CN113591636A - Fingerprint feature based revocable template protection technology design method - Google Patents
Fingerprint feature based revocable template protection technology design method Download PDFInfo
- Publication number
- CN113591636A CN113591636A CN202110817339.0A CN202110817339A CN113591636A CN 113591636 A CN113591636 A CN 113591636A CN 202110817339 A CN202110817339 A CN 202110817339A CN 113591636 A CN113591636 A CN 113591636A
- Authority
- CN
- China
- Prior art keywords
- revocable
- template
- fingerprint
- bit string
- minutiae
- 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
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- 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
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioethics (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention designs an irreversible but changeable function or parameter based on fingerprint characteristics and an encoding algorithm to encrypt fingerprint information, converts an original fingerprint characteristic template into a transformation template, and generates a fingerprint characteristic revocable template. The revocable templates designed by the invention have lower matching degree, so that the possibility of recovering the original fingerprint characteristics through the cross matching of the fingerprint characteristic templates transformed by the same fingerprint characteristic is avoided; and through the irreversible design of the cryptographic algorithm, even if an attacker acquires the revocable template in the fingerprint identification system, the original fingerprint characteristics of the user cannot be recovered through the revocable template. Therefore, the revocable template protection technology designed by the invention has safety, can protect the original fingerprint characteristic information of the user from being stolen and lost, can protect the privacy of the user identity, and can prevent the identity information of the user from being tracked.
Description
Technical Field
The invention relates to the technical field of fingerprint identification security, in particular to a design method of a revocable template protection technology based on fingerprint characteristics.
Background
The existing template protection technology based on revocable is mainly divided into three categories: a biological hash algorithm, a template deformation technology, and a theory and a method based on auxiliary data.
(1) The basic idea of the biological hash algorithm is to use wavelet Fourier transform characteristics of a fingerprint image and a group of pseudo random numbers in a user identity token to carry out iterative inner product to generate a user binary number sequence, and the purpose of identity authentication is achieved by comparing the binary sequence. However, since the high-distinguishability fixed-length features required by the algorithm are difficult to extract from the fingerprint, the authentication performance cannot be guaranteed under the condition of random number loss.
(2) The template deformation technology is a method for carrying out geometric change through a fingerprint minutiae template. And determining a straight line for folding by searching singular points of the fingerprint, and mapping the minutiae on one side of the straight line to the other side to obtain the deformed template. Due to the need to detect singular points, which are difficult to detect accurately, associated errors are introduced.
(3) A typical representation of the theory and method based on auxiliary data is a fuzzy safe scheme. The fuzzy safe is the most classical practical scheme in the field of fingerprint feature encryption, but the algorithm has the security defect that a fingerprint template can be obtained by cross matching of a plurality of vaults generated by the same fingerprint.
Disclosure of Invention
The invention aims to provide a fingerprint feature based revocable template protection technology design method, which aims to solve the problem of how to ensure that the original fingerprint features of a user are not acquired when a feature template is lost or leaked in a fingerprint identification system, and can quickly update and generate the fingerprint feature template and ensure the identity authentication function of the fingerprint identification system.
The invention provides a fingerprint feature based revocable template protection technology design method, which comprises the following steps:
s1, generating revocable templates:
s11, extracting fingerprint features of the registered fingerprint to obtain minutiae, and generating a minutiae set V through coordinate system transformation and screening;
s12, mapping the detail point set V to a two-dimensional polar coordinate grid to generate a bit string set B;
s13, establishing a three-layer feedforward neural network; taking a bit string set B as input, randomly generating a pseudo-random matrix R by using a user PIN code, and taking a result B' multiplied by the pseudo-random matrix R after the bit string set B is transformed as output, so as to train the three-layer feedforward neural network to obtain a weight matrix W and generate a revocable template { W, R };
s2, template matching:
s21, performing the same operation as the generation of the revocable template on the verification fingerprint to generate a bit string set b;
s22, inputting a bit string set b and a weight matrix W corresponding to the registered fingerprint into the three-layer feedforward neural network to obtain an output result Y of the three-layer feedforward neural network; reading a pseudo-random matrix R generated by a user PIN code in a revocable template (W, R), and calculating a result b' of multiplying the bit string set b by the pseudo-random matrix R after the bit string set b is converted; carrying out matching evaluation by calculating the similarity of Y and b';
and S23, if the revocable template is lost, replacing a user PIN code, and generating a weight matrix once to obtain a new revocable template.
Further, step S11 includes the following sub-steps:
s111, extracting minutiae after image enhancement and refinement of the registered fingerprints; each detail point is denoted as mi={xi,yi,θiWhere i represents the minutiae's ordinal number, xiAbscissa, y, representing the ith minutiae pointiDenotes the ordinate, θ, of the ith minutiae pointiRepresents the angle of the ith minutia point; the set of all minutiae points isn is the number of the detail points;
s112, arbitrarily taking a minutiae mi={xi,yi,θiTaking the reference detail point as the origin of a rectangular coordinate system; sequentially carrying out coordinate system transformation on the remaining n-1 minutiae points, and recording the minutiae points to be processed as mj={xj,yj,θjAnd f, the detail point after the coordinate system transformation is mij={xij,yij,θijTherein of
xij=(xj-xi)cosθi+(yj-yi)sinθi
yij=(xj-xi)sinθi-(yj-yi)cosθi
S113, calculating all the remaining n-1 minutiae points relative to the reference minutiae point miIs a distance ofWith reference to minutiae miAs a center of a circle, dminTo a set minimum spacing, dmaxFor a set maximum distance, screen out the positions respectively dminAnd dmaxDetail points within concentric circles of radius, notedWherein r is the screened effective minutiae;
s114, after the current reference detail point is processed in the steps S112 to S113, the next detail point is replaced to be used as the reference detail point, and the steps S112 to S113 are repeated for all the detail points obtained in the step S111 to obtain a detail point set
Further, step S12 includes the following sub-steps:
s121, constructing a two-dimensional polar coordinate grid:
the grid unit length of the two-dimensional polar coordinate grid is l, and the grid unit width is b;
s122, mapping the detail point set V into the two-dimensional polar coordinate grid, wherein the mapping relation is as follows:
x′ij、y′ijrespectively mapping the detail points in the detail point set V to position coordinates in the two-dimensional polar coordinate grid, marking all places with detail points in the two-dimensional polar coordinate grid as 1 and other places as 0, and reading out the bit string B according to the sequence of j from small to largeiThen, changing reference point, repeating the operation to obtain bit string set
Further, step S13 includes: establishing a three-layer feedforward neural network NN; using bit string set B as input, using user PIN code to randomly generate pseudo-random matrix R ═ Rm×tConverting the bit string set B into Bt×1A 1 to Bt×1Multiplying with a pseudo-random matrix R to obtain B ═ Rm×t·Bt×1Taking B' as an output; for each bit string B in the set of bit strings BiInput, before passing through three layersNN output of feed neural network corresponding to B'iTraining a weight matrix WiPerforming this operation on all bit strings in the bit string set B to obtain a weight matrixThereby generating a revocable template W, R.
Further, step S22 includes: set bit stringInputting a weight matrix W corresponding to the registered fingerprint into the three layers of feedforward neural networks NN to obtain an output result Y of the three layers of feedforward neural networks NN; reading a pseudo-random matrix R ═ R generated by a user PIN code in a revocable template { W, R }m×tConverting the bit string set b into bt×1B is mixingt×1Multiplying with a pseudo-random matrix R to obtain b ═ Rm×t·bt×1(ii) a Carrying out matching evaluation by calculating the similarity of Y and b'; the method for calculating the similarity of Y and b' comprises the following steps: and calculating cosine values of included angles of Y and b' to obtain the similarity.
Further, the formula for calculating the similarity between Y and b' in step S22 is as follows:
where S represents the similarity of Y and b', the closer S is to 1 indicating the more matched the verification fingerprint is to the enrollment fingerprint.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
the revocable templates designed by the invention have lower matching degree, so that the possibility of recovering the original fingerprint characteristics through the cross matching of the fingerprint characteristic templates transformed by the same fingerprint characteristic is avoided; and through the irreversible design of the cryptographic algorithm, even if an attacker acquires the revocable template in the fingerprint identification system, the original fingerprint characteristics of the user cannot be recovered through the revocable template. Therefore, the revocable template protection technology designed by the invention has safety, can protect the original fingerprint characteristic information of the user from being stolen and lost, can protect the privacy of the user identity, and can prevent the identity information of the user from being tracked.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention, and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a flowchart of a design method of a revocable template protection technique based on fingerprint features according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Examples
As shown in fig. 1, the present embodiment provides a method for designing a revocable template protection technology based on fingerprint features, which includes the following steps:
s1, generating revocable templates:
s11, extracting fingerprint features of the registered fingerprint to obtain minutiae, and generating a minutiae set V through coordinate system transformation and screening; specifically, the method comprises the following steps:
s111, extracting minutiae after image enhancement and refinement of the registered fingerprints; each detail point is denoted as mi={xi,yi,θiWhere i represents the minutiae's ordinal number, xiAbscissa, y, representing the ith minutiae pointiDenotes the ordinate, θ, of the ith minutiae pointiRepresents the angle of the ith minutia point; the set of all minutiae points isn is the number of the detail points;
s112, arbitrarily taking a minutiae mi={xi,yi,θiTaking the reference detail point as the origin of a rectangular coordinate system; sequentially carrying out coordinate system transformation on the remaining n-1 minutiae points, and recording the minutiae points to be processed as mj={xj,yj,θjAnd f, the detail point after the coordinate system transformation is mij={xij,yij,θijTherein of
xij=(xj-xi)cosθi+(yj-yi)sinθi
yij=(xj-xi)sinθi-(yj-yi)cosθi
S113, calculating all the remaining n-1 minutiae points relative to the reference minutiae point miIs a distance ofWith reference to minutiae miAs a center of a circle, dminTo a set minimum spacing, dmaxFor a set maximum distance, screen out the positions respectively dminAnd dmaxDetail points within concentric circles of radius, notedWherein r is the screened effective minutiae;
s114, after the current reference detail point is processed in the steps S112 to S113, the next detail point is replaced to be used as the reference detail point, and the steps S112 to S113 are repeated for all the detail points obtained in the step S111 to obtain a detail point set
S12, mapping the detail point set V to a two-dimensional polar coordinate grid to generate a bit string set B; specifically, the method comprises the following steps:
s121, constructing a two-dimensional polar coordinate grid:
the grid unit length of the two-dimensional polar coordinate grid is l, and the grid unit width is b;
s122, mapping the detail point set V into the two-dimensional polar coordinate grid, wherein the mapping relation is as follows:
x′ij、y′ijrespectively mapping the detail points in the detail point set V to position coordinates in the two-dimensional polar coordinate grid, marking all places with detail points in the two-dimensional polar coordinate grid as 1 and other places as 0, and reading out the ratio according to the sequence of j from small to largeSpecial string BiThen, changing reference point, repeating the operation to obtain bit string set
S13, establishing a three-layer feedforward neural network NN; using bit string set B as input, using user PIN code to randomly generate pseudo-random matrix R ═ Rm×tConverting the bit string set B into Bt×1A 1 to Bt×1Multiplying with a pseudo-random matrix R to obtain B ═ Rm×t·Bt×1Taking B' as an output; for each bit string B in the set of bit strings BiInputting, and outputting corresponding B 'through a three-layer feedforward neural network NN'iTraining a weight matrix WiPerforming this operation on all bit strings in the bit string set B to obtain a weight matrixGenerating a revocable template { W, R };
s2, template matching:
s21, generating a bit string set by performing the same operation on the verification fingerprint as the generation of the revocable template
S22, collecting the bit stringInputting a weight matrix W corresponding to the registered fingerprint into the three layers of feedforward neural networks NN to obtain an output result Y of the three layers of feedforward neural networks NN; reading a pseudo-random matrix R ═ R generated by a user PIN code in a revocable template { W, R }m×tConverting the bit string set b into bt×1B is mixingt×1Multiplying with a pseudo-random matrix R to obtain b ═ Rm×t·bt×1(ii) a Carrying out matching evaluation by calculating the similarity of Y and b'; the method for calculating the similarity of Y and b' comprises the following steps: the similarity is obtained by calculating the cosine value of the included angle between Y and b', and the formula is as follows:
where S represents the similarity of Y and b', the closer S is to 1 indicating the more matched the verification fingerprint is to the enrollment fingerprint.
And S23, if the revocable template is lost, replacing a user PIN code, and generating a weight matrix once to obtain a new revocable template.
According to the content, the matching degree of the revocable templates designed by the invention is lower, and the possibility of recovering the original fingerprint characteristics through the cross matching of the fingerprint characteristic templates transformed by the same fingerprint characteristic is avoided; and through the irreversible design of the cryptographic algorithm, even if an attacker acquires the revocable template in the fingerprint identification system, the original fingerprint characteristics of the user cannot be recovered through the revocable template. Therefore, the revocable template protection technology designed by the invention has safety, can protect the original fingerprint characteristic information of the user from being stolen and lost, can protect the privacy of the user identity, and can prevent the identity information of the user from being tracked.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. A method for designing a revocable template protection technology based on fingerprint characteristics is characterized by comprising the following steps:
s1, generating revocable templates:
s11, extracting fingerprint features of the registered fingerprint to obtain minutiae, and generating a minutiae set V through coordinate system transformation and screening;
s12, mapping the detail point set V to a two-dimensional polar coordinate grid to generate a bit string set B;
s13, establishing a three-layer feedforward neural network; taking a bit string set B as input, randomly generating a pseudo-random matrix R by using a user PIN code, and taking a result B' multiplied by the pseudo-random matrix R after the bit string set B is transformed as output, so as to train the three-layer feedforward neural network to obtain a weight matrix W and generate a revocable template { W, R };
s2, template matching:
s21, performing the same operation as the generation of the revocable template on the verification fingerprint to generate a bit string set b;
s22, inputting a bit string set b and a weight matrix W corresponding to the registered fingerprint into the three-layer feedforward neural network to obtain an output result Y of the three-layer feedforward neural network; reading a pseudo-random matrix R generated by a user PIN code in a revocable template (W, R), and calculating a result b' of multiplying the bit string set b by the pseudo-random matrix R after the bit string set b is converted; carrying out matching evaluation by calculating the similarity of Y and b';
and S23, if the revocable template is lost, replacing a user PIN code, and generating a weight matrix once to obtain a new revocable template.
2. The fingerprint-based revocable template protection technology design method of claim 1, wherein the step S11 comprises the following sub-steps:
s111, extracting minutiae after image enhancement and refinement of the registered fingerprints; each detail point is denoted as mi={xi,yi,θiWhere i represents the minutiae's ordinal number, xiAbscissa, y, representing the ith minutiae pointiDenotes the ordinate, θ, of the ith minutiae pointiRepresents the angle of the ith minutia point; the set of all minutiae points isn is the number of the detail points;
s112, arbitrarily taking a minutiae mi={xi,yi,θiTaking the reference detail point as the origin of a rectangular coordinate system; sequentially transforming the coordinate system of the remaining n-1 detail points to be processedThe minutiae points are recorded as mj={xj,yj,θjAnd f, the detail point after the coordinate system transformation is mij={xij,yij,θijTherein of
xij=(xj-xi)cosθi+(yj-yi)sinθi
yij=(xj-xi)sinθi-(yj-yi)cosθi
S113, calculating all the remaining n-1 minutiae points relative to the reference minutiae point miIs a distance ofWith reference to minutiae miAs a center of a circle, dminTo a set minimum spacing, dmaxFor a set maximum distance, screen out the positions respectively dminAnd dmaxDetail points within concentric circles of radius, notedWherein r is the screened effective minutiae;
3. The fingerprint-based revocable template protection technology design method of claim 2, wherein the step S12 comprises the following sub-steps:
s121, constructing a two-dimensional polar coordinate grid:
the grid unit length of the two-dimensional polar coordinate grid is l, and the grid unit width is b;
s122, mapping the detail point set V into the two-dimensional polar coordinate grid, wherein the mapping relation is as follows:
x′ij、y′ijrespectively mapping the detail points in the detail point set V to position coordinates in the two-dimensional polar coordinate grid, marking all places with detail points in the two-dimensional polar coordinate grid as 1 and other places as 0, and reading out the bit string B according to the sequence of j from small to largeiThen, changing reference point, repeating the operation to obtain bit string set
4. The fingerprint-based revocable template protection technology designing method of claim 3, wherein the step S13 comprises: establishing a three-layer feedforward neural network NN; using bit string set B as input, using user PIN code to randomly generate pseudo-random matrix R ═ Rm×tConverting the bit string set B into Bt×1A 1 to Bt×1Multiplying with a pseudo-random matrix R to obtain B ═ Rm×t·Bt×1Taking B' as an output; for each bit string B in the set of bit strings BiInputting, and outputting corresponding B 'through a three-layer feedforward neural network NN'iTraining a weight matrix WiPerforming this operation on all bit strings in the bit string set B to obtain a weight matrixThereby generating a revocable template W, R.
5. The fingerprint-based revocable template protection technology designing method of claim 4, wherein the step S22 comprises: set bit stringInputting a weight matrix W corresponding to the registered fingerprint into the three layers of feedforward neural networks NN to obtain an output result Y of the three layers of feedforward neural networks NN; reading a pseudo-random matrix R ═ R generated by a user PIN code in a revocable template { W, R }m×tConverting the bit string set b into bt×1B is mixingt×1Multiplying with a pseudo-random matrix R to obtain b ═ Rm×t·bt×1(ii) a Carrying out matching evaluation by calculating the similarity of Y and b'; the method for calculating the similarity of Y and b' comprises the following steps: and calculating cosine values of included angles of Y and b' to obtain the similarity.
6. The design method of revocable template protection technology based on fingerprint features of claim 5, wherein the formula for calculating the similarity of Y and b' in step S22 is as follows:
where S represents the similarity of Y and b', the closer S is to 1 indicating the more matched the verification fingerprint is to the enrollment fingerprint.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110817339.0A CN113591636B (en) | 2021-07-20 | 2021-07-20 | Fingerprint feature-based revocable template protection technology design method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110817339.0A CN113591636B (en) | 2021-07-20 | 2021-07-20 | Fingerprint feature-based revocable template protection technology design method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113591636A true CN113591636A (en) | 2021-11-02 |
CN113591636B CN113591636B (en) | 2023-04-07 |
Family
ID=78248251
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110817339.0A Active CN113591636B (en) | 2021-07-20 | 2021-07-20 | Fingerprint feature-based revocable template protection technology design method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113591636B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103279697A (en) * | 2013-05-15 | 2013-09-04 | 电子科技大学 | Fingerprint detail information hiding and restoring method based on orthogonal matrix and modular arithmetic |
CN106936586A (en) * | 2016-12-07 | 2017-07-07 | 中国电子科技集团公司第三十研究所 | A kind of biological secret key extracting method based on fingerprint bit string and Error Correction of Coding |
CN108960039A (en) * | 2018-05-07 | 2018-12-07 | 西安电子科技大学 | A kind of irreversible fingerprint template encryption method based on symmetrical hash |
-
2021
- 2021-07-20 CN CN202110817339.0A patent/CN113591636B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103279697A (en) * | 2013-05-15 | 2013-09-04 | 电子科技大学 | Fingerprint detail information hiding and restoring method based on orthogonal matrix and modular arithmetic |
CN106936586A (en) * | 2016-12-07 | 2017-07-07 | 中国电子科技集团公司第三十研究所 | A kind of biological secret key extracting method based on fingerprint bit string and Error Correction of Coding |
CN108960039A (en) * | 2018-05-07 | 2018-12-07 | 西安电子科技大学 | A kind of irreversible fingerprint template encryption method based on symmetrical hash |
Also Published As
Publication number | Publication date |
---|---|
CN113591636B (en) | 2023-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Abdullahi et al. | Fractal coding-based robust and alignment-free fingerprint image hashing | |
Liu et al. | Finger vein secure biometric template generation based on deep learning | |
Sandhya et al. | Biometric template protection: A systematic literature review of approaches and modalities | |
Sandhya et al. | k-Nearest Neighborhood Structure (k-NNS) based alignment-free method for fingerprint template protection | |
Ali et al. | Robust technique for fingerprint template protection | |
CN101777115A (en) | Safe fingerprint verification method and system | |
Lutsenko et al. | Biometric cryptosystems: overview, state-of-the-art and perspective directions | |
CN101814131A (en) | Method for improving security of fuzzy fingerprint safe | |
Liu et al. | Minutiae and modified biocode fusion for fingerprint-based key generation | |
Benhammadi et al. | Password hardened fuzzy vault for fingerprint authentication system | |
Nafea et al. | Hybrid multi-biometric template protection using watermarking | |
US9129142B2 (en) | Method and system for generating a representation of a finger print minutiae information | |
Selwal et al. | Low overhead octet indexed template security scheme for multi-modal biometric system | |
Appati et al. | Implementation of a Transform‐Minutiae Fusion‐Based Model for Fingerprint Recognition | |
Salama et al. | Cancelable biometric system for IoT applications based on optical double random phase encoding | |
Chitra et al. | Security analysis of prealigned fingerprint template using fuzzy vault scheme | |
Lalithamani et al. | An effective scheme for generating irrevocable cryptographic key from cancelable fingerprint templates | |
Moon et al. | Improved cancelable fingerprint templates using minutiae‐based functional transform | |
Selwal et al. | A scheme for template security at feature fusion level in multimodal biometric system | |
Topcu et al. | Fixed-length asymmetric binary hashing for fingerprint verification through GMM-SVM based representations | |
Djebli et al. | Quantized random projections of SIFT features for cancelable fingerprints | |
Singh et al. | FDFNet: A secure cancelable deep finger dorsal template generation network secured via. bio-hashing | |
CN113591636B (en) | Fingerprint feature-based revocable template protection technology design method | |
Nandini et al. | Efficient cryptographic key generation from fingerprint using symmetric hash functions | |
Patil et al. | Wet and dry fingerprint enhancement by using multi resolution technique |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |