CN103886235A - Face image biological key generating method - Google Patents
Face image biological key generating method Download PDFInfo
- Publication number
- CN103886235A CN103886235A CN201410075104.9A CN201410075104A CN103886235A CN 103886235 A CN103886235 A CN 103886235A CN 201410075104 A CN201410075104 A CN 201410075104A CN 103886235 A CN103886235 A CN 103886235A
- Authority
- CN
- China
- Prior art keywords
- face
- matrix
- secret key
- image
- biological secret
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/45—Structures or tools for the administration of authentication
- G06F21/46—Structures or tools for the administration of authentication by designing passwords or checking the strength of passwords
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Collating Specific Patterns (AREA)
- Image Processing (AREA)
Abstract
The invention provides a face image biological key generating method. The face image biological key generating method includes steps of subjecting face images of users to characteristic space conversion, projecting the face images into a higher space, stabilizing facial feature information into an acceptable fluctuation range in the higher space, extracting digital sequences from stabilized feature vectors, and encoding in the digital sequences to generate a biological key. By adopting the face image biological key generating method, no face information of the users is required to be stored in mobile terminals and identification servers, and the face images of the users are also dispensed with transmission in the network. The users generate (user names and secret keys) pairs by acquiring the face images of their own and perform network identity authentication by various authentication methods derived from the (user names and secret keys) pairs. The private data of the users are subjected to direct encipherment protection by the method supporting the face biological secret key, and the method can be extended to application in the field of cloud storage safety. As long as key space of the face biological secret keys is larger enough, high safety can be guaranteed.
Description
Technical field
The invention belongs to field of information security technology, be specifically related to a kind of method of extracting face biological secret key by front face image.It can, by picked-up facial image, directly generate biological secret key, network ID authentication process based on face is simplified and flexibly more, for network ID authentication technology provides a kind of new authentication method.The application of expansion face recognition technology in network security.
Background technology
In recent years, the face recognition technology based on machine vision is subject to extensive concern, because it can be widely used at daily life field.One of them important application is authentication, face check card system, network-side authentication etc. be all face recognition technology use good case.In network ID authentication field, face authentication adopts following certification mode: 1) gather user's face, extract and use face feature templates, store far-end network certificate server into; 2) in the time that need carry out authenticating user identification, gather user's face at user terminal, generate face characteristic, be transferred to far-end network certificate server; 3) certificate server is compared the skin detection of user's face characteristic and storage, and unanimously authentication is passed through, inconsistent authentification failure.This certification mode has certain shortcoming: need in unsafe network environment, store, transmit user's face information.If user is unfamiliar with certification end, generally can not coordinate the facial image of uploading oneself.This has limited the popularization of face authentication in network ID authentication.In addition, store in flourish environment at cloud, face authentication is not owing to supporting face biological information to encrypt, and user cannot protect the private data of oneself with the biological characteristic of oneself.This has limited to the development of face recognition technology at information security field, and face recognition technology fails to bring into play its due effect aspect cloud storage security.
Once there is researcher to propose the concept of biological secret key, wished directly from biological characteristic, to obtain stable biological secret key sequence.But current research does not provide complete face characteristic information, the face biological secret key technology that in actual production life, appearance can be practical.
Summary of the invention
The present invention proposes a kind of face biological secret key generation method.Method by user's front face image after Feature Space Transformation, to projection in higher dimensional space, in higher dimensional space, face characteristic information is stabilized in acceptable fluctuation range, then the proper vector after stable is extracted to Serial No., from Serial No., coding generates biological secret key.Whole method at mobile terminal, certificate server end all without storage user face information, also without the facial image that transmits user in network.User generates (user name, key) by the front face image of collection self in this locality right, by (user name, key), derivative various authentication methods is carried out to network ID authentication.The method is also supported directly user's private data to be encrypted to protection with face biological secret key, can expand in cloud storage security field and apply.As long as the key space of face biological secret key is enough large, can guarantee high security.The face biological secret key sequence length that the present invention extracts is adjustable, can be greater than 256bit.
Face biological secret key generates point two parts, and Part I is face biological secret key training part, and Part II is face biological secret key Extraction parts.
Face biological secret key training part concrete steps are:
The first step, user is by camera collection frontal faces image, frontal faces is adjusted voluntarily by user, gathers environmental requirement at the abundant environment of indoor light, natural light, artificial light source all can, repeated acquisition is more than 8 times.
Second step, carries out gray processing processing to facial image, adjusts image size for unified size 128 × 128, or 64 × 64, user can decide in its sole discretion by rule of thumb.
The 3rd step, asks facial image from quotient graph, obtains 8 secondary above from quotient graph image.
The 4th step, will more than 8 width be made into sample matrix from quotient graph image sets, carries out principal component analysis (PCA) (PCA) and processes, and obtains the projection matrix of face in feature space, is designated as P1.By more than 8 width from quotient graph image respectively through projection matrix P1 projection, obtain face characteristic vector.The eigenvectors matrix that the proper vector of trying to achieve is organized as to a M × D dimension, is designated as S1, and M is from quotient graph image number, and D is proper vector element number after projection, general D>M.
The 5th step, expands to 2 matrixes by matrix S 1, the stochastic error square formation EX of L × L dimension, and the standard value square formation EY of L × L dimension, the concrete building method of L>D(illustrates in embodiment).
The 6th step, solves the generalized inverse matrix of EX, is designated as IEX, IEX premultiplication matrix EY is obtained to the higher dimensional space projection matrix PEX=IEX × EY of face characteristic vector, at user side storage projection matrix P1 and PEX.
Face biological secret key has been trained.
Face biological secret key Extraction parts concrete steps are:
The first step, user is by camera collection frontal faces image, and frontal faces is adjusted voluntarily by user, gathers environmental requirement at the abundant environment of indoor light, and natural light, artificial light source all can.
Second step, carries out gray processing processing to facial image, the consistent size of setting while adjusting image size for unified size and the training of face biological secret key.
The 3rd step, asks facial image from quotient graph.
The 4th step, will transfer row vector to from quotient graph image, the projection matrix P1 of storage while getting the training of face biological secret key, and premultiplication projection matrix P1, obtains the proper vector of face in feature space, is designated as Z, and length is D.
The 5th step, expands to 1 × L dimension matrix EZ by vector Z, and premultiplication PEX matrix, obtains 1 × L dimensional vector ED; It is consistent when extended method is trained with face biological secret key.
The 6th step, carries out further stable processing by chessboard method to the numerical value in vectorial ED, and getting front DL number is worth 1 × DL dimensional vector EE, DL≤D.By splicing before and after the numerical value of each element in vectorial EE, generate face biological secret key.(chessboard method illustrates in embodiment)
Beneficial effect of the present invention: the present invention proposes a kind of face biological secret key generation method.Can change traditional network biometric identity certification mode, user, without storing individual face information at mobile terminal, certificate server end, also, without transmit facial image in network, can complete the network ID authentication based on face.Meanwhile, the method is also supported directly user's private data to be encrypted to protection with face biological secret key, can expand in cloud storage security field and apply.
Accompanying drawing explanation
Fig. 1 is that face biological secret key extracts process flow diagram.
Fig. 2 is that face is from quotient graph effect schematic diagram.
Fig. 3 is that facial image is converted into row vector schematic diagram.
Fig. 4 is face principal component analysis process flow diagram.
Fig. 5 is face biological secret key generative process schematic diagram.
Embodiment
Below in conjunction with accompanying drawing, the invention will be further described.
Current face recognition technology cannot correctly be identified multi-pose Face, complex illumination condition face.The precondition that face biological secret key of the present invention extracts is frontal faces, and illumination is abundant, without multiple light courcess multi-angle irradiation.Putting before this, recognition of face has very high accuracy rate.Through a series of stable processing, can therefrom extract biological secret key.The extraction flow process of face biological secret key as shown in Figure 1.
Illumination condition has a great impact existing recognition of face effect, need to first eliminate illumination effect, and the present invention uses from quotient graph method and eliminates illumination effect, and effect as shown in Figure 2.
The face biological secret key generation method that the present invention proposes is divided two parts, and Part I is face biological secret key training part, and Part II is face biological secret key Extraction parts.
Face biological secret key training part concrete steps are:
The first step, user is by camera collection frontal faces image, frontal faces is adjusted voluntarily by user, gathers environmental requirement at the abundant environment of indoor light, natural light, artificial light source all can, repeated acquisition is more than 8 times.
Second step, carries out gray processing processing to facial image.Gray processing is processed formula
f(i,j)=0.30R(i,j)+0.59G(i,j)+0.11B(i,j) (1)
R, G, B are red, green, blue three-component.Adjust image size for unified size 128 × 128, or 64 × 64 or user can decide in its sole discretion by rule of thumb.
The 3rd step, asks facial image from quotient graph, obtains 8 secondary above from quotient graph image.From quotient graph computing formula be
Wherein
for the version of I after level and smooth, F is filtering core, and * is convolution algorithm symbol.Generally get gaussian filtering core, 3 rank, 5 rank all can, as F gets
The 4th step, will more than 8 width be made into sample matrix from quotient graph image sets.The total M width of note is from quotient graph image.Single image is arranged with splicing before and after behavior unit, becomes one dimension row vector, containing n element, as shown in Figure 3; Allly be converted into after row vector from quotient graph, walk to from the 1st with behavior unit that M is capable to be arranged in turn, obtain M × n dimension sample matrix S.
Sample matrix is carried out to principal component analysis (PCA) (PCA).Analysis process as shown in Figure 4.
Sample matrix centralization processing, each of matrix is listed as divided by corresponding average, and formula is:
S
ijfor arbitrary component of sample matrix.
Calculate sample matrix covariance matrix;
By covariance matrix C diagonalization.First C is carried out to Eigenvalues Decomposition, obtain eigenvectors matrix and orthogonalization is P.P meets:
P
TCP=Λ (5)
Λ is diagonal matrix, the eigenwert that the value of diagonal element is Matrix C.
Get eigenvectors matrix P1(n × D dimension that the individual eigenwert characteristic of correspondence vector of maximum front D (D<n) composition is new), P1 is the projection matrix of face in feature space.
By M width from quotient graph image respectively through projection matrix P1 projection, computing formula is
S1=S×P1 (6)
S1 is the eigenvectors matrix of M × D dimension, and D is proper vector element number after projection, general D>M.
The 5th step, expands to 2 matrixes by matrix S 1, the stochastic error square formation EX of L × L dimension, and the EY of L × L dimension, L>D, building method is:
Get M row vector of matrix S 1, average, obtain mean vector EB(1 × D dimension);
Set fluctuation range Er, as Er=10; For EB increases stochastic error disturbance, computing formula is
S1
jrepresent that the j in S1 matrix is capable, EX
jrepresent a row vector; Rand (0,1) function returns to the random number between (0,1); By EX
jbe assembled into the matrix of L × D dimension with behavior unit.
Construct L-D nonlinear function, input variable is one dimension row vector (x
1, x
2..., x
d), D element, is output as one dimension row vector (x
1, x
2..., x
d..., x
l), L element.Nonlinear function can be by user's self-defining, as example, and desirable following nonlinear function
Z (t)=(x
1-x
2) × sin (t)+(t
^2) × (x
3%10) (t is integer, 0<t<L-D) (8)
Sin (t) trigonometric function, (t
^2) represent t square, (x
3%10) represent x
3mould 10 computings.
With structure Z (t) to EX
jcarry out computing, j travels through 1~L, obtains L × L and ties up matrix, i.e. stochastic error square formation EX.
EY building method is:
Mean vector EB is repeated to L capable, obtain L × D and tie up matrix, be designated as EYt.With Z (t) to EYt
jcarry out computing, j travels through 1-L, obtains L × L and ties up matrix, i.e. standard value square formation EY.
The 6th step, solves the generalized inverse matrix of EX, is designated as IEX, IEX premultiplication matrix EY is obtained to the higher dimensional space projection matrix PEX=IEX × EY of face characteristic vector, at user side storage projection matrix P1 and PEX.
Face biological secret key has been trained.
As shown in Figure 5, concrete steps are the Serial No. stream situation of change of face biological secret key leaching process:
The first step, user is by camera collection frontal faces image, and frontal faces is adjusted voluntarily by user, gathers environmental requirement at the abundant environment of indoor light, and natural light, artificial light source all can.
Second step, carries out gray processing processing to facial image, the consistent size of setting while adjusting image size for unified size and the training of face biological secret key.
The 3rd step, asks facial image from quotient graph.Identical with face biological secret key training department separating method.
The 4th step, will transfer row vector to from quotient graph image, and method is identical with face biological secret key training department separating method.The projection matrix P1 of storage while getting the training of face biological secret key, premultiplication projection matrix P1, obtains the proper vector of face in feature space, is designated as Z, and length is D.
The 5th step, expands to 1 × L dimension matrix EZ by vector Z.When extended method and the training of face biological secret key, be consistent.The spread function Z (t) that spread function is the 5th step description of face biological secret key training part as got.
Matrix EZ premultiplication PEX, obtains 1 × L dimensional vector ED;
The 6th step, carries out further stablizing by chessboard method to the numerical value in vectorial ED and processes.Chessboard method is described below:
Each element in ED (is designated as to EDX
i) carry out once-through operation, false code is
Mod () is mod, and the grid size of maxdis mark chessboard method, gets odd number, and occurrence can be rule of thumb selected by user.
Get front DL number and be worth 1 × DL dimensional vector EE, DL≤D.By splicing before and after the numerical value of each element in vectorial EE, generate face biological secret key.DL is selected as required by user.
Those of ordinary skill in the art will be appreciated that; above embodiment is only for the present invention is described; and not as limitation of the invention, as long as in essential scope of the present invention, variation, modification to above embodiment all will drop on protection scope of the present invention.
Claims (1)
1. a front face image biological secret key generation method, is characterized in that the method comprises the following steps: face biological secret key training part and face biological secret key Extraction parts;
Face biological secret key training part concrete steps are:
The first step, user is by camera collection frontal faces image, and frontal faces is adjusted voluntarily by user, gathers environmental requirement at the abundant environment of indoor light, and repeated acquisition is more than 8 times;
Second step, carries out gray processing processing to facial image, adjusts image size for unified size 128 × 128 or 64 × 64;
The 3rd step, asks facial image from quotient graph, obtains 8 secondary above from quotient graph image;
The 4th step, will more than 8 width be made into sample matrix from quotient graph image sets, carries out principal component analysis (PCA) processing, obtains the projection matrix of face in feature space, is designated as P1; By more than 8 width from quotient graph image respectively through projection matrix P1 projection, obtain face characteristic vector; The eigenvectors matrix that the proper vector of trying to achieve is organized as to a M × D dimension, is designated as S1, and M is from quotient graph image number, and D is proper vector element number after projection;
The 5th step, expands to 2 matrixes by matrix S 1, the stochastic error square formation EX of L × L dimension, the standard value square formation EY of L × L dimension, L>D;
The 6th step, solves the generalized inverse matrix of EX, is designated as IEX, IEX premultiplication matrix EY is obtained to the higher dimensional space projection matrix PEX=IEX × EY of face characteristic vector, at user side storage projection matrix P1 and PEX;
Face biological secret key has been trained;
Face biological secret key Extraction parts concrete steps are:
The first step, user is by camera collection frontal faces image, and frontal faces is adjusted voluntarily by user, gathers environmental requirement at the abundant environment of indoor light;
Second step, carries out gray processing processing to facial image, the consistent size of setting while adjusting image size for unified size and the training of face biological secret key;
The 3rd step, asks facial image from quotient graph;
The 4th step, will transfer row vector to from quotient graph image, the projection matrix P1 of storage while getting the training of face biological secret key, and premultiplication projection matrix P1, obtains the proper vector of face in feature space, is designated as Z, and length is D;
The 5th step, expands to 1 × L dimension matrix EZ by vector Z, and premultiplication PEX matrix, obtains 1 × L dimensional vector ED;
The 6th step, carries out further stable processing by chessboard method to the numerical value in vectorial ED, and getting front DL number is worth 1 × DL dimensional vector EE, DL≤D; By splicing before and after the numerical value of each element in vectorial EE, generate face biological secret key.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410075104.9A CN103886235B (en) | 2014-03-03 | 2014-03-03 | Face image biological key generating method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410075104.9A CN103886235B (en) | 2014-03-03 | 2014-03-03 | Face image biological key generating method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103886235A true CN103886235A (en) | 2014-06-25 |
CN103886235B CN103886235B (en) | 2017-02-22 |
Family
ID=50955124
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410075104.9A Active CN103886235B (en) | 2014-03-03 | 2014-03-03 | Face image biological key generating method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103886235B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104639528A (en) * | 2014-11-19 | 2015-05-20 | 中国联合网络通信集团有限公司 | DBA (database administrator) mobile client counterattack method and DBA mobile client counterattack device |
CN107852325A (en) * | 2015-07-02 | 2018-03-27 | 高通股份有限公司 | For promoting to measure the apparatus and method for generating encryption key from biometric |
CN110517182A (en) * | 2019-08-29 | 2019-11-29 | 海南大学 | A kind of medical image zero watermarking embedding grammar based on NSCT combined transformation |
CN110990849A (en) * | 2019-11-20 | 2020-04-10 | 维沃移动通信有限公司 | Encryption and decryption method for private data and terminal |
CN111144352A (en) * | 2019-12-30 | 2020-05-12 | 杭州电子科技大学 | Safe transmission and recognition method for intelligent induction of face image |
CN111723395A (en) * | 2020-05-11 | 2020-09-29 | 华南理工大学 | Portrait biological characteristic privacy protection and decryption method |
CN112949576A (en) * | 2021-03-29 | 2021-06-11 | 北京京东方技术开发有限公司 | Attitude estimation method, attitude estimation device, attitude estimation equipment and storage medium |
CN114726506A (en) * | 2021-01-04 | 2022-07-08 | 腾讯科技(深圳)有限公司 | Data encryption method and device, computer equipment and storage medium |
CN116647335A (en) * | 2023-05-26 | 2023-08-25 | 中国大唐集团财务有限公司 | Method and device for generating private key through scene based on discrete cosine transform |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1297553A (en) * | 1998-12-14 | 2001-05-30 | 皇家菲利浦电子有限公司 | Biometric identification mechanism that preserves integrity of biometric information |
CN101459518A (en) * | 2008-12-01 | 2009-06-17 | 清华大学 | Digital cipher extraction and protection method based on biological characteristic |
CN101976321A (en) * | 2010-09-21 | 2011-02-16 | 北京工业大学 | Generated encrypting method based on face feature key |
US8422746B2 (en) * | 2009-04-28 | 2013-04-16 | Samsung Electro-Mechanics Co., Ltd. | Face authentication system and authentication method thereof |
-
2014
- 2014-03-03 CN CN201410075104.9A patent/CN103886235B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1297553A (en) * | 1998-12-14 | 2001-05-30 | 皇家菲利浦电子有限公司 | Biometric identification mechanism that preserves integrity of biometric information |
CN101459518A (en) * | 2008-12-01 | 2009-06-17 | 清华大学 | Digital cipher extraction and protection method based on biological characteristic |
US8422746B2 (en) * | 2009-04-28 | 2013-04-16 | Samsung Electro-Mechanics Co., Ltd. | Face authentication system and authentication method thereof |
CN101976321A (en) * | 2010-09-21 | 2011-02-16 | 北京工业大学 | Generated encrypting method based on face feature key |
Non-Patent Citations (1)
Title |
---|
毋立芳等: ""基于人脸特征密钥生成的身份认证系统"", 《中国科技论文在线》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104639528A (en) * | 2014-11-19 | 2015-05-20 | 中国联合网络通信集团有限公司 | DBA (database administrator) mobile client counterattack method and DBA mobile client counterattack device |
CN107852325A (en) * | 2015-07-02 | 2018-03-27 | 高通股份有限公司 | For promoting to measure the apparatus and method for generating encryption key from biometric |
CN110517182A (en) * | 2019-08-29 | 2019-11-29 | 海南大学 | A kind of medical image zero watermarking embedding grammar based on NSCT combined transformation |
CN110990849A (en) * | 2019-11-20 | 2020-04-10 | 维沃移动通信有限公司 | Encryption and decryption method for private data and terminal |
CN111144352A (en) * | 2019-12-30 | 2020-05-12 | 杭州电子科技大学 | Safe transmission and recognition method for intelligent induction of face image |
CN111144352B (en) * | 2019-12-30 | 2023-05-05 | 杭州电子科技大学 | Intelligent sensing-oriented safe transmission and identification method for face images |
CN111723395A (en) * | 2020-05-11 | 2020-09-29 | 华南理工大学 | Portrait biological characteristic privacy protection and decryption method |
CN111723395B (en) * | 2020-05-11 | 2022-11-18 | 华南理工大学 | Portrait biological characteristic privacy protection and decryption method |
CN114726506A (en) * | 2021-01-04 | 2022-07-08 | 腾讯科技(深圳)有限公司 | Data encryption method and device, computer equipment and storage medium |
CN112949576A (en) * | 2021-03-29 | 2021-06-11 | 北京京东方技术开发有限公司 | Attitude estimation method, attitude estimation device, attitude estimation equipment and storage medium |
CN112949576B (en) * | 2021-03-29 | 2024-04-23 | 北京京东方技术开发有限公司 | Attitude estimation method, apparatus, device and storage medium |
CN116647335A (en) * | 2023-05-26 | 2023-08-25 | 中国大唐集团财务有限公司 | Method and device for generating private key through scene based on discrete cosine transform |
Also Published As
Publication number | Publication date |
---|---|
CN103886235B (en) | 2017-02-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103886235A (en) | Face image biological key generating method | |
CN102938767B (en) | The fuzzy keyword search methodology that efficiently can verify that based on the outer packet system of cloud data | |
CN104168112B (en) | A kind of key generation method based on multi-modal biological characteristic | |
Gaddam et al. | Efficient Cancelable Biometric Key Generation Scheme for Cryptography. | |
CN102510330B (en) | Novel fuzzy vault method based on fingerprint characteristic data and matching algorithm | |
CN102215223B (en) | Fuzzy strong box remote identity authentication method based on face feature | |
CN111178408B (en) | Health monitoring model construction method and system based on federal random forest learning | |
CN104298973A (en) | Face image rotation method based on autoencoder | |
Groza et al. | SAPHE: simple accelerometer based wireless pairing with heuristic trees | |
CN103873234B (en) | Biological quantum secret key distribution method oriented to wireless body area network | |
CN105981050A (en) | Method and system for exacting face features from data of face images | |
CN103870810A (en) | Method for generating human digital vein biometric key | |
CN103873253B (en) | Method for generating human fingerprint biometric key | |
CN112801054B (en) | Face recognition model processing method, face recognition method and device | |
CN105337725A (en) | Key management device and key management method | |
CN103873254A (en) | Method for generating human vocal print biometric key | |
CN103258156A (en) | Method for generating secret key on basis of fingerprint characteristics | |
CN107659398A (en) | Suitable for Android symmetric encryption method | |
CN102710417B (en) | Fuzzy vault method based on fingerprint features and Internet key exchange protocol | |
CN103929425A (en) | Identity registration and identity authentication method, device and system | |
CN104038347B (en) | The signature verification method sampled based on Gauss | |
CN111934852A (en) | AES password chip electromagnetic attack method and system based on neural network | |
CN104009973A (en) | Fingerprint detail information hiding and recovering method based on set polynomial conversion and harmonics | |
CN113779615B (en) | Safe decentralized diagram federation learning method | |
CN107294705A (en) | A kind of method, equipment and the system of key generation and checking |
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 |