CN108133198A - A kind of extracting method and its extraction element based on finger vein features point - Google Patents
A kind of extracting method and its extraction element based on finger vein features point Download PDFInfo
- Publication number
- CN108133198A CN108133198A CN201810024329.XA CN201810024329A CN108133198A CN 108133198 A CN108133198 A CN 108133198A CN 201810024329 A CN201810024329 A CN 201810024329A CN 108133198 A CN108133198 A CN 108133198A
- Authority
- CN
- China
- Prior art keywords
- point
- minutiae
- minutiae point
- image
- vein
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- 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
Abstract
The invention discloses a kind of extracting methods and its extraction element based on finger vein features point, include the following steps:Step 1:Under the irradiation of infrared light supply, finger venous image is acquired using sensor devices;Step 2:By adjusting infrared light supply lambda1-wavelength and video camera wavelength can receptive field, obtain the finger venous image that meets the requirements of brightness;Step 3:By n pending image of the parameter acquisition that step 2 determines, n pending image is subjected to micronization processes;Step 4:It redefines vein minutiae feature and includes endpoint, bifurcation and double bifurcations, to using M*M square formations at the details dot center of treated n width images, the position of determination details point and type calculate the angle between angle and minutiae point and the horizontal line between the branch of minutiae point;Step 5:Screening needs the minutiae point extracted to be characterized a little from the minutiae point of detection.Advantageous effect is to state the type that method has redefined characteristic point, can improve the accuracy of acquisition characteristics and can obtain the more characteristic point with important information, help to improve the accuracy of hand vein recognition.
Description
Technical field
The present invention relates to biometrics identification technology field, refer in particular to a kind of extracting method based on finger vein features point and
Its extraction element.
Background technology
Finger vein identification technology is a kind of novel biometrics identification technology, because of the finger vein features of user
It is difficult to be replicated, therefore security level is high, it is well suited for the high place of safety requirements and uses.
The process of finger vena identification is that infrared light supply generates Infrared irradiation on the finger of picker, by infrared
Vein pattern is extracted in the acquisition of video camera from the image of acquisition, then carries out characteristic matching, it is achieved thereby that finger vena is known
Not.
One of committed step of finger vena identification is the extraction of vein pattern point.Vein image is straight in vein blood vessel
Diameter, veinprint etc. all exist obtains greatly difference very much, these differences can be retouched by the topological structure of vein, minutiae point
It states, therefore finger vein identification method can be probably summarized as:
Recognition methods based on vein image topological structure.It in the past can be in face of the result of finger venous image micronization processes
Find out, the topological structure of finger vena is highly stable, contains abundant vein pattern information, can carry out identity knowledge enough
Not, but this method has some shortcomings, and for different finger placement locations, the topological structure extracted has small inclined
Move, to improve discrimination, during template is stored, need for a vein image need to store it is several small range into
Row translation and the different templates of rotation, increase memory space.
Meanwhile be different from details in fingerprint point extracting method and be very different with referring to vein minutiae extraction algorithm, in fingerprint
In, the position of crestal line is very close to but different for vein pattern, the distance between vein is distant, and vein image is not
It can obtain the field of direction in a region.
Invention content
Present invention aims at provide a kind of extracting method and its extraction element based on finger vein features point, Neng Gouti
The stability of high vein pattern point extraction, and the important information feature of finger vena can be preserved, memory space is reduced, and with feature
Relevant information between point is as basis of characterization.
In order to achieve the above object, technical scheme of the present invention has:
A kind of extracting method based on finger vein features point, includes the following steps:
Step 1:Under the irradiation of infrared light supply, finger venous image is acquired using sensor devices;
Step 2:By adjusting infrared light supply lambda1-wavelength and video camera wavelength can receptive field, obtain brightness expire
The finger venous image required enough;
Step 3:By n pending image of the parameter acquisition that step 2 determines, n pending image is carried out thin
Change is handled;
Step 4:It redefines vein minutiae feature and includes endpoint, bifurcation and double bifurcations, to treated n width figures
Using M*M square formations, the position of determination details point and type at the details dot center of picture, the angle between the branch of minutiae point is calculated
And the angle between minutiae point and horizontal line;
Step 5:Screening needs the minutiae point extracted to be characterized a little from the minutiae point of detection.
Further, the position of the determination details point of the step 5 and type step are as follows:
Using a M*M square formation in the image of refinement, wherein m is minutiae point to be detected, NiRepresent the neighbor point of m,
It enablesIf the value of N is 1, then it represents that minutiae point to be measured is endpoint;If the value of N is 3, table
It is bifurcation to show minutiae point to be measured;If the value of N is 4, then it represents that minutiae point to be measured is double bifurcations;During if other values, then
Represent that the tested point is not required to the minutiae point of extraction.
Further, the extraction step of the endpoint, bifurcation and double bifurcations is as follows:
The step of extracting endpoint:
Centered on any one minutiae point, extract a M*M square formation, delete other in the square formation not with the minutiae point phase
Point even calculates the connection number of its vein pattern and square formation boundary, if linking number is one, which is considered as end
Point, while the angle for calculating and preserving minutiae point between square formation boundary line formed section and horizontal line, if linking number is not one,
Then the minutiae point is considered as a wrong minutiae point or is not endpoint;
The step of extracting bifurcation and double bifurcations:
Centered on any one minutiae point, extract a M*M square formation, delete other in the square formation not with the minutiae point phase
Point even calculates the connection number of its vein pattern and square formation boundary, if linking number is three, which is considered as point
Crunode, while calculate and preserve the angle between each two contiguous branch, if linking number is four, then it is assumed that the minutiae point is
Double bifurcations, the angle between each two branch are also calculated and are preserved simultaneously, if linking number is not three or four, then it is assumed that this is thin
Node is considered as a wrong minutiae point or is not bifurcation or double bifurcations.
Further, the endpoint, bifurcation and double bifurcations are defined as follows:
Endpoint refers to the terminating point of vein skeleton line segment, when vein is in skin certain depth or when infrared light is to people
Body tissue transmission depth will appear endpoint when inadequate;
Bifurcation is the tie point that a single vein segment splits into two vein segments;
Double bifurcations be when two bifurcations relatively close to when occur.
Further, the step 2 is further thin using morphological image before the characteristics of image of extraction finger vena
Change algorithm and veinprint skeletonizing is carried out to image, the skeleton image that the image change being partitioned into is single pixel width is used for
Show the minutiae point of finger venous image.
Further, the step 4 further includes:It will be between the angle between the branch of minutiae point and minutiae point and horizontal line
Angle encryption and preserve operation.
Further, the step 5 further comprises also:Obtained characteristic point is normalized, with default mould
Template in plate library is matched, and forms final vein pattern point.
Further, the finger vein features point extracting method is encapsulated using BSP and realizes feature point extraction by matlab,
And by dynamic load and call multiple multiple applications of BSP examples parallel processing.
A kind of extraction element of application based on finger vein features point extracting method, further includes:
Acquisition module:For obtaining finger venous image, and by adjusting the lambda1-wavelength and video camera of infrared light supply
Wavelength can receptive field, obtain the finger venous image that meets the requirements of brightness, and the image is subjected to micronization processes.
Computing module:For the parameter of every minutiae point of the n width images after calculation processing, used at details dot center
M*M square formations calculate the angle between angle and minutiae point and the horizontal line between the branch of minutiae point, pass through result determination details
Point;
Matching module:For the characteristic point of extraction to be matched with the template in default template library, best is determined
With template, final vein pattern point is formed.
The acquisition module is connect with computing module, and the computing module is connect with matching module.
The beneficial effects of the present invention are:
1st, the present invention has redefined the type of characteristic point, can improve the accuracy of acquisition characteristics and can obtain compared with
There is the characteristic point of important information more, help to improve the accuracy of hand vein recognition;
2nd, the present invention saves the angle between the Eigenvector on minutiae point and square formation boundary, helps whether to judge the point
For required characteristic point;
3rd, the present invention helps to improve vein using the vein image that high quality is obtained by adjusting the wavelength of infrared light supply
Extract the accuracy of characteristic point.
Description of the drawings
Fig. 1 is the flow diagram of the present invention;
Fig. 2 is the minutiae detection template schematic diagram of the embodiment of the present invention one;
Fig. 3 is the vein details vertex type schematic diagram of the embodiment of the present invention one
Fig. 4 is the angle information schematic diagram of three kinds of minutiae points of the embodiment of the present invention one;
Fig. 5 is that the vein image minutiae point of the embodiment of the present invention one finally extracts image schematic diagram.
Specific embodiment
A kind of extracting method based on finger vein features point of the present invention is described with reference to the drawings.
Embodiment one, as shown in Figure 1, a kind of Feature Points Extraction, includes the following steps:
Step 1:Under the irradiation of infrared light supply, finger venous image is acquired using sensor devices;
Step 2:By adjusting infrared light supply lambda1-wavelength and video camera wavelength can receptive field, obtain brightness expire
The finger venous image required enough;
Step 3:By n pending image of the parameter acquisition that step 2 determines, n pending image is carried out thin
Change is handled;
Step 4:It redefines vein minutiae feature and includes endpoint, bifurcation and double bifurcations, to treated n width figures
Using M*M square formations, the position of determination details point and type at the details dot center of picture, the angle between the branch of minutiae point is calculated
And the angle between minutiae point and horizontal line;
Step 5:Screening needs the minutiae point extracted to be characterized a little from the minutiae point of detection.
Further, as shown in Fig. 2, the position of the determination details point of the step 5 and type step are as follows:
Using a M*M square formation in the image of refinement, wherein M points are minutiae points to be detected, NiRepresent the neighbouring of M points
Point,
It enablesIf the value of N is 1, then it represents that minutiae point to be measured is endpoint;If the value of N is 3, table
It is bifurcation to show minutiae point to be measured;If the value of N is 4 values, then it represents that minutiae point to be measured is double bifurcations;During if other values, then
Represent that the tested point is not required to the minutiae point of extraction.
Specifically, when refinement image using 3*3 square formation when, then Ni(i=1 ... 8) represents the point of proximity of M, makes
Use formulaAsIf the value of N is 1, then it represents that minutiae point to be measured is endpoint;If
It is 3, then it represents that minutiae point to be measured is bifurcation;If it is 4, then it represents that minutiae point to be measured is double bifurcations;If it is other values,
It is not the minutiae points to be extracted of this chapter then to represent the tested point.
Further, as shown in Figures 3 to 5, the extraction step of the endpoint, bifurcation and double bifurcations is as follows:
The step of extracting endpoint:
Centered on any one minutiae point, extract a M*M square formation, delete other in the square formation not with the minutiae point phase
Point even calculates the connection number of its vein pattern and square formation boundary, if linking number is one, which is considered as end
Point, while the angle for calculating and preserving minutiae point between square formation boundary line formed section and horizontal line, if linking number is not one,
Then the minutiae point is considered as a wrong minutiae point or is not endpoint;
The step of extracting bifurcation and double bifurcations:
Centered on any one minutiae point, extract a M*M square formation, delete other in the square formation not with the minutiae point phase
Point even calculates the connection number of its vein pattern and square formation boundary, if linking number is three, which is considered as point
Crunode, while calculate and preserve the angle between each two contiguous branch, if linking number is four, then it is assumed that the minutiae point is
Double bifurcations, the angle between each two branch are also calculated and are preserved simultaneously, if linking number is not three or four, then it is assumed that this is thin
Node is considered as a wrong minutiae point or is not bifurcation or double bifurcations.
Further, the endpoint, bifurcation and double bifurcations are defined as follows:
Endpoint refers to the terminating point of vein skeleton line segment, when vein is in skin certain depth or when infrared light is to people
Body tissue transmission depth will appear endpoint when inadequate;
Bifurcation is the tie point that a single vein segment splits into two vein segments;
Double bifurcations be when two bifurcations relatively close to when occur.
Further, as shown in Figure 4 by calculating and distinguishing above, different tables can be obtained for different minutiae points
Show method:
Endpoint:
Bifurcation:[x,y,θ1,θ2,θ3];
Double bifurcations:
Wherein x, y are the coordinates of each minutiae point,It is the angle between endpoint and horizontal line, θi It is bifurcation respectively
With the angle between double bifurcation branches.During i=1, θiRepresent minimum angle, other angle arranged clockwises.
Further, the step 2 is further thin using morphological image before the characteristics of image of extraction finger vena
Change algorithm and veinprint skeletonizing is carried out to image, the skeleton image that the image change being partitioned into is single pixel width is used for
Show the minutiae point of finger venous image.
Further, the step 4 further includes:It will be between the angle between the branch of minutiae point and minutiae point and horizontal line
Angle encryption and preserve operation.
Further, the step 5 further includes:Obtained characteristic point is normalized, and in default template library
Template matched, form final vein pattern point.
Further, the finger vein features point extracting method is encapsulated using BSP and realizes feature point extraction by matlab,
And by dynamic load and call multiple multiple applications of BSP examples parallel processing.
Preferably, BSP encapsulates the finger vena characteristic extracting method realized by matlab, then that class is embedded in unified finger is quiet
In arteries and veins recording module and authentication module, and the realization for referring to vein identification technology on algorithm and data structure is shielded, to upper strata
Application program unified interface and data structure are provided.
The collection of functions that BSP is provided both had contained the most common operation of authentication procedures, as the finger venous information of user is recorded
Enter, identities match verification etc., the processing step of more bottom is also contained, in addition, also passing through dynamic load and calling multiple BSP
Example carrys out the multiple application programs of parallel processing.
Wherein, BSP is between one layer driven in motherboard hardware and operating system between layer program, it is considered that it belongs to
An operating system part, mainly realizes the support to operating system, the driver for upper strata provides access hardware devices and posts
The function packet of storage enables preferably to run on hardware mainboard, in this programme mainly for acquisition information make bottom or
Rudimentary calculation process.
MATLAB is a kind of mathematical software, its master data unit is matrix, due to calculating involved in the present invention
Medium spacing is matrix or determinant, therefore resolves the problems in present invention than with language such as C, FORTRAN with MATLAB
It completes simpler and more direct.
A kind of extraction element of application based on finger vein features point extracting method, further includes:
Acquisition module:For obtaining finger venous image, and by adjusting the lambda1-wavelength and video camera of infrared light supply
Wavelength can receptive field, obtain the finger venous image that meets the requirements of brightness, and the image is subjected to micronization processes;
Computing module:For the parameter of every minutiae point of the n width images after calculation processing, used at details dot center
M*M square formations calculate the angle between angle and minutiae point and the horizontal line between the branch of minutiae point, pass through result determination details
Point;
Matching module:For the characteristic point of extraction to be matched with the template in default template library, best is determined
With template, final vein pattern point is formed;
The acquisition module is connect with computing module, and the computing module is connect with matching module.
The beneficial effects of the present invention are:
1st, the present invention has redefined the type of characteristic point, can improve the accuracy of acquisition characteristics and can obtain compared with
There is the characteristic point of important information more, help to improve the accuracy of hand vein recognition;
2nd, the present invention saves the angle between the Eigenvector on minutiae point and square formation boundary, helps whether to judge the point
For required characteristic point;
3rd, the present invention helps to improve vein using the vein image that high quality is obtained by adjusting the wavelength of infrared light supply
Extract the accuracy of characteristic point.
According to the disclosure and teachings of the above specification, those skilled in the art in the invention can also be to above-mentioned embodiment party
Formula is changed and is changed.Therefore, the invention is not limited in specific embodiment disclosed and described above, to the present invention's
Some modifications and changes should also be as falling into the scope of the claims of the present invention.In addition, it although is used in this specification
Some specific terms, but these terms are merely for convenience of description, do not limit the present invention in any way.
Claims (9)
1. a kind of extracting method based on finger vein features point, which is characterized in that include the following steps:
Step 1:Under the irradiation of infrared light supply, finger venous image is acquired using sensor devices;
Step 2:By adjusting infrared light supply lambda1-wavelength and video camera wavelength can receptive field, obtain brightness meet will
The finger venous image asked;
Step 3:By n pending image of the parameter acquisition that step 2 determines, n pending image is carried out at refinement
Reason;
Step 4:It redefines vein minutiae feature and includes endpoint, bifurcation and double bifurcations, to treated n width images
Using M*M square formations, the position of determination details point and type at details dot center, angle between the branch of minutiae point and thin is calculated
Angle between node and horizontal line;
Step 5:Screening needs the minutiae point extracted to be characterized a little from the minutiae point of detection.
2. extracting method according to claim 1, which is characterized in that the position of the determination details point of the step 5 and class
Type step is as follows:
Using a M*M square formation in the image of refinement, wherein m is minutiae point to be detected, NiRepresent the neighbor point of m,
It enablesIf the value of N is 1, then it represents that minutiae point to be measured is endpoint;If the value of N is 3, then it represents that treat
Survey minutiae point is bifurcation;If the value of N is 4, then it represents that minutiae point to be measured is double bifurcations;During if other values, then it represents that
The tested point is not required to the minutiae point of extraction.
3. extracting method according to claim 2, which is characterized in that the extraction of the endpoint, bifurcation and double bifurcations
Step is as follows:
The step of extracting endpoint:
Centered on any one minutiae point, a M*M square formation is extracted, deletes what other in the square formation were not connected with the minutiae point
Point calculates the connection number of its vein pattern and square formation boundary, if linking number is one, which is considered as endpoint,
The angle for calculating simultaneously and preserving minutiae point between square formation boundary line formed section and horizontal line, if linking number is not one,
The minutiae point is considered as a wrong minutiae point or is not endpoint;
The step of extracting bifurcation and double bifurcations:
Centered on any one minutiae point, a M*M square formation is extracted, deletes what other in the square formation were not connected with the minutiae point
Point calculates the connection number of its vein pattern and square formation boundary, if linking number is three, which is considered as bifurcated
Point, while calculate and preserve the angle between each two contiguous branch, if linking number is four, then it is assumed that the minutiae point is double
Bifurcation, the angle between each two branch are also calculated and are preserved simultaneously, if linking number is not three or four, then it is assumed that the details
Point is considered as a wrong minutiae point or is not bifurcation or double bifurcations.
4. extracting method according to claim 3, which is characterized in that the definition of the endpoint, bifurcation and double bifurcations
It is as follows:
Endpoint refers to the terminating point of vein skeleton line segment, when vein is in skin certain depth or when infrared light is to human body group
Knit transmission depth it is inadequate when will appear endpoint;
Bifurcation is the tie point that a single vein segment splits into two vein segments;
Double bifurcations be when two bifurcations relatively close to when occur.
5. extracting method according to claim 1, which is characterized in that the step 2 is special in the image of extraction finger vena
Before sign, veinprint skeletonizing is further carried out to image using morphological image thinning algorithm, the image being partitioned into is become
The skeleton image of single pixel width is turned to, for showing the minutiae point of finger venous image.
6. extracting method according to claim 1, which is characterized in that the step 4 further includes:By the branch of minutiae point it
Between angle and minutiae point and horizontal line between angle encryption and preserve operation.
7. extracting method according to claim 1, which is characterized in that the step 5 further includes:Obtained feature is clicked through
Row normalized is matched with the template in default template library, forms final vein pattern point.
8. extracting method according to claim 1, which is characterized in that the finger vein features point extracting method uses
BSP encapsulation realizes feature point extraction by matlab, and by dynamic load and calls multiple BSP examples parallel processing are multiple should
With.
9. a kind of extraction element using based on finger vein features point extracting method described in any one of claim 1 to 8, special
Sign is, including:
Acquisition module:For obtaining finger venous image, and by adjusting the lambda1-wavelength of infrared light supply and the wave of video camera
Length can receptive field, obtain the finger venous image that meets the requirements of brightness, and the image is subjected to micronization processes;
Computing module:For the parameter of every minutiae point of the n width images after calculation processing, M*M is used at details dot center
Square formation calculates the angle between angle and minutiae point and the horizontal line between the branch of minutiae point, passes through result determination details point;
Matching module:For the characteristic point of extraction to be matched with the template in default template library, best matching mould is determined
Plate forms final vein pattern point;
The acquisition module is connect with computing module, and the computing module is connect with matching module.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2017110601287 | 2017-11-01 | ||
CN201711060128 | 2017-11-01 |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108133198A true CN108133198A (en) | 2018-06-08 |
Family
ID=62400592
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810024329.XA Pending CN108133198A (en) | 2017-11-01 | 2018-01-10 | A kind of extracting method and its extraction element based on finger vein features point |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108133198A (en) |
Citations (8)
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 |
CN101853378A (en) * | 2010-05-24 | 2010-10-06 | 哈尔滨工程大学 | Finger vein identification method based on relative distance |
CN101866419A (en) * | 2009-04-14 | 2010-10-20 | 株式会社日立制作所 | Person authentication device |
KR101354881B1 (en) * | 2012-08-24 | 2014-02-05 | 한국오므론전장주식회사 | Apparatus and method for recognizing vein of finger |
CN103886321A (en) * | 2014-02-26 | 2014-06-25 | 中国船舶重工集团公司第七一〇研究所 | Finger vein feature extraction method |
CN105426821A (en) * | 2015-11-04 | 2016-03-23 | 浙江工业大学 | Palm vein feature extracting and matching method based on eight neighborhood and secondary matching |
CN105787417A (en) * | 2014-12-19 | 2016-07-20 | 上海箩箕技术有限公司 | Optical fingerprint imaging system and optical fingerprint imaging method |
US20170109563A1 (en) * | 2015-10-14 | 2017-04-20 | Wayne State University | Palm vein-based low-cost mobile identification system for a wide age range |
-
2018
- 2018-01-10 CN CN201810024329.XA patent/CN108133198A/en active Pending
Patent Citations (8)
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 |
CN101866419A (en) * | 2009-04-14 | 2010-10-20 | 株式会社日立制作所 | Person authentication device |
CN101853378A (en) * | 2010-05-24 | 2010-10-06 | 哈尔滨工程大学 | Finger vein identification method based on relative distance |
KR101354881B1 (en) * | 2012-08-24 | 2014-02-05 | 한국오므론전장주식회사 | Apparatus and method for recognizing vein of finger |
CN103886321A (en) * | 2014-02-26 | 2014-06-25 | 中国船舶重工集团公司第七一〇研究所 | Finger vein feature extraction method |
CN105787417A (en) * | 2014-12-19 | 2016-07-20 | 上海箩箕技术有限公司 | Optical fingerprint imaging system and optical fingerprint imaging method |
US20170109563A1 (en) * | 2015-10-14 | 2017-04-20 | Wayne State University | Palm vein-based low-cost mobile identification system for a wide age range |
CN105426821A (en) * | 2015-11-04 | 2016-03-23 | 浙江工业大学 | Palm vein feature extracting and matching method based on eight neighborhood and secondary matching |
Non-Patent Citations (2)
Title |
---|
吴作凌等: "一种近红外手背静脉图像识别算法", 《微电子学与计算机》 * |
葛彦平: "基于匹配融合的指纹与指静脉双模态生物识别技术的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10762366B2 (en) | Finger vein identification method and device | |
Han et al. | Palm vein recognition using adaptive Gabor filter | |
CN110852160B (en) | Image-based biometric identification system and computer-implemented method | |
Miura et al. | Feature extraction of finger vein patterns based on iterative line tracking and its application to personal identification | |
CN107423712B (en) | 3D face recognition method | |
Wang et al. | An automatic physical access control system based on hand vein biometric identification | |
KR20090087895A (en) | Method and apparatus for extraction and matching of biometric detail | |
US10922399B2 (en) | Authentication verification using soft biometric traits | |
CN107169479A (en) | Intelligent mobile equipment sensitive data means of defence based on fingerprint authentication | |
CN103886283A (en) | Method for fusing multi-biometric image information for mobile user and application thereof | |
CN109766836A (en) | A kind of finger hand vein recognition unlocking method and system | |
Meng et al. | Finger vein recognition based on zone-based minutia matching | |
CN110443146A (en) | Auth method, device, equipment and readable medium based on bio-identification | |
Yang et al. | $\alpha $-Trimmed Weber Representation and Cross Section Asymmetrical Coding for Human Identification Using Finger Images | |
CN108664859A (en) | Refer to vein identification method and system | |
Uriarte-Antonio et al. | Vascular biometrics based on a minutiae extraction approach | |
Pal et al. | Implementation of hand vein structure authentication based system | |
Liu et al. | Finger-vein as a biometric-based authentication | |
CN110309814A (en) | A kind of iris identification method and device based on edge detection | |
Albadarneh et al. | Iris recognition system for secure authentication based on texture and shape features | |
Rajan et al. | A novel finger vein feature extraction technique for authentication | |
CN108133198A (en) | A kind of extracting method and its extraction element based on finger vein features point | |
Cohen et al. | 3D iris model and reader for iris identification | |
Kubanek et al. | Feature extraction of palm vein patterns based on two-dimensional density function | |
Avey et al. | An FPGA-based hardware accelerator for iris segmentation |
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: 20180608 |
|
RJ01 | Rejection of invention patent application after publication |