CN108664859A - Refer to vein identification method and system - Google Patents
Refer to vein identification method and system Download PDFInfo
- Publication number
- CN108664859A CN108664859A CN201710209064.6A CN201710209064A CN108664859A CN 108664859 A CN108664859 A CN 108664859A CN 201710209064 A CN201710209064 A CN 201710209064A CN 108664859 A CN108664859 A CN 108664859A
- Authority
- CN
- China
- Prior art keywords
- image
- finger vein
- vein image
- coding
- model
- 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.)
- Pending
Links
Classifications
-
- 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
-
- 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
- G06V40/14—Vascular patterns
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
A kind of finger vein identification method of present invention offer and system, method include：Acquisition refers to vein image, and is pre-processed to the finger vein image；Image coding is carried out to pretreated finger vein image, encoding model is established according to image coding and is preserved；All coding characteristics of finger vein image to be identified are extracted, and it is slightly matched with encoding model, obtain the degree of correlation for referring to each position and the aspect of model in vein image；Matching result is obtained according to the degree of correlation；By establishing iconic model to referring to after vein image carries out image coding in the present invention, it can be used in the finger hand vein recognition in the case of complicated image, the performance of collecting device is relied on relatively low, avoid the feature heavy losses of the finger vena in conventional method, it is especially important characteristic point such as crosspoint and loses serious problem, present invention optimization is apparent, improves timeliness and practicability to referring to vein image identification technology.
Description
Technical field
The present invention relates to hand vein recognition field more particularly to a kind of finger vein identification method and systems.
Background technology
Refer to one kind that hand vein recognition is hand vein recognition, it is subcutaneously shallow through finger using blood stream to refer to vein biometric identification technology
The vascular distribution pattern formed when table blood vessel carries out identity authentication method, generally use is by referring to vein as biological characteristic
Identifier obtains personal finger vena distribution map, extracts characteristic value from finger vena distribution map according to special alignment algorithm, passes through
Near infrared light irradiates, and the image of finger vena is obtained using CCD camera, the digital picture of finger vena is stored in calculating
In machine system, characteristic value is stored.It is the dynamic being made of blood flow to refer to vein unlike fingerprint static state biometric image
Image, it is a kind of vivo identification technology, relies primarily on Infrared irradiation finger and obtains blood vessel lines, is formed by blood flow
A kind of live body password, medical research proves, the shape of finger vena has uniqueness and stability, i.e., everyone finger it is quiet
Arteries and veins image is different from, and the vein image of the different finger of same person also differs；The vein shape of normal adults is no longer
It changes.This just provides medicine foundation to refer to vein.Relative to the transreplication of fingerprint recognition, refer to vein biometric identification skill
The breakthrough of art becomes now the most accurately " live body " biological identification technology, and this feature will disappear after being detached from human body
It loses, therefore is difficult to be stolen.In current numerous biological identification technologies, it is security level and technical indicator highest to refer to vein technology
, use habit is similar with fingerprint, is widely applied and will be the following body in most of field supplement or alternative fingerprint technique
The trend of part identification.However the finger vena identification in currently available technology also exists as follows technical problem：
One, finger venous image is handled.The main purpose of image procossing is to carry out image analysis for people, finger vena
Image is to be shot by CCD camera and obtained, due to being influenced by various factors, what same person acquired in different situations
Image has very big difference.Therefore, image procossing occupies considerable status in finger vena identifies whole process, while
It is the difficulties in finger vein recognition system.
Two, the feature extraction of finger venous image.From image, the image distribution of human finger vein is similar " tree "
The structure of shape, to obtain the higher recognition result of precision, effective extraction of vein pattern is just particularly important.The prior art
In, the extraction of finger vein features is all first then to obtain image binaryzation, such methods make portion by thinning algorithm
The feature heavy losses for dividing finger vena, are especially important characteristic point such as crosspoint etc..Therefore, there is an urgent need for a kind of new technology hands
Section, to overcome above-mentioned technical problem.
Invention content
In view of the foregoing deficiencies of prior art, the purpose of the present invention is to provide one kind in view of this, the present invention carries
For a kind of finger vein identification method and system, to solve the above technical problems.
Finger vein identification method provided by the invention, including：Acquisition refers to vein image, and is carried out to the finger vein image
Pretreatment；Image coding is carried out to pretreated finger vein image, encoding model is established according to image coding and is preserved；Extraction
All coding characteristics of finger vein image to be identified, and it is slightly matched with encoding model, acquisition refers in vein image
The degree of correlation of each position and the aspect of model；Matching result is obtained according to the degree of correlation；
Further, pretreatment includes：The finger vein image of acquisition is normalized.
Further, pretreatment further includes：Local contrast enhancing is carried out to the finger vein image after normalization, and to enhancing
Finger vein image afterwards carries out Gaussian Blur processing.
Further, further include：
Read encoding model；Finger vein image to be identified is acquired, and extracts its aspect of model；
The aspect of model of finger vein image to be identified is matched with encoding model, obtains finger vein figure to be identified
The degree of correlation of each position to be matched as in；
The maximum matching position of the degree of correlation is obtained, and as thick matching result.
Further, further include after step：C4. according to the thick matching result, obtain the feature locations of images to be recognized with
The offset between the feature locations after corresponding thick matching in encoding model calculates maximum relevance degree and by the correlation
Angle value is as smart matching result.
Further, further include：
According to pretreated finger vein image, the integrogram for referring to vein image is obtained；
Each integrogram for referring to vein image is divided into several subgraphs, the subgraph is made of continuously arranged grid；
By being encoded to the subgraph, the feature coding of each subgraph is obtained, according to all sons in finger vein image
The feature coding of figure establishes corresponding encoding model.
The present invention also provides a kind of finger vein recognition systems, including：
Collecting unit refers to vein image for acquiring；
Pretreatment unit is pre-processed for the finger vein image to acquisition；
Coding unit encodes according to image for carrying out image coding to pretreated finger vein image and establishes coding
Model；
Storage unit, for preserving encoding model；
Matching unit, all aspect of model of the finger vein image to be identified for that will extract and encoding model progress
Match, obtains the degree of correlation of each position to be matched, and matching result is obtained according to the degree of correlation.
Further, the pretreatment unit includes：
Subelement is normalized, is normalized for the finger vein image to acquisition；
Contrast enhanson, for carrying out local contrast enhancing to the finger vein image after normalization, and to increasing
Finger vein image after strong carries out Gaussian Blur processing.
Further, the matching unit includes：
Reading subunit for reading encoding model and acquiring finger vein image to be identified, and extracts its model spy
Sign；
Thick matching unit is obtained for matching the aspect of model of finger vein image to be identified with encoding model
The degree of correlation for referring to each position to be matched in vein image to be identified, obtains the maximum matching position of the degree of correlation, and made
For thick matching result；
Smart matching unit, for according to the thick matching result, obtaining the feature locations and encoding model of images to be recognized
In corresponding thick matching after feature locations between offset, calculate maximum relevance degree and using the relevance degree as
Smart matching result.
Further, the coding unit includes：
Integrogram subelement will be every for according to pretreated finger vein image, obtaining the integrogram for referring to vein image
A integrogram for referring to vein image is divided into several subgraphs, and the subgraph is made of continuously arranged grid；
Coding modeling subelement, for by being encoded to the subgraph, obtaining the feature coding of each subgraph, according to
The feature coding for referring to all subgraphs in vein image, establishes corresponding encoding model.
Beneficial effects of the present invention：Finger vein identification method and system in the present invention to referring to vein image by carrying out figure
As establishing iconic model after coding, it can be used in the finger hand vein recognition in the case of complicated image, the performance of collecting device relied on
It is relatively low, the feature heavy losses of the finger vena in conventional method are avoided, characteristic point such as crosspoint is especially important and damages
Serious problem is lost, the present invention can extract abundant finger vein pattern, have maximum effect, this hair for screening more details
Bright optimization is apparent, improves timeliness and practicability to referring to vein image identification technology, for following finger vein identification technology
Quick comparison popularization and application established theoretical developments basis.
Description of the drawings
Fig. 1 is the Method And Principle schematic diagram of the present invention.
Fig. 2 is the method flow schematic diagram of the present invention.
Fig. 3 is the system structure diagram of the present invention.
Specific implementation mode
Illustrate that embodiments of the present invention, those skilled in the art can be by this specification below by way of specific specific example
Disclosed content understands other advantages and effect of the present invention easily.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also be based on different viewpoints with application, without departing from
Various modifications or alterations are carried out under the spirit of the present invention.It should be noted that in the absence of conflict, following embodiment and implementation
Feature in example can be combined with each other.
It should be noted that the diagram provided in following embodiment only illustrates the basic structure of the present invention in a schematic way
Think, component count, shape and size when only display is with related component in the present invention rather than according to actual implementation in schema then
Draw, when actual implementation kenel, quantity and the ratio of each component can be a kind of random change, and its assembly layout kenel
It is likely more complexity.
As shown in Figure 1, the finger vein identification method in the present embodiment includes：
A. acquisition refers to vein image, and is pre-processed to the finger vein image；
B. image coding is carried out to pretreated finger vein image, encoding model is established according to image coding and preserved；
C. all coding characteristics of finger vein image to be identified are acquired, and it is matched with encoding model, are obtained
Refer to the degree of correlation of each position and the aspect of model in vein image；
D. matching result is obtained according to the degree of correlation.
In the present embodiment, it includes image intelligent enhancing, image coding and feature recognition three to refer to vein identification method mainly
The enhancing of part, wherein image intelligent includes being pre-processed to the image of acquisition, locally refers to vein image by pre-processing realization
Contrast enhancing.Thick matching result in the present embodiment is to capture a large amount of characteristic blocks in image to be identified to compare concentration
And the feature and template expressed are almost the same.
As shown in Fig. 2, the pretreatment in step a in the present embodiment includes：
A1. the finger vein image of acquisition is normalized；
A2. local contrast enhancing is carried out to the finger vein image after normalization, part is carried out to the image after normalization
Contrast enhances, mainly local histogram's acceleration technique and the new histogram equalization techniques used in the present embodiment；
A3. Gaussian Blur processing, issuable noise in compacting enhancing are carried out to enhanced finger vein image.
The present embodiment carries out local contrast enhancing to the image after normalization, and the mainly local histogram used accelerates
Technology and histogram equalization techniques present embodiments provide best image enhancement technique, can do local auto-adaptive contrast
Promoted, will drown out under low contrast largely refer to venous information highlight, while by for finger vein image coding,
Directly handle enhanced image so that details is extracted to the greatest extent.It can be made in the present embodiment by image enhancement
Refer to vein identification method and can be used in the finger hand vein recognition in the case of complicated image, the performance of collecting device is relied on relatively low.
Step b in the present embodiment is specifically included：
B1. according to pretreated finger vein image, the integrogram for referring to vein image is obtained；
B2. each integrogram for referring to vein image is divided into several subgraphs, the subgraph is by continuously arranged grid group
At；
B3. by being encoded to the subgraph, the feature coding of each subgraph is obtained, is owned according to referring in vein image
The feature coding of subgraph establishes corresponding encoding model.
Preferably, the present embodiment is by calculating the integrogram of image, and to each subgraph, encodes the code word in 8 neighborhoods, press
Certain regularly arranged one feature coding of composition together, each feature coding is grouped together, and is made with decimal number
For model, trained model is preserved.Such as：Each subgraph is divided into the grid of u × v, then removing four sides of this subgraph
Except the grid at angle, other each grids have 8 neighborhoods, because to consider the problems of illumination and rotation robustness, the present embodiment
Using by the gray scale aggregate-value of 8 neighborhoods of grid sort or with median than the similar LBP algorithms of size by the way of, such as：
If u × v=8 × 8, which just has 6 × 6 grids to have complete 8 neighborhood, this 6 × 6 each grid is counted
The coding is calculated, a subgraph just is spelled to get up to form by 6 × 6 codings, and therefore, each coding has independent mapping, with coding
Model corresponds.Matched feature not instead of gray feature in the present embodiment, the feature after gray-coded, can be effective
Reduction calculation amount, increase robustness.
Step c is specifically included in the present embodiment：
C1. encoding model is read；Finger vein image to be identified is acquired, and extracts its aspect of model；
C2. the aspect of model of finger vein image to be identified is matched with encoding model, it is quiet obtains finger to be identified
The degree of correlation of each position to be matched in arteries and veins image；
C3. the maximum matching position of the degree of correlation is obtained, and as thick matching result.
C4. according to the thick matching result, the feature locations for obtaining images to be recognized are corresponding in encoding model thick
The offset between feature locations after matching calculates maximum relevance degree and using the relevance degree as smart matching result.
In the present embodiment, feature extraction is carried out to finger vein image to be identified and traditional Niblack two-values may be used
Change and refines to obtain vein texture, it is special to the curvature feature of texture feature extraction on this basis, such as sift or curve
Technology that more deep learnings put forward feature, such as drop out etc. can be added in sign extraction, reject the inefficient feature in part,
In the present embodiment, the acquisition modes of offset may be used Fast Fourier Transform and other may be implemented above-mentioned function its
His mode, the present embodiment is by coordinating a set of completely new most fast registration technique based on Fourier transform to make overall technology side
The robustness of case can cope with extremely complex scene completely.
Correspondingly, the present embodiment also provides a kind of finger vein recognition system in technique, as shown in figure 3, including：
Collecting unit refers to vein image for acquiring；
Pretreatment unit is pre-processed for the finger vein image to acquisition；
Coding unit encodes according to image for carrying out image coding to pretreated finger vein image and establishes coding
Model；
Storage unit, for preserving encoding model；
Matching unit, all aspect of model of the finger vein image to be identified for that will extract and encoding model progress
Match, obtains the degree of correlation of each position to be matched, and matching result is obtained according to the degree of correlation.
The pretreatment unit includes：
Subelement is normalized, is normalized for the finger vein image to acquisition；
Contrast enhanson, for carrying out local contrast enhancing to the finger vein image after normalization, and to increasing
Finger vein image after strong carries out Gaussian Blur processing.
The matching unit includes：
Reading subunit for reading encoding model and acquiring finger vein image to be identified, and extracts its model spy
Sign；
Thick matching unit is obtained for matching the aspect of model of finger vein image to be identified with encoding model
The degree of correlation for referring to each position to be matched in vein image to be identified, obtains the maximum matching position of the degree of correlation, and made
For thick matching result；
Smart matching unit, for according to the thick matching result, obtaining the feature locations and encoding model of images to be recognized
In corresponding thick matching after feature locations between offset, calculate maximum relevance degree and using the relevance degree as
Smart matching result.
The coding unit includes：
Integrogram subelement will be every for according to pretreated finger vein image, obtaining the integrogram for referring to vein image
A integrogram for referring to vein image is divided into several subgraphs, and the subgraph is made of continuously arranged grid；
Coding modeling subelement, for by being encoded to the subgraph, obtaining the feature coding of each subgraph, according to
The feature coding for referring to all subgraphs in vein image, establishes corresponding encoding model.
A specific embodiment is set forth below to be described in detail：
Collecting unit acquisition refers to vein image A1, A2, A3 ... An, and pretreatment unit is located in advance to referring to vein image
Reason, enhancing locally refer to the contrast of vein image, and coding unit carries out image coding to pretreated finger vein image, according to
Image coding establishes encoding model, such as：The encoding model for referring to vein image A1 is A11, A12, A13 ... A1N, wherein A11,
A12, A13 ... A1N refer respectively to the feature coding of the subgraph of vein image integrogram, extract a finger vein image to be identified
There are several aspect of model m1, m2, m3 ... mn in a1, these aspect of model and trained encoding model are carried out one by one
Match, if the result after matching is the feature A13 and finger vein image a1 to be identified referred in vein image A1 in encoding model
In the m3 degrees of correlation it is maximum, then will be using feature A13 as thick matching result, thick matching result is that each feature locations generate one
Matching value.Based on slightly matching corresponding subgraph position, using Fourier transform, quickly essence matching obtains offset, will calculate
Rear maximum relevance degree is as smart matching result, that is to say, that final matching result be in encoding model with figure to be identified
As matched position is most and the maximum finger vein image of the degree of correlation.Existing skill may be used in collecting unit in the present embodiment
Arbitrary collecting device in art, therefore the performance of collecting device is relied on relatively low.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.It is any ripe
The personage for knowing this technology can all carry out modifications and changes to above-described embodiment without violating the spirit and scope of the present invention.Cause
This, institute is complete without departing from the spirit and technical ideas disclosed in the present invention by those of ordinary skill in the art such as
At all equivalent modifications or change, should by the present invention claim be covered.
Claims (10)
1. a kind of finger vein identification method, which is characterized in that including：
Acquisition refers to vein image, and is pre-processed to the finger vein image；
Image coding is carried out to pretreated finger vein image, encoding model is established according to image coding and is preserved；
All coding characteristics of finger vein image to be identified are extracted, and it is slightly matched with encoding model, acquisition refers to quiet
The degree of correlation of each position and the aspect of model in arteries and veins image；
Matching result is obtained according to the degree of correlation.
2. finger vein identification method according to claim 1, which is characterized in that the pretreatment includes：To the finger of acquisition
Vein image is normalized.
3. finger vein identification method according to claim 2, which is characterized in that the pretreatment further includes：To normalization
Finger vein image afterwards carries out local contrast enhancing, and carries out Gaussian Blur processing to enhanced finger vein image.
4. according to the finger vein identification method described in claim 1-3 any claims, which is characterized in that described extract waits knowing
It is other to refer to all aspect of model of vein image, and it is matched with encoding model, obtain the phase of each position to be matched
Guan Du is specifically included：
Read encoding model；Finger vein image to be identified is acquired, and extracts its aspect of model；
The aspect of model of finger vein image to be identified is matched with encoding model, is obtained in finger vein image to be identified
The degree of correlation of each position to be matched；
The maximum matching position of the degree of correlation is obtained, and as thick matching result.
5. finger vein identification method according to claim 4, which is characterized in that the maximum match bit of the acquisition degree of correlation
Set, and as thick matching result after, further include：According to the thick matching result, the feature locations of images to be recognized are obtained
The offset between feature locations after thick matching corresponding in encoding model calculates maximum relevance degree and by the phase
Angle value is closed as smart matching result.
6. according to the finger vein identification method described in claim 1-3 any claims, which is characterized in that described pair of pretreatment
Finger vein image afterwards carries out image coding, establishes encoding model according to image coding and preserves, specifically includes：
According to pretreated finger vein image, the integrogram for referring to vein image is obtained；
Each integrogram for referring to vein image is divided into several subgraphs, the subgraph is made of continuously arranged grid；
By being encoded to the subgraph, the feature coding of each subgraph is obtained, according to all subgraphs in finger vein image
Feature coding establishes corresponding encoding model.
7. a kind of finger vein recognition system, which is characterized in that including：
Collecting unit refers to vein image for acquiring；
Pretreatment unit is pre-processed for the finger vein image to acquisition；
Coding unit establishes encoding model for carrying out image coding to pretreated finger vein image according to image coding；
Storage unit, for preserving encoding model；
Matching unit, for all aspect of model of the finger vein image to be identified of extraction to be matched with encoding model,
The degree of correlation of each position to be matched is obtained, and matching result is obtained according to the degree of correlation.
8. finger vein recognition system according to claim 7, which is characterized in that the pretreatment unit includes：
Subelement is normalized, is normalized for the finger vein image to acquisition；
Contrast enhanson, for after normalization finger vein image carry out local contrast enhancing, and to enhancing after
Finger vein image carry out Gaussian Blur processing.
9. finger vein recognition system according to claim 7 or 8, which is characterized in that the matching unit includes：
Reading subunit for reading encoding model and acquiring finger vein image to be identified, and extracts its aspect of model；
Thick matching unit obtains for matching the aspect of model of finger vein image to be identified with encoding model and waits knowing
The degree of correlation of each position to be matched in other finger vein image obtains the maximum matching position of the degree of correlation, and as thick
Matching result；
Smart matching unit is used for according to the thick matching result, in the feature locations and encoding model that obtain images to be recognized
The offset between feature locations after corresponding thick matching calculates maximum relevance degree and using the relevance degree as essence
With result.
10. finger vein recognition system according to claim 7 or 8, which is characterized in that the coding unit includes：
Integrogram subelement, for according to pretreated finger vein image, obtaining the integrogram for referring to vein image, will each refer to
The integrogram of vein image is divided into several subgraphs, and the subgraph is made of continuously arranged grid；
Coding modeling subelement, it is quiet according to referring to for by being encoded to the subgraph, obtaining the feature coding of each subgraph
The feature coding of all subgraphs in arteries and veins image, establishes corresponding encoding model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710209064.6A CN108664859A (en) | 2017-03-31 | 2017-03-31 | Refer to vein identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710209064.6A CN108664859A (en) | 2017-03-31 | 2017-03-31 | Refer to vein identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108664859A true CN108664859A (en) | 2018-10-16 |
Family
ID=63784016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710209064.6A Pending CN108664859A (en) | 2017-03-31 | 2017-03-31 | Refer to vein identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108664859A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109766836A (en) * | 2019-01-11 | 2019-05-17 | 防灾科技学院 | A kind of finger hand vein recognition unlocking method and system |
| CN109800702A (en) * | 2019-01-16 | 2019-05-24 | 北京智慧眼科技股份有限公司 | Refer to the rapid comparison method and computer-readable storage medium of hand vein recognition |
| CN110619302A (en) * | 2019-09-16 | 2019-12-27 | Oppo广东移动通信有限公司 | Vein identification method and related product |
| CN110717469A (en) * | 2019-10-16 | 2020-01-21 | 山东浪潮人工智能研究院有限公司 | Finger vein identification method and system based on correlation semantic feature learning |
| CN112217938A (en) * | 2019-07-09 | 2021-01-12 | 深圳企示录信息科技有限公司 | Business card sharing method and related products |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101002682A (en) * | 2007-01-19 | 2007-07-25 | 哈尔滨工程大学 | Method for retrieval and matching of hand back vein characteristic used for identification of status |
| CN102254165A (en) * | 2011-08-12 | 2011-11-23 | 北方工业大学 | Hand back vein identification method based on fusion of structural coding features and texture coding features |
| CN102411711A (en) * | 2012-01-04 | 2012-04-11 | 山东大学 | Finger vein recognition method based on individualized weight |
| CN102651074A (en) * | 2012-02-22 | 2012-08-29 | 大连理工大学 | Texture feature-based printed paper identification method |
| CN103679172A (en) * | 2013-10-10 | 2014-03-26 | 南京理工大学 | Method for detecting long-distance ground moving object via rotary infrared detector |
| CN104036260A (en) * | 2014-06-30 | 2014-09-10 | 山东大学 | Finger joint grain identification method based on Gabor - band-limited phase-only correlation |
-
2017
- 2017-03-31 CN CN201710209064.6A patent/CN108664859A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101002682A (en) * | 2007-01-19 | 2007-07-25 | 哈尔滨工程大学 | Method for retrieval and matching of hand back vein characteristic used for identification of status |
| CN102254165A (en) * | 2011-08-12 | 2011-11-23 | 北方工业大学 | Hand back vein identification method based on fusion of structural coding features and texture coding features |
| CN102411711A (en) * | 2012-01-04 | 2012-04-11 | 山东大学 | Finger vein recognition method based on individualized weight |
| CN102651074A (en) * | 2012-02-22 | 2012-08-29 | 大连理工大学 | Texture feature-based printed paper identification method |
| CN103679172A (en) * | 2013-10-10 | 2014-03-26 | 南京理工大学 | Method for detecting long-distance ground moving object via rotary infrared detector |
| CN104036260A (en) * | 2014-06-30 | 2014-09-10 | 山东大学 | Finger joint grain identification method based on Gabor - band-limited phase-only correlation |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109766836A (en) * | 2019-01-11 | 2019-05-17 | 防灾科技学院 | A kind of finger hand vein recognition unlocking method and system |
| CN109800702A (en) * | 2019-01-16 | 2019-05-24 | 北京智慧眼科技股份有限公司 | Refer to the rapid comparison method and computer-readable storage medium of hand vein recognition |
| CN109800702B (en) * | 2019-01-16 | 2021-01-26 | 智慧眼科技股份有限公司 | Quick comparison method for finger vein identification and computer readable storage medium |
| CN112217938A (en) * | 2019-07-09 | 2021-01-12 | 深圳企示录信息科技有限公司 | Business card sharing method and related products |
| CN112217938B (en) * | 2019-07-09 | 2022-08-05 | 深圳心慧科技有限公司 | Business card sharing method and related products |
| CN110619302A (en) * | 2019-09-16 | 2019-12-27 | Oppo广东移动通信有限公司 | Vein identification method and related product |
| CN110717469A (en) * | 2019-10-16 | 2020-01-21 | 山东浪潮人工智能研究院有限公司 | Finger vein identification method and system based on correlation semantic feature learning |
| CN110717469B (en) * | 2019-10-16 | 2022-04-12 | 山东浪潮科学研究院有限公司 | Finger vein identification method and system based on correlation semantic feature learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108664859A (en) | Refer to vein identification method and system | |
| CN108009520A (en) | A kind of finger vein identification method and system based on convolution variation self-encoding encoder neutral net | |
| CN103870808B (en) | Finger vein identification method | |
| Kim et al. | Illumination normalization for SIFT based finger vein authentication | |
| Liu et al. | An efficient finger-vein extraction algorithm based on random forest regression with efficient local binary patterns | |
| Wang et al. | Hand vein recognition based on multiple keypoints sets | |
| CN107832739A (en) | A kind of palm vein identification system and method based on ORB feature extractions | |
| Kang et al. | The biometric recognition on contactless multi-spectrum finger images | |
| Singh et al. | Iris recognition system using a canny edge detection and a circular hough transform | |
| CN105760841A (en) | Identify recognition method and identify recognition system | |
| Patil et al. | A survey on Iris recognition system | |
| Cancian et al. | An embedded Gabor-based palm vein recognition system | |
| Ting et al. | A review of finger vein recognition system | |
| Yang et al. | $\alpha $-Trimmed Weber Representation and Cross Section Asymmetrical Coding for Human Identification Using Finger Images | |
| Uriarte-Antonio et al. | Vascular biometrics based on a minutiae extraction approach | |
| Kekre et al. | An effectual method for extraction of ROI of palmprints | |
| Benziane et al. | Dorsal hand vein identification based on binary particle swarm optimization | |
| CN106295622A (en) | A kind of recognition methods based on hand back vein | |
| Khodadoust et al. | Design and implementation of a multibiometric system based on hand’s traits | |
| Zhichao et al. | Two modality-based bi-finger vein verification system | |
| Rajan et al. | A novel finger vein feature extraction technique for authentication | |
| Rossan et al. | Impact of changing parameters when preprocessing dorsal hand vein pattern | |
| Chihaoui et al. | Human identification system based on the detection of optical Disc Ring in retinal images | |
| Yang et al. | Feature-level fusion of finger veins and finger dorsal texture for personal authentication based on orientation selection | |
| Malutan et al. | Dorsal hand vein recognition based on Riesz Wavelet Transform and Local Line Binary Pattern |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181016 |
|
| RJ01 | Rejection of invention patent application after publication |