nearest image block, seek K the image block of this K image block in low resolution people face sample block space, adopt during execution in step 2.2 step 2.1 gained to estimate the high-definition picture piece as current reconstruct high-definition picture piece first; And utilize K image block in the low resolution people face sample block space that the low-resolution image piece of importing is carried out linear reconstruction, obtain optimum weights coefficient; Utilize K image block on optimum weights coefficient and the high-resolution human face sample block space, linear reconstruction obtains the reconstruct high-definition picture piece of this iteration; K is default value;
Step 2.3, the reconstruct high-definition picture piece current according to step 2.2 gained returns repeating step 2.2, reaches the value that sets in advance up to iterations;
Step 3 divides other corresponding reconstruct high-definition picture piece to superpose according to the position all images piece in the low resolution facial image of input, divided by the overlapping number of times of each location of pixels, reconstructs the high-resolution human face image then.
2. according to the described unreal structure method of people's face that embeds based on local restriction iteration neighborhood of claim 1, it is characterized in that:
If the low resolution facial image X to input tDividing gained image block collection is
Figure FDA00003105196200011
Estimate high-resolution human face image Y t(0) dividing gained image block collection is
Figure FDA00003105196200012
All high-resolution human face sample images in the high resolving power training set are divided respectively obtain high-definition picture piece collection Y={y Ij| 1≤i≤N, 1≤j≤M} divides respectively all low resolution people face sample images in the low resolution training set and to obtain low-resolution image piece collection X={x Ij| 1≤i≤N, 1≤j≤M}; Wherein, sign i represents the sequence number of low resolution people face sample image in the sequence number of high resolving power training set middle high-resolution people face sample image and the low resolution training set, piece position number on the sign j presentation video;
Figure FDA00003105196200021
Be to estimate high-resolution human face image Y t(1) image block at position j place,
Figure FDA00003105196200022
Be the low resolution facial image X of input tThe image block at j place, position; y IjBe that i opens the image block at j place, picture position in the high resolving power training set, x IjBe that i opens the image block at j place, picture position in the low resolution training set; The number of the number of low resolution people face sample image and high resolving power training set middle high-resolution people face sample image all is designated as N in the low resolution training set, and M is the piece number of every width of cloth image partitioned image piece;
In the step 2, to arbitrary image block in the low resolution facial image of input
Figure FDA000031051962000218
Carry out following substep,
Step 2.1, the initial value that makes iterations p is 1; Image block to the arbitrary position in the low resolution facial image of input
Figure FDA00003105196200023
Set up low resolution people face sample block space X j={ x Ij| 1≤i≤N} sets up high-resolution human face sample block space Y as low-resolution image piece dictionary j={ y Ij| 1≤i≤N} seeks the relevant position and estimates the high-definition picture piece as high-definition picture piece dictionary
Figure FDA00003105196200024
Wherein { y j t ( 1 ) = Bicubic ( x j t ) | 1 ≤ j ≤ M } ;
Step 2.2, the reconstruct high-definition picture piece that execution in step 2.2 obtains when utilizing last iteration calculates the reconstruct high-definition picture piece of this iteration, comprises following substep:
Step 2.2.1 is according to current reconstruct high-definition picture piece Calculate the high-definition picture piece dictionary Y with the relevant position j={ y Ij| the distance of each image block among 1≤i≤N}, and it is as follows to seek K minimum image block of distance,
dist ( p ) = | | y j t ( p ) - y ij | | 2 , i = 1 , · · · , N
N K ( y j t ( p ) ) = support ( dist | K )
Wherein, dist (p) ∈ R N, dist (p) expression reconstruct high-definition picture piece
Figure FDA00003105196200029
With each image block y in the high-definition picture piece dictionary IjDistance, R NExpression N dimension real number space; Dist| KK value of minimum among the expression dist (p), It is current high-definition picture piece
Figure FDA000031051962000211
Index set with K image block of high-definition picture piece dictionary middle distance minimum;
For the first time during execution in step 2.2.1, current reconstruct high-definition picture piece
Figure FDA000031051962000212
The high-definition picture piece is estimated in employing Afterwards during execution in step 2.2.1, current reconstruct high-definition picture piece
Figure FDA000031051962000214
The reconstruct high-definition picture piece that execution in step 2.2.3 obtains during for last iteration;
Step 2.2.2 seeks the set of step 2.2.1 gained
Figure FDA000031051962000215
Middle K image block y kCorrespondence image piece x in low-resolution image piece dictionary respectively k, and to image block
Figure FDA000031051962000216
Carry out linear reconstruction, obtain optimum weights coefficient
Figure FDA000031051962000217
As shown in the formula,
Wherein, Return the value about function w (p) when obtaining minimum value of weights coefficient w (p), w k(p) corresponding x among the expression weights coefficient w (p) kComponent, τ is the regularization parameter that balance is rebuild the sum of errors local restriction;
Step 2.2.3 rebuilds the reconstruct high-definition picture piece of this iteration by following formula,
y j t ( p + 1 ) = Σ y k ∈ N K ( y j t ( p ) ) w ^ k ( p ) y k
Wherein,
Figure FDA00003105196200034
It is the optimum weights coefficient of step 2.2.2 gained
Figure FDA00003105196200035
Middle correspondence image piece y kComponent;
Step 2.3 is judged whether iterations reaches the value that sets in advance, otherwise is made p=p+1, carries out next iteration according to returning repeating step 2.2 at step 2.2.3 gained reconstruct high-definition picture piece in this iteration; Be with in this iteration in the reconstruct high-definition picture piece of step 2.2.3 gained reconstruct high-definition picture piece as final gained, finishing iteration.
CN201310147620.3A 2013-04-25 2013-04-25 A kind of unreal structure method of face embedded based on local restriction iteration neighborhood Expired - Fee Related CN103208109B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310147620.3A CN103208109B (en) 2013-04-25 2013-04-25 A kind of unreal structure method of face embedded based on local restriction iteration neighborhood

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310147620.3A CN103208109B (en) 2013-04-25 2013-04-25 A kind of unreal structure method of face embedded based on local restriction iteration neighborhood

Publications (2)

Publication Number Publication Date
CN103208109A true CN103208109A (en) 2013-07-17
CN103208109B CN103208109B (en) 2015-09-16

Family

ID=48755326

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310147620.3A Expired - Fee Related CN103208109B (en) 2013-04-25 2013-04-25 A kind of unreal structure method of face embedded based on local restriction iteration neighborhood

Country Status (1)

Country Link
CN (1) CN103208109B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105469359A (en) * 2015-12-09 2016-04-06 武汉工程大学 Locality-constrained and low-rank representation based human face super-resolution reconstruction method
CN105550649A (en) * 2015-12-09 2016-05-04 武汉工程大学 Extremely low resolution human face recognition method and system based on unity coupling local constraint expression
CN106157274A (en) * 2015-04-01 2016-11-23 武汉大学 A kind of face unreal structure method embedded based on picture position block neighbour
CN106558018A (en) * 2015-09-25 2017-04-05 北京大学 The unreal structure method and device of video human face that Component- Based Development decomposes
CN106780318A (en) * 2015-11-25 2017-05-31 北京大学 The unreal structure method of face and the unreal construction system of face
WO2017177363A1 (en) * 2016-04-11 2017-10-19 Sensetime Group Limited Methods and apparatuses for face hallucination

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102402784A (en) * 2011-12-16 2012-04-04 武汉大学 Human face image super-resolution method based on nearest feature line manifold learning
CN102521810A (en) * 2011-12-16 2012-06-27 武汉大学 Face super-resolution reconstruction method based on local constraint representation

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102402784A (en) * 2011-12-16 2012-04-04 武汉大学 Human face image super-resolution method based on nearest feature line manifold learning
CN102521810A (en) * 2011-12-16 2012-06-27 武汉大学 Face super-resolution reconstruction method based on local constraint representation

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
BO LI 等: "Aligning Coupled Manifolds for Face Hallucination", 《2009 IEEE SIGNAL PROCESSING LETTERS》 *
HONG CHANG 等: "Super-Resolution Through Neighbor Embedding", 《2004 IEEE CVPR》 *
JUNJUN JIANG 等: "POSITION-PATCH BASED FACE HALLUCINATION VIA LOCALITY-CONSTRAINED REPRESENTATION", 《2012 IEEE ICME》 *
SUNG WON PARK,MARIOS SAVVIDES: "ROBUST SUPER-RESOLUTION OF FACE IMAGES BY ITERATIVE COMPENSATING NEIGHBORHOOD RELATIONSHIPS", 《2007 IEEE BIOMETRICS SUMPOSIUM》 *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106157274A (en) * 2015-04-01 2016-11-23 武汉大学 A kind of face unreal structure method embedded based on picture position block neighbour
CN106157274B (en) * 2015-04-01 2019-01-29 武汉大学 A kind of unreal structure method of face based on picture position block neighbour insertion
CN106558018A (en) * 2015-09-25 2017-04-05 北京大学 The unreal structure method and device of video human face that Component- Based Development decomposes
CN106558018B (en) * 2015-09-25 2019-08-06 北京大学 The unreal structure method and device of video human face that Component- Based Development decomposes
CN106780318A (en) * 2015-11-25 2017-05-31 北京大学 The unreal structure method of face and the unreal construction system of face
CN106780318B (en) * 2015-11-25 2020-07-14 北京大学 Face magic structure method and face magic structure system
CN105469359A (en) * 2015-12-09 2016-04-06 武汉工程大学 Locality-constrained and low-rank representation based human face super-resolution reconstruction method
CN105550649A (en) * 2015-12-09 2016-05-04 武汉工程大学 Extremely low resolution human face recognition method and system based on unity coupling local constraint expression
CN105469359B (en) * 2015-12-09 2019-05-03 武汉工程大学 Face super-resolution reconstruction method based on local restriction low-rank representation
WO2017177363A1 (en) * 2016-04-11 2017-10-19 Sensetime Group Limited Methods and apparatuses for face hallucination

Also Published As

Publication number Publication date
CN103208109B (en) 2015-09-16

Similar Documents

Publication Publication Date Title
Zhao et al. Discrete cosine transform network for guided depth map super-resolution
CN102354397B (en) Method for reconstructing human facial image super-resolution based on similarity of facial characteristic organs
CN114782691A (en) Robot target identification and motion detection method based on deep learning, storage medium and equipment
US20110170784A1 (en) Image registration processing apparatus, region expansion processing apparatus, and image quality improvement processing apparatus
CN103208109A (en) Local restriction iteration neighborhood embedding-based face hallucination method
CN106952228A (en) The super resolution ratio reconstruction method of single image based on the non local self-similarity of image
Tuzel et al. Global-local face upsampling network
Zhu et al. Neurreg: Neural registration and its application to image segmentation
Xin et al. Residual attribute attention network for face image super-resolution
CN104657962B (en) The Image Super-resolution Reconstruction method returned based on cascading linear
CN102136065B (en) Face super-resolution method based on convex optimization
CN111626927B (en) Binocular image super-resolution method, system and device adopting parallax constraint
WO2024021523A1 (en) Graph network-based method and system for fully automatic segmentation of cerebral cortex surface
CN106910215B (en) Super-resolution method based on fractional order gradient interpolation
CN105488759B (en) A kind of image super-resolution rebuilding method based on local regression model
CN114429555A (en) Image density matching method, system, equipment and storage medium from coarse to fine
CN104091320A (en) Noise human face super-resolution reconstruction method based on data-driven local feature conversion
Chen et al. Nonlinear neighbor embedding for single image super-resolution via kernel mapping
KR102543690B1 (en) Image Upscaling Apparatus And Method Based On Learning With Privileged Information
CN112101262A (en) Multi-feature fusion sign language recognition method and network model
CN104036482A (en) Facial image super-resolution method based on dictionary asymptotic updating
CN114049314A (en) Medical image segmentation method based on feature rearrangement and gated axial attention
Shi et al. Exploiting multi-scale parallel self-attention and local variation via dual-branch transformer-CNN structure for face super-resolution
CN110717978B (en) Three-dimensional head reconstruction method based on single image
Zheng et al. Multi-strategy mutual learning network for deformable medical image registration

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
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20150916