CN101697197A - Method for recognizing human face based on typical correlation analysis spatial super-resolution - Google Patents

Method for recognizing human face based on typical correlation analysis spatial super-resolution Download PDF

Info

Publication number
CN101697197A
CN101697197A CN200910207562A CN200910207562A CN101697197A CN 101697197 A CN101697197 A CN 101697197A CN 200910207562 A CN200910207562 A CN 200910207562A CN 200910207562 A CN200910207562 A CN 200910207562A CN 101697197 A CN101697197 A CN 101697197A
Authority
CN
China
Prior art keywords
resolution
image
low
recognition
recognition feature
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
CN200910207562A
Other languages
Chinese (zh)
Other versions
CN101697197B (en
Inventor
黄华
何惠婷
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 CN2009102075622A priority Critical patent/CN101697197B/en
Publication of CN101697197A publication Critical patent/CN101697197A/en
Application granted granted Critical
Publication of CN101697197B publication Critical patent/CN101697197B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a method for recognizing human face based on typical correlation analysis spatial super-resolution. Aiming at the problem of the low recognition efficiency of a low-resolution face image, the invention provides a method for obtaining the recognition feature of the low-resolution face image in a high-resolution space by using the super-resolution reconstruction of a recognition feature. Based on a manifold learning theory, the recognition features of the high-resolution and low-resolution face images are considered to be generated by a common internal structure, so the method comprises the following steps: enhancing the consistency of neighborhood relationships of the recognition features of the high-resolution and low-resolution face images by using typical correlation analysis so as to better meet the hypothesis on a neighborhood reconstruction concept; and utilizing neighborhood reconstruction to obtain the recognition feature of the high-resolution face image corresponding to the tested low-resolution face image in a related subspace obtained by the transformation of the typical correlation analysis, and finally utilizing the feature to recognize a face. Experiments show that a recognition rate obtained by the method is less influenced by the resolution of the face image and is relatively higher.

Description

A kind of face identification method based on typical correlation analysis spatial super-resolution
Technical field
The present invention relates to the recognition of face field, be specifically related to a kind of low resolution face identification method based on the canonical correlation analysis space.
Background technology
Face recognition technology has very important significance in the safe-guard system of current society.As one of the main direction of studying in pattern-recognition and machine learning field, there has been a large amount of face recognition algorithms to be suggested.But because the restriction of distance and hardware condition etc., the facial image resolution interested of taking in the large scene video monitoring system is often lower, has reduced the performance of recognition of face.How to improve recognition effect under the low resolution condition, be the problem that recognition of face aspect in recent years need solve.
(Super-resolution SR) is meant and utilizes certain algorithm (low resolution obtains a width of cloth or a series of high-definition picture (highresolution, technology HR) in LR) from a width of cloth or a series of low-resolution image image super-resolution.Therefore, the face image super-resolution algorithm is used as one of solution that improves low resolution facial image recognition effect very naturally.Particularly, utilize the super-resolution rebuilding algorithm to obtain visual effect facial image preferably earlier, and then carry out recognition of face.But face image super-resolution rebuilding part independently is carried out with identification division in this scheme, and the target localization of super-resolution improving image visual effect, rather than the raising discrimination.
Based on above reason, people such as Gunturk have proposed the face identification method based on eigenface territory super-resolution rebuilding.This method no longer attempts to improve the visual effect of image, but directly rebuilds the required high-resolution features face domain information of face identification system.At first adopt the KL conversion to extract the facial image eigenface, the use imaging model is set up the contact between the high low-resolution image feature, the prior probability of supposing the high-resolution features vector of asking is the associating Gaussian distribution, utilize the iteration steepest descent algorithm that this proper vector is carried out maximum a posteriori probability and estimate that the proper vector that last basis is tried to achieve is carried out recognition of face.This method provides a kind of and has well directly utilized super-resolution to carry out the framework of recognition of face, but this method computation complexity is higher, and the method has the space of further improvement on performance.
People such as Pablo have proposed the low resolution face identification method that super-resolution rebuilding and feature extraction combine.Utilize classical face characteristic extraction algorithm to obtain the feature of training image earlier as prior imformation, the sorter objective function that utilizes this prior imformation then and be used to discern is set up the regularization objective function, and obtain the parameter of regularization objective function by the method for study, in application, obtain super-resolution rebuilding result and recognition result simultaneously with regularization objective function minimum.The regularization objective function model that this method proposed clear expression simultaneously is to the restriction of super-resolution rebuilding result and recognition result, but the learning process more complicated of objective function parameter.In order to reduce algorithm complex, to improve discrimination, need to seek better method and solve low resolution recognition of face problem.
Summary of the invention
The objective of the invention is to overcome the shortcoming of above-mentioned prior art, proposed a kind of based on canonical correlation analysis (Canonical Correlation Analysis, CCA) face identification method of spatial super-resolution.
In order to achieve the above object, the technical solution used in the present invention is:
1) at first, utilize classical feature extracting method to extract high low resolution training of human face image recognition feature, utilize two groups of recognition features being extracted as training data, according to the requirement of CCA algorithm, must shine upon base vector, recognition feature is transformed into CCA correlator space according to this mapping base vector;
2) secondly, in the correlator space, utilize neighborhood reconstruct to try to achieve the recognition feature of test low resolution facial image recognition feature, realize the super-resolution rebuilding of recognition feature in high resolving power territory correspondence;
3) last, utilize nearest neighbor classifier based on the L2 norm, carry out the arest neighbors Classification and Identification according to the recognition feature in the CCA space of trying to achieve, thereby obtain discrimination.
Recognition feature of the present invention is transformed into CCA correlator space and may further comprise the steps:
1) establishing high resolving power and the low resolution training of human face image collection removed after the average is respectively
Figure G2009102075622D0000031
Figure G2009102075622D0000032
I wherein i HBe i panel height image in different resolution, I i LBe i width of cloth low-resolution image, m is the total number of samples of training image; Definition
Figure G2009102075622D0000033
B wherein HBe that the high-definition picture characteristic of correspondence is extracted matrix, x i HIt is representative's face image I i HProper vector; In like manner, the character representation that can obtain low-resolution image is B wherein LBe that low resolution facial image characteristic of correspondence is extracted matrix, x i LRepresent low resolution facial image I i LProper vector; Thus, obtain representing that the set of eigenvectors of corresponding high low resolution training image is With X wherein i HBe i panel height resolution facial image characteristic of correspondence vector, x i LIt is the proper vector of i width of cloth low resolution facial image;
2) for set of eigenvectors X H, X LDeduct its average x respectively HAnd x L, obtain the data set of centralization
Figure G2009102075622D0000037
With
Figure G2009102075622D0000038
Definition
Figure G2009102075622D0000039
Be respectively With
Figure G2009102075622D00000312
Auto-covariance matrix,
Figure G2009102075622D00000313
With
Figure G2009102075622D00000314
Be respectively
Figure G2009102075622D00000315
With The cross covariance matrix, E[wherein] represent mathematical expectation, T to represent the transposition computing; Calculate
Figure G2009102075622D00000317
Figure G2009102075622D00000318
R 1And R 2Proper vector be the base vector V that asks HAnd V L
3) utilize the base vector of asking, with set of eigenvectors X H, X LTransform to the CCA subspace, obtain the projection coefficient collection of high resolving power and low resolution training facial image correspondence
Figure G2009102075622D00000319
Figure G2009102075622D00000320
That is:
Figure G2009102075622D00000321
With
Recognition feature super-resolution rebuilding step of the present invention is as follows:
1) the low resolution people's face test pattern I to importing l, try to achieve its characteristic of correspondence vector x l, further with x lTransform to the CCA subspace, obtain c l, that is: c l=(V L) T(x l-x L);
2) according to the thought of neighborhood reconstruct, at C LThe middle c that seeks lK nearest neighbor { c Li L} I=1 K, c wherein Li LBe c lI neighbour, and ask the reconstruct weights
Figure G2009102075622D00000323
W wherein i GBe the weights coefficient of i neighbour's correspondence, make objective function
Figure G2009102075622D00000324
Reach minimum, and satisfy
Figure G2009102075622D00000325
3) with weights
Figure G2009102075622D00000326
Be applied to C HIn with { c Li L} I=1 KCorresponding { c Li H} I=1 K, promptly reconstruct I lThe recognition feature of corresponding full resolution pricture is:
Figure G2009102075622D00000327
Described classical feature extracting method adopts principal component analysis (PCA) or linear judgment analysis.
The present invention regards the recognition feature of high low resolution facial image as the variable of two different dimensions, utilize canonical correlation analysis to extract the correlator space of high low resolution facial image recognition feature, thereby strengthen the consistance of high low resolution facial image recognition feature topological structure.In the correlator space, the present invention utilizes neighborhood reconstruct to try to achieve the recognition feature of the high-resolution human face image area of test low resolution facial image correspondence, and utilizes the nearest neighbor classifier based on the L2 norm to carry out Classification and Identification, thereby obtains discrimination.
Description of drawings
Fig. 1 algorithm frame of the present invention;
A certain personage's five width of cloth facial expression images in Fig. 2 CAS-PEAL expression storehouse;
Fig. 3 utilizes CAS-PEAL expression picture library gained discrimination result;
Fig. 4 utilizes LDA to extract feature gained discrimination result;
Fig. 5 AR facial image database example, wherein (a) is 32 * 32 high resolving power training facial image, (b) is 8 * 8 low resolution training facial image, (c) is 8 * 8 low resolution test facial image;
Fig. 6 proper vector dimension size is to the influence of discrimination.
Embodiment
For making purpose of the present invention, technical scheme and advantage clearer,, the present invention is described in further details below in conjunction with accompanying drawing and instantiation.These examples are only illustrative, and are not limitation of the present invention.
The face image super-resolution identification problem can be described as: known two corresponding mutually high low resolution facial image training set I HAnd I LPerhaps two mutual training set X of corresponding facial image recognition feature HAnd X L, import a width of cloth low resolution facial image I l, ask the recognition feature c of its corresponding high-resolution human face image h
The theory hypothesis people face space of manifold learning is a kind of embedding manifold structure, promptly is embedded in the low-dimensional stream shape of higher-dimension theorem in Euclid space.This show higher-dimension structure that people's face data set constitutes under local sense with certain low-dimensional theorem in Euclid space topological homeomorphism.Only resolution difference, just dimension difference between corresponding high low resolution people's face data set.Therefore, can think that high low resolution people's face data set is to be generated by relevant immanent structure.Satisfying under the assumed condition of manifold learning, can be according to local linear (the Locallylinear embedding that embeds in the manifold learning, LLE) principle of algorithm, adopt the thought of neighborhood reconstruct, carry out face image super-resolution rebuilding, the neighborhood and the reconstruct weights that are about to the test data that low-resolution spatial tries to achieve are applied to high resolution space, thereby reconstruct the high resolution space data of test high-resolution data correspondence.
In recent years,, proposed some human face super-resolution algorithms, obtained good effect based on manifold learning based on above theory.Equally, if regard the recognition feature of high low resolution facial image as the height dimension data respectively, have reason also to think that these two data sets are to be generated by relevant immanent structure.Therefore, also can use based on the high-resolution recognition feature of the direct reconstruction of the thinking of manifold learning.
But, often can not obtain well satisfying about the hypothesis of high high-resolution data afflux shape local topology homeomorphism in practice owing to reasons such as training picture library limited in number.CCA is the method that is used for analyzing two groups of data line sexual intercourse at first, its objective is that being respectively every group of data seeks one group of base vector, makes to reach maximum by the data dependence after these two groups of base vector conversion.The present invention with the recognition feature of high-resolution and low-resolution image as two groups of pending data, set up the correlator space by CCA, consistance with the neighborhood relationships that strengthens high low resolution facial image recognition feature, satisfying hypothesis better based on neighborhood reconstruct thought in the manifold learning method, thus reconstruct high-resolution human face image recognition feature more accurately.
Algorithm frame of the present invention mainly comprises three parts as shown in Figure 1: facial image feature extraction, the super-resolution rebuilding of recognition feature and final identifying.
If high resolving power after the removal average and low resolution training of human face image collection are respectively
Figure G2009102075622D0000051
Wherein m is a number of samples.The facial image feature can by classical principal component analysis (PCA) (Principal Component Analysis, PCA) or linear judgment analysis (Linear Discriminant Analysis LDA) waits and obtains.At this, definition
Figure G2009102075622D0000053
B wherein HBe that high-resolution human face image characteristic of correspondence is extracted matrix, x i HIt is representative's face image I i HProper vector.In like manner, the character representation that can obtain low-resolution image is
Figure G2009102075622D0000054
B wherein LBe that low resolution facial image characteristic of correspondence is extracted matrix, x i LRepresent low resolution facial image I i LProper vector.Thus, obtain representing that the set of eigenvectors of corresponding high low resolution training image is
Figure G2009102075622D0000061
With
Figure G2009102075622D0000062
Wherein m is a number of samples.
In the super-resolution rebuilding part of recognition feature, the proper vector with high low resolution training image is transformed into the CCA subspace earlier.Concrete, for set of eigenvectors X H, X LDeduct its average x respectively HAnd x L, obtain the data set of centralization
Figure G2009102075622D0000063
With
Figure G2009102075622D0000064
The target of CCA is to be respectively sample set
Figure G2009102075622D0000065
With
Figure G2009102075622D0000066
Seek two groups of base vector V H, V L, the feasible variable that utilizes after base vector shines upon
Figure G2009102075622D0000067
With
Figure G2009102075622D0000068
Between related coefficient ρ reach maximum, promptly have:
ρ = E [ C H C L ] E [ ( C H ) 2 ] E [ ( C L ) 2 ] - - - ( 1 )
Figure G2009102075622D00000610
Obtain maximal value, wherein E[] represent mathematical expectation.
In order to find the solution base vector V HAnd V L, definition
Figure G2009102075622D00000611
Be respectively
Figure G2009102075622D00000613
With
Figure G2009102075622D00000614
Auto-covariance matrix, With
Figure G2009102075622D00000616
Be respectively
Figure G2009102075622D00000617
With
Figure G2009102075622D00000618
The cross covariance matrix.Calculate
Figure G2009102075622D00000619
Figure G2009102075622D00000620
R 1And R 2Proper vector be the base vector V that asks HAnd V L
Utilize the base vector of asking, with set of eigenvectors X H, X LTransform to the CCA subspace, obtain corresponding projection coefficient collection
Figure G2009102075622D00000621
Figure G2009102075622D00000622
That is:
Figure G2009102075622D00000623
Figure G2009102075622D00000624
Because X H, X LHave relevant immanent structure between these two data sets, it is transformed to the CCA subspace, just behind the correlator space, the linear dependence maximum between two data sets makes the consistance of two data set inner topology structures strengthen.Thereby in the CCA subspace, projection coefficient collection C H, C LThe hypothesis that the preface of data point keeps between the high lower dimensional space neighborhood of satisfied better local linear embedding algorithm, so can utilize the thought of neighborhood reconstruct to try to achieve the recognition feature of test low resolution facial image in high resolution space.
Low resolution people's face test pattern I to input l, try to achieve its characteristic of correspondence vector x l, further with x lTransform to the CCA subspace, obtain c l, that is:
c l＝(V L) T(x l-x L) (4)
According to the thought of neighborhood reconstruct, at C LThe middle c that seeks lK nearest neighbor { c Li L} I=1 K, and ask the reconstruct weights Make
ϵ = | | c l - Σ i = 1 K w i G c li L | | - - - ( 5 )
Reach minimum, and satisfy
Figure G2009102075622D0000073
These weights are applied to C HIn with { c Li L} I=1 KCorresponding { c Li H} I=1 K, can reconstruct I lThe corresponding recognition feature of full resolution pricture in the CCA subspace is:
c h = Σ i = 1 K w i G c li H - - - ( 6 )
At identification division, the present invention carries out recognition of face according to the recognition feature of CCA subspace.Utilize feature c hWith
Figure G2009102075622D0000075
Employing is carried out Classification and Identification based on the nearest neighbor classifier of L2 norm, and promptly decision function is:
g k ( c h ) = min ( | | c h - c ik H | | 2 ) , I = 1,2 , . . . m - - - ( 7 )
C wherein Ik HExpression C HIn belong to i sample of k class.
In order to verify validity of the present invention, utilize CAS-PEAL expression people's face picture library and AR face database to experimentize respectively.The gained experimental result respectively with based on the method for Gunturk in the recognizer of bicubic interpolation, the document and utilize the original high resolution facial image to discern the gained discrimination to compare.Wherein, be meant based on the bicubic interpolation recognizer and utilize bicubic interpolation to obtain the high-resolution human face image, extract the feature of this high-resolution human face image then and discern the low resolution facial image; Utilize the original high resolution facial image to discern, promptly directly extract the feature of this high-resolution human face image and discern.
Utilize CAS-PEAL expression picture library to carry out in the recognition of face experiment, 190 personages of picked at random from original 377 personages' expression picture library, each personage comprise the image of the different expressions of 5 width of cloth.Fig. 2 has provided the lineup's face image through pretreated a certain personage.
In this experimentation, utilize first three width of cloth image of same personage to train, remain two width of cloth images and discern.Divide three kinds of situations to carry out recognition of face according to high low-resolution image size, be respectively: high resolving power training image size is 64 * 64, and the low-resolution image size is 16 * 16; High resolving power training image size is 64 * 64, and the low-resolution image size is 8 * 8; High resolving power training image size is 32 * 32, and the low-resolution image size is 8 * 8.Utilize PCA to extract feature, and the high-definition picture proper vector keep preceding 50 dimensions, preceding 30 dimensions of low-resolution image reservation; In the inventive method, the neighborhood number during neighborhood reconstruct is 20.Parameter in the Gunturk method list of references: preceding 50 dimensional feature vectors are selected in the KL conversion, and the greatest iteration number is 7, λ=0.5, and experimentation used parameter in back is identical therewith.
By result among Fig. 3 as can be seen, when image resolution ratio to be identified is low, compare other method, the inventive method discrimination is higher, and overall performance is more stable.The inventive method gained discrimination is with to utilize the original high resolution image to discern the gained discrimination very approaching, this is because the present invention carries out super-resolution rebuilding for recognition feature, can obtain to test the recognition feature of low-resolution image, effectively raise discrimination in the high-resolution features space.
For the performance of multianalysis algorithm of the present invention, utilize LDA to extract face characteristic, for algorithm of the present invention, compare based on bicubic recognizer and the method for utilizing the original high resolution image to discern.Other parameter setting and computation process are identical with top experiment in the experiment.The gained result as shown in Figure 4.Comparison diagram 3 and Fig. 4 as can be known, the inventive method and the method for utilizing original image identification are utilized LDA to extract aspect ratio and are utilized PCA to extract feature gained discrimination to want high, this is consistent with theory.
Utilize the parts of images in the AR image library to carry out the recognition of face experiment, select 135 width of cloth facial images in the picture library, each personage selects three width of cloth images, and wherein preceding two width of cloth are used for training, and last width of cloth is used for test.In this group experimentation, high resolving power training image size is 32 * 32, and the low-resolution image size is 8 * 8.List the high low resolution facial image of training of lineup's thing and test the low resolution facial image as shown in Figure 5.
Utilize PCA to extract the facial image feature in this experiment equally, high resolving power training image size is 32 * 32, the low-resolution image size is 8 * 8, the neighborhood number is 10, low-resolution image utilizes PCA to keep preceding 30 dimensional feature vectors, analyzes the influence of high-definition picture proper vector dimension variation to experimental result.The result as shown in Figure 6.
As seen from Figure 6: along with the increase of proper vector dimension, the gained discrimination is all in rising trend at first, is stabilized in gradually then in the interval, and fluctuation range is no more than 0.05; The method that the inventive method gained discrimination result compares Gunturk can reach the stabilized zone faster, and discrimination is higher; When the proper vector dimension greater than 20, the inventive method gained discrimination with utilize original image gained discrimination very approaching, sometimes also less times greater than utilizing original image gained discrimination, this is because the inventive method is utilized the super-resolution rebuilding of recognition feature, solution space is limited in the high-resolution features space, can obtain the information that helps discerning.
In sum, the present invention is directed to the lower problem of low resolution facial image discrimination, proposed a kind of super-resolution rebuilding of recognition feature that utilizes and obtained the method for low resolution facial image in the recognition feature of high resolution space correspondence.In the super-resolution rebuilding process of recognition feature, the present invention utilizes CCA to obtain the correlator space of high low-resolution image, utilizes neighborhood reconstruct to obtain testing the recognition feature of low-resolution image in high resolution space then in this correlator space.Experiment shows that it is less that the inventive method gained discrimination is influenced by the image resolution ratio size, and the gained discrimination is higher.

Claims (4)

1. face identification method based on typical correlation analysis spatial super-resolution is characterized in that: comprise following steps:
1) at first, utilize classical feature extracting method to extract high low resolution training of human face image recognition feature, utilize two groups of recognition features being extracted as training data, according to the requirement of CCA algorithm, must shine upon base vector, recognition feature is transformed into CCA correlator space according to this mapping base vector;
2) secondly, in the correlator space, utilize neighborhood reconstruct to try to achieve the recognition feature of test low resolution facial image recognition feature, realize the super-resolution rebuilding of recognition feature in high resolving power territory correspondence;
3) last, utilize nearest neighbor classifier based on the L2 norm, carry out the arest neighbors Classification and Identification according to the recognition feature in the CCA space of trying to achieve, thereby obtain discrimination.
2. the face identification method based on typical correlation analysis spatial super-resolution as claimed in claim 1 is characterized in that: described recognition feature is transformed into CCA correlator space and may further comprise the steps:
1) establishing high resolving power and the low resolution training of human face image collection removed after the average is respectively
Figure F2009102075622C0000011
I wherein i HBe i panel height image in different resolution, I i LBe i width of cloth low-resolution image, m is the total number of samples of training image; Definition
Figure F2009102075622C0000012
B wherein HBe that the high-definition picture characteristic of correspondence is extracted matrix, x i HIt is representative's face image I i HProper vector; In like manner, the character representation that can obtain low-resolution image is
Figure F2009102075622C0000013
B wherein LBe that low resolution facial image characteristic of correspondence is extracted matrix, x i LRepresent low resolution facial image I i LProper vector; Thus, obtain representing that the set of eigenvectors of corresponding high low resolution training image is
Figure F2009102075622C0000014
With
Figure F2009102075622C0000015
X wherein i HBe i panel height resolution facial image characteristic of correspondence vector, x i LIt is the proper vector of i width of cloth low resolution facial image;
2) for set of eigenvectors X H, X LDeduct its average x respectively HAnd x L, obtain the data set of centralization
Figure F2009102075622C0000016
With
Figure F2009102075622C0000017
Definition
Figure F2009102075622C0000018
Be respectively
Figure F2009102075622C0000019
With
Figure F2009102075622C00000110
Auto-covariance matrix,
Figure F2009102075622C00000111
With
Figure F2009102075622C00000112
Be respectively With
Figure F2009102075622C00000114
The cross covariance matrix, E[wherein] represent mathematical expectation, T to represent the transposition computing; Calculate
Figure F2009102075622C0000021
Figure F2009102075622C0000022
R 1And R 2Proper vector be the base vector V that asks HAnd V L
3) utilize the base vector of asking, with set of eigenvectors X H, X LTransform to the CCA subspace, obtain the projection coefficient collection of high resolving power and low resolution training facial image correspondence
Figure F2009102075622C0000023
Figure F2009102075622C0000024
That is:
Figure F2009102075622C0000025
With
Figure F2009102075622C0000026
3. the face identification method based on typical correlation analysis spatial super-resolution as claimed in claim 1 or 2 is characterized in that: described recognition feature super-resolution rebuilding step is as follows:
1) the low resolution people's face test pattern I to importing l, try to achieve its characteristic of correspondence vector x l, further with x lTransform to the CCA subspace, obtain c l, that is: c l=(V L) T(x l-x L);
2) according to the thought of neighborhood reconstruct, at C LThe middle c that seeks lK nearest neighbor { c Li L} I=1 K, c wherein Li LBe c lI neighbour, and ask the reconstruct weights
Figure F2009102075622C0000027
W wherein i GBe the weights coefficient of i neighbour's correspondence, make objective function
Figure F2009102075622C0000028
Reach minimum, and satisfy
Figure F2009102075622C0000029
3) with weights Be applied to C HIn with { c Li L} I=1 KCorresponding { c Li H} I=1 K, promptly reconstruct I lThe recognition feature of corresponding full resolution pricture is:
Figure F2009102075622C00000211
4. the face identification method based on typical correlation analysis spatial super-resolution as claimed in claim 1 is characterized in that: described classical feature extracting method adopts principal component analysis (PCA) or linear judgment analysis.
CN2009102075622A 2009-10-20 2009-10-20 Method for recognizing human face based on typical correlation analysis spatial super-resolution Expired - Fee Related CN101697197B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2009102075622A CN101697197B (en) 2009-10-20 2009-10-20 Method for recognizing human face based on typical correlation analysis spatial super-resolution

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2009102075622A CN101697197B (en) 2009-10-20 2009-10-20 Method for recognizing human face based on typical correlation analysis spatial super-resolution

Publications (2)

Publication Number Publication Date
CN101697197A true CN101697197A (en) 2010-04-21
CN101697197B CN101697197B (en) 2012-05-23

Family

ID=42142301

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2009102075622A Expired - Fee Related CN101697197B (en) 2009-10-20 2009-10-20 Method for recognizing human face based on typical correlation analysis spatial super-resolution

Country Status (1)

Country Link
CN (1) CN101697197B (en)

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102693419A (en) * 2012-05-24 2012-09-26 武汉大学 Super-resolution face recognition method based on multi-manifold discrimination and analysis
CN105701513A (en) * 2016-01-14 2016-06-22 深圳市未来媒体技术研究院 Method of rapidly extracting area of interest of palm print
CN106096547A (en) * 2016-06-11 2016-11-09 北京工业大学 A kind of towards the low-resolution face image feature super resolution ratio reconstruction method identified
CN106097250A (en) * 2016-06-22 2016-11-09 江南大学 A kind of based on the sparse reconstructing method of super-resolution differentiating canonical correlation
CN106203256A (en) * 2016-06-24 2016-12-07 山东大学 A kind of low resolution face identification method based on sparse holding canonical correlation analysis
CN106295700A (en) * 2016-08-12 2017-01-04 中国石油大学(华东) A kind of two multi-view image recognition methodss based on canonical correlation analysis network
CN107330381A (en) * 2017-06-15 2017-11-07 浙江捷尚视觉科技股份有限公司 A kind of face identification method
CN107967677A (en) * 2017-12-15 2018-04-27 广东欧珀移动通信有限公司 Image processing method, device, computer-readable recording medium and computer equipment
CN108108673A (en) * 2017-12-08 2018-06-01 浙江捷尚视觉科技股份有限公司 A kind of unrelated deep learning faceform's training method of picture quality
CN109583426A (en) * 2018-12-23 2019-04-05 广东腾晟信息科技有限公司 A method of according to image identification face
CN109712069A (en) * 2018-11-08 2019-05-03 宁波大学 A kind of facial image multilayer reconstructing method based on the space CCA
CN110705498A (en) * 2019-10-12 2020-01-17 北京泰豪信息科技有限公司 Low-resolution face recognition method
CN110796022A (en) * 2019-10-09 2020-02-14 西安工程大学 Low-resolution face recognition method based on multi-manifold coupling mapping
CN111275624A (en) * 2020-01-21 2020-06-12 扬州大学 Face image super-resolution reconstruction recognition method based on multi-set canonical correlation analysis
CN111611962A (en) * 2020-05-29 2020-09-01 扬州大学 Face image super-resolution identification method based on fractional order multi-set partial least square
CN112102170A (en) * 2020-09-18 2020-12-18 重庆紫光华山智安科技有限公司 Super-resolution reconstruction network training method, super-resolution reconstruction network training system, super-resolution reconstruction network training image generation method, super-resolution reconstruction network training system, terminal and medium

Cited By (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102693419B (en) * 2012-05-24 2014-02-26 武汉大学 Super-resolution face recognition method based on multi-manifold discrimination and analysis
CN102693419A (en) * 2012-05-24 2012-09-26 武汉大学 Super-resolution face recognition method based on multi-manifold discrimination and analysis
CN105701513A (en) * 2016-01-14 2016-06-22 深圳市未来媒体技术研究院 Method of rapidly extracting area of interest of palm print
CN105701513B (en) * 2016-01-14 2019-06-07 深圳市未来媒体技术研究院 The method of rapidly extracting palmmprint area-of-interest
CN106096547B (en) * 2016-06-11 2019-02-19 北京工业大学 A kind of low-resolution face image feature super resolution ratio reconstruction method towards identification
CN106096547A (en) * 2016-06-11 2016-11-09 北京工业大学 A kind of towards the low-resolution face image feature super resolution ratio reconstruction method identified
CN106097250A (en) * 2016-06-22 2016-11-09 江南大学 A kind of based on the sparse reconstructing method of super-resolution differentiating canonical correlation
CN106097250B (en) * 2016-06-22 2019-04-16 江南大学 A kind of sparse reconstructing method of super-resolution based on identification canonical correlation
CN106203256A (en) * 2016-06-24 2016-12-07 山东大学 A kind of low resolution face identification method based on sparse holding canonical correlation analysis
CN106295700A (en) * 2016-08-12 2017-01-04 中国石油大学(华东) A kind of two multi-view image recognition methodss based on canonical correlation analysis network
CN106295700B (en) * 2016-08-12 2019-05-14 中国石油大学(华东) A kind of two multi-view image recognition methods based on canonical correlation analysis network
CN107330381A (en) * 2017-06-15 2017-11-07 浙江捷尚视觉科技股份有限公司 A kind of face identification method
CN108108673A (en) * 2017-12-08 2018-06-01 浙江捷尚视觉科技股份有限公司 A kind of unrelated deep learning faceform's training method of picture quality
US11003891B2 (en) 2017-12-15 2021-05-11 Guangdong Oppo Mobile Telecommunications Corp., Ltd. Image processing method and apparatus, and electronic device
CN107967677A (en) * 2017-12-15 2018-04-27 广东欧珀移动通信有限公司 Image processing method, device, computer-readable recording medium and computer equipment
CN107967677B (en) * 2017-12-15 2020-02-04 Oppo广东移动通信有限公司 Image processing method, image processing device, computer-readable storage medium and computer equipment
CN109712069A (en) * 2018-11-08 2019-05-03 宁波大学 A kind of facial image multilayer reconstructing method based on the space CCA
CN109712069B (en) * 2018-11-08 2023-04-07 宁波大学 Face image multilayer reconstruction method based on CCA space
CN109583426A (en) * 2018-12-23 2019-04-05 广东腾晟信息科技有限公司 A method of according to image identification face
CN110796022A (en) * 2019-10-09 2020-02-14 西安工程大学 Low-resolution face recognition method based on multi-manifold coupling mapping
CN110796022B (en) * 2019-10-09 2023-07-21 奥园智慧生活服务(广州)集团有限公司 Low-resolution face recognition method based on multi-manifold coupling mapping
CN110705498A (en) * 2019-10-12 2020-01-17 北京泰豪信息科技有限公司 Low-resolution face recognition method
CN111275624A (en) * 2020-01-21 2020-06-12 扬州大学 Face image super-resolution reconstruction recognition method based on multi-set canonical correlation analysis
CN111275624B (en) * 2020-01-21 2023-08-08 扬州大学 Face image super-resolution reconstruction and identification method based on multi-set typical correlation analysis
CN111611962A (en) * 2020-05-29 2020-09-01 扬州大学 Face image super-resolution identification method based on fractional order multi-set partial least square
CN112102170A (en) * 2020-09-18 2020-12-18 重庆紫光华山智安科技有限公司 Super-resolution reconstruction network training method, super-resolution reconstruction network training system, super-resolution reconstruction network training image generation method, super-resolution reconstruction network training system, terminal and medium

Also Published As

Publication number Publication date
CN101697197B (en) 2012-05-23

Similar Documents

Publication Publication Date Title
CN101697197B (en) Method for recognizing human face based on typical correlation analysis spatial super-resolution
Liew et al. Gender classification: a convolutional neural network approach
Wan et al. End-to-end integration of a convolution network, deformable parts model and non-maximum suppression
CN107085716A (en) Across the visual angle gait recognition method of confrontation network is generated based on multitask
CN101615290B (en) Face image super-resolution reconstructing method based on canonical correlation analysis
CN103679142B (en) A kind of recognition method for target human body based on space constraint
CN101710386A (en) Super-resolution face recognition method based on relevant characteristic and non-liner mapping
Herdiyeni et al. Combination of morphological, local binary pattern variance and color moments features for indonesian medicinal plants identification
CN103699874B (en) Crowd abnormal behavior identification method based on SURF (Speed-Up Robust Feature) stream and LLE (Locally Linear Embedding) sparse representation
CN104933414A (en) Living body face detection method based on WLD-TOP (Weber Local Descriptor-Three Orthogonal Planes)
Khan et al. Head pose estimation through multi-class face segmentation
CN103226699B (en) A kind of face identification method having supervision locality preserving projections based on separating degree difference
CN107463917A (en) A kind of face feature extraction method merged based on improved LTP with the two-way PCA of two dimension
CN103745205A (en) Gait recognition method based on multi-linear mean component analysis
CN110796022B (en) Low-resolution face recognition method based on multi-manifold coupling mapping
CN104834909B (en) A kind of new image representation method based on Gabor comprehensive characteristics
CN113158880A (en) Deep learning-based student classroom behavior identification method
Liu et al. Extended faster R-CNN for long distance human detection: Finding pedestrians in UAV images
CN105868711B (en) Sparse low-rank-based human behavior identification method
CN109635726A (en) A kind of landslide identification method based on the symmetrical multiple dimensioned pond of depth network integration
Tong et al. Cross-view gait recognition based on a restrictive triplet network
CN111414958B (en) Multi-feature image classification method and system for visual word bag pyramid
CN101430760B (en) Human face super-resolution processing method based on linear and Bayesian probability mixed model
Abaza et al. Ear recognition: a complete system
CN110728238A (en) Personnel re-detection method of fusion type neural network

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
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: 20120523

Termination date: 20161020