CN110472498A - Identity identifying method, system, storage medium and equipment based on hand-characteristic - Google Patents
Identity identifying method, system, storage medium and equipment based on hand-characteristic Download PDFInfo
- Publication number
- CN110472498A CN110472498A CN201910616396.5A CN201910616396A CN110472498A CN 110472498 A CN110472498 A CN 110472498A CN 201910616396 A CN201910616396 A CN 201910616396A CN 110472498 A CN110472498 A CN 110472498A
- Authority
- CN
- China
- Prior art keywords
- hand
- characteristic
- image
- finger
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 239000013598 vector Substances 0.000 claims abstract description 337
- 210000003462 vein Anatomy 0.000 claims abstract description 226
- 210000001145 finger joint Anatomy 0.000 claims abstract description 120
- 230000004927 fusion Effects 0.000 claims description 38
- 238000004590 computer program Methods 0.000 claims description 14
- 210000001015 abdomen Anatomy 0.000 claims description 9
- 238000013475 authorization Methods 0.000 claims description 5
- 230000004907 flux Effects 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 description 17
- 108090000623 proteins and genes Proteins 0.000 description 10
- 241000905957 Channa melasoma Species 0.000 description 9
- 238000003384 imaging method Methods 0.000 description 9
- 239000000284 extract Substances 0.000 description 6
- 238000002156 mixing Methods 0.000 description 6
- 206010010356 Congenital anomaly Diseases 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 210000001367 artery Anatomy 0.000 description 1
- 208000030757 autosomal dominant osteopetrosis Diseases 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000001605 fetal effect Effects 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 210000001161 mammalian embryo Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- ZWLUXSQADUDCSB-UHFFFAOYSA-N phthalaldehyde Chemical compound O=CC1=CC=CC=C1C=O ZWLUXSQADUDCSB-UHFFFAOYSA-N 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
- G06V40/12—Fingerprints or palmprints
- G06V40/1365—Matching; Classification
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention relates to a kind of identity identifying method based on hand-characteristic, system, storage medium and equipment.This method comprises: obtaining the hand-characteristic image of target to be identified, hand-characteristic image carries target identification, and hand-characteristic image includes finger pulp vein image, dorsal digital vein image, refers to band image, finger-joint print image；Hand characteristic image is pre-processed, the feature vector of hand-characteristic is obtained to pretreated hand-characteristic image zooming-out, the feature vector of hand-characteristic includes finger pulp vein pattern vector, dorsal digital vein feature vector, refers to striations characteristic vector, finger-joint print feature vector；The feature vector of hand-characteristic corresponding with target identification is matched with registration hand-characteristic sample in registration hand-characteristic database, obtains matching result；The corresponding identity authentication result of target to be identified is determined according to matching result.Of the invention is not easy to be stolen, and identification accuracy is high, and identification result remains stability.
Description
Technical field
The present invention relates to human body biological characteristics identification technology field more particularly to a kind of authentications based on hand-characteristic
Method, system, storage medium and equipment.
Background technique
With the development of science and technology, person identification and certification have become the fundamental of every field, wherein base
It is paid close attention in the authentication increasingly hand of biological characteristic.Authentication based on biological characteristic is exactly to utilize life specific to the mankind
It manages feature and behavioural characteristic carries out authentication.The prior art carries out identification, such as hand life using single creature feature
Hand shape, finger-type, fingerprint, finger vena of object feature etc., but identification is carried out using single creature feature and is easily stolen, identifies
Accuracy is not high, stability is not high.
Summary of the invention
Based on this, it is necessary in view of the above-mentioned problems, propose a kind of identity identifying method based on hand-characteristic, system,
Storage medium and equipment.
In a first aspect, the present invention provides a kind of identity identifying methods based on hand-characteristic, which comprises
The hand-characteristic image of target to be identified is obtained, the hand-characteristic image carries target identification, the hand
Characteristic image includes finger pulp vein image, dorsal digital vein image, refers to band image, finger-joint print image；
The hand-characteristic image is pre-processed, hand-characteristic is obtained to pretreated hand-characteristic image zooming-out
Feature vector, the feature vector of the hand-characteristic includes finger pulp vein pattern vector, dorsal digital vein feature vector, refers to band
Feature vector, finger-joint print feature vector；
Registration hand in the feature vector of hand-characteristic corresponding with target identification and registration hand-characteristic database is special
Sign sample is matched, and matching result is obtained；
The corresponding identity authentication result of the target to be identified is determined according to the matching result.
Further, the feature vector by hand-characteristic corresponding with target identification and registration hand-characteristic database
Middle registration hand-characteristic sample is matched, and matching result is obtained, comprising:
By and the feature vector of the corresponding hand-characteristic of target identification merge to obtain hand-characteristic corresponding with target identification
Feature vector fusion value；
It will be in the feature vector fusion value of the hand-characteristic corresponding with target identification and registration hand-characteristic database
Feature vector fusion value is matched, and matching result is obtained.
Further, the feature vector by hand-characteristic corresponding with target identification and registration hand-characteristic database
Middle registration hand-characteristic sample is matched, and matching result is obtained, comprising:
It calculates every in the feature vector and the registration hand-characteristic database of the corresponding hand-characteristic of the target identification
It is a registration hand-characteristic sample vector between Vectors matching value, the Vectors matching value include: finger pulp vein Vectors matching value,
Dorsal digital vein Vectors matching value refers to band Vectors matching value, finger-joint print Vectors matching value；
Matching fusion value corresponding with each registration hand-characteristic sample vector is calculated according to the Vectors matching value,
The matching result is determined according to the matching fusion value.
Further, it is described be calculated according to the Vectors matching value it is corresponding with each registration hand-characteristic sample vector
Matching fusion value, the matching result is determined according to the matching fusion value, comprising:
Obtain Vectors matching threshold value, the Vectors matching threshold value include: finger pulp vein Vectors matching threshold value, dorsal digital vein to
Flux matched threshold value refers to band Vectors matching threshold value, finger-joint print Vectors matching threshold value；
Finger pulp vein Vectors matching value and finger pulp vein Vectors matching threshold value, dorsal digital vein Vectors matching value and finger is quiet and secluded
Arteries and veins Vectors matching threshold value refers to band Vectors matching value and refers to band Vectors matching threshold value, finger-joint print Vectors matching value and refer to and closes
Section line Vectors matching threshold value is compared to obtain comparison result；
When comparison result is that any one is lower than Vectors matching threshold value, the matching fusion value is assigned a value of zero；
When comparison result is all not less than Vectors matching threshold value, corresponding with the same registration hand-characteristic sample
Finger pulp vein Vectors matching value, dorsal digital vein Vectors matching value refer to that band Vectors matching value, finger-joint print Vectors matching value carry out
Fusion obtains matching fusion value.
Further, the feature vector by hand-characteristic corresponding with target identification and registration hand-characteristic database
When middle registration hand-characteristic sample is matched, the finger pulp vein pattern vector weight is not less than finger striations characteristic vector weight
And finger-joint print feature vector weight, the dorsal digital vein feature vector weight is not less than finger striations characteristic vector weight and refers to pass
Save line feature vector weight.
Further, described that the hand-characteristic image is pre-processed, pretreated hand-characteristic image is mentioned
The feature vector of hand-characteristic is obtained, the feature vector of the hand-characteristic includes finger pulp vein pattern vector, dorsal digital vein
Feature vector refers to striations characteristic vector, finger-joint print feature vector, comprising:
Hand-characteristic image after obtaining binaryzation according to the hand-characteristic image；
Finger pulp vein image after binaryzation is extracted to obtain finger pulp vein pattern vector；
Dorsal digital vein feature vector is obtained to the dorsal digital vein image zooming-out after binaryzation；
Finger band image zooming-out after binaryzation is obtained to refer to striations characteristic vector；
Finger-joint print image after binaryzation is extracted to obtain finger-joint print feature vector.
Further, the hand-characteristic image for obtaining target to be identified, the hand-characteristic image carry target
Mark, the hand-characteristic image include finger pulp vein image, dorsal digital vein image, refer to band image, finger-joint print image, are wrapped
It includes:
The finger of target to be identified is put into image capturing area；
Abdomen and back to the finger of the target to be identified are shot simultaneously, obtain the finger pulp of digital signal form
Vein image, dorsal digital vein image refer to band image, finger-joint print image, the finger pulp vein image, dorsal digital vein image,
Refer to that band image, finger-joint print image carry identical target identification.
Further, the hand-characteristic image for obtaining target to be identified, the hand-characteristic image carry target
Mark, the hand-characteristic image include finger pulp vein image, dorsal digital vein image, refer to band image, finger-joint print image, are wrapped
It includes:
The palm of target to be identified is opened naturally and is put into image capturing area；
Abdomen and back to all fingers of target to be identified are shot simultaneously, obtain the institute of digital signal form
There is the finger pulp vein image of finger, dorsal digital vein image, refer to band image, finger-joint print image；
According to the finger pulp vein image of all fingers, dorsal digital vein image, refer to that band image, finger-joint print image identify
Same root finger corresponding finger pulp vein image, refers to band image, finger-joint print image, same root finger at dorsal digital vein image
The corresponding finger pulp vein image, refers to that band image, finger-joint print image carry identical target mark at dorsal digital vein image
Know.
Further, the method also includes: according to application scenarios, multiple Permission Levels, the acquisition of different rights grade are set
The finger hand-characteristic of various combination carries out authentication.
Second aspect, the present invention also provides a kind of identity authorization system based on hand-characteristic, the system comprises:
Hand-characteristic sample module is registered, for recording the registration hand-characteristic sample；
Image capture module, for obtaining the hand-characteristic image of target to be identified, the hand-characteristic image is carried
Target identification, the hand-characteristic image include finger pulp vein image, dorsal digital vein image, refer to band image, finger-joint print figure
Picture；
Characteristic vector pickup module, it is special to pretreated hand for being pre-processed to the hand-characteristic image
Sign image zooming-out obtains the feature vector of hand-characteristic, the feature vector of the hand-characteristic include finger pulp vein pattern vector,
Dorsal digital vein feature vector refers to striations characteristic vector, finger-joint print feature vector；
Authentication module, for by the feature vector of hand-characteristic corresponding with target identification and registration hand-characteristic number
It is matched according to hand-characteristic sample is registered in library, obtains matching result；The mesh to be identified is determined according to the matching result
Mark corresponding identity authentication result.
The third aspect, the present invention also provides a kind of storage mediums, are stored with computer program of instructions, and the computer refers to
When program being enabled to be executed by processor, so that the step of processor executes first aspect the method.
Fourth aspect, the present invention also provides a kind of computer equipments, including at least one processor, at least one processing
Device, the memory is stored with computer program of instructions, when the computer program of instructions is executed by the processor, so that institute
State the step of processor executes first aspect the method.
In conclusion a kind of identity identifying method based on hand-characteristic of the invention passes through the finger pulp vein of hand-characteristic
Image, dorsal digital vein image refer to that band image, finger-joint print image extract finger pulp vein pattern vector after pre-processing, refer to back
Vein pattern vector refers to striations characteristic vector, finger-joint print feature vector, by finger pulp vein pattern vector, dorsal digital vein feature
Vector, refer to striations characteristic vector, finger-joint print feature vector and registration hand-characteristic database in registration hand-characteristic sample into
Authentication is realized in row matching.Due to referring to that band determines that folding line is coarse, direction is single by gene, not vulnerable to noise jamming,
It is not easy to be stolen for identification, accuracy is high, stability is high；Finger-joint print texture structure is relatively single, mostly
It is made of vertical line, oblique line, camber line etc., due to the congenital heredity gene of human individual, the difference of posteriori living habit and environment
The difference for being formed by finger-joint print has preferable distinction, be not easy to be stolen for identification, accuracy it is high；By mixed
It closes using finger pulp vein, dorsal digital vein, refer to that band, finger-joint print carry out identification, be not easy to be stolen, further improve body
Part recognition accuracy, stability.Therefore, the identity identifying method of the invention based on hand-characteristic is not easy to be stolen, and identity is known
Other accuracy is high, and identification result remains stability.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Wherein:
Fig. 1 is the flow chart of the identity identifying method based on hand-characteristic in one embodiment；
Fig. 2 is to be matched to obtain the flow chart of matching result in one embodiment；
Fig. 3 is to be matched to obtain the flow chart of matching result in another embodiment；
Fig. 4 is the flow chart that matching fusion value is obtained in one embodiment；
Fig. 5 is the flow chart that the hand-characteristic image of target to be identified is obtained in one embodiment；
Fig. 6 is the flow chart that the hand-characteristic image of target to be identified is obtained in another embodiment；
Fig. 7 is the structural block diagram of the identity authorization system based on hand-characteristic in one embodiment；
Fig. 8 is the structural block diagram of computer equipment in one embodiment.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
As shown in Figure 1, in one embodiment, providing a kind of identity identifying method based on hand-characteristic, this method
By the finger pulp vein image of hand-characteristic, dorsal digital vein image, refer to band image, finger-joint print image pretreatment after extract
Finger pulp vein pattern vector, refers to striations characteristic vector, finger-joint print feature vector at dorsal digital vein feature vector, by finger pulp vein
Feature vector, dorsal digital vein feature vector refer to striations characteristic vector, finger-joint print feature vector and registration hand-characteristic database
Middle registration hand-characteristic sample carries out matching and realizes authentication.Due to referring to that band is determined by gene, folding line is coarse, direction
It is single, not vulnerable to noise jamming, it is not easy to be stolen for identification, accuracy is high, stability is high；Finger-joint print texture structure
It is relatively single, it is mostly made of vertical line, oblique line, camber line etc., due to the congenital heredity gene of human individual, posteriori life
The difference that habit living and the difference of environment are formed by finger-joint print has preferable distinction, is not easy to be stolen for identification
It takes, accuracy height；By mixing using finger pulp vein, dorsal digital vein, refer to band, finger-joint print carry out identification, be not easy by
It steals, further improve identification accuracy, stability.The identity identifying method based on hand-characteristic specifically includes
Following steps:
S102, the hand-characteristic image for obtaining target to be identified, the hand-characteristic image carries target identification, described
Hand-characteristic image includes finger pulp vein image, dorsal digital vein image, refers to band image, finger-joint print image；
Specifically, the hand-characteristic image for obtaining target to be identified specifically includes: obtaining hand-characteristic imaging device and clap
The hand-characteristic image for the target to be identified taken the photograph, the hand-characteristic image are number format, and the hand-characteristic image includes
Finger pulp vein image, refers to band image, finger-joint print image at dorsal digital vein image.
It is understood that in order to improve the safety of authentication, finger pulp vein image, refers to cross at dorsal digital vein image
Print image, finger-joint print image need to ensure be same target to be identified hand-characteristic image, image pickup method includes: to be identified
The hand placement of target disposably shoots finger pulp vein image, dorsal digital vein figure in shooting area, by hand-characteristic imaging device
Picture refers to band image, finger-joint print image.For example, including multiple imaging devices in hand-characteristic imaging device, pass through controller
It controls multiple imaging devices while shooting obtains finger pulp vein image, dorsal digital vein image, refers to band image, finger-joint print figure
Picture, only citing is not especially limited herein.
The hand-characteristic imaging device can select visual light imaging equipment, infrared imaging device from the prior art,
Therefore not to repeat here for specific structure.
The finger pulp vein refers to the vein from finger pulp loss, and from Fingers back side, dorsal digital vein figure is can be obtained in shooting
Picture.
The dorsal digital vein refers to the vein carried on the back from Fingers, and finger pulp vein figure can be obtained from the shooting of finger pulp loss lower section
Picture.
The folding line for referring to band and referring to finger the second articulations digitorum manus inner surface, the second articulations digitorum manus refer to from palm of the hand number past between finger
Second articulations digitorum manus, the inner surface of second articulations digitorum manus is flat and has streakline abundant；Refer to that band is determined by gene, in embryo
Fetal hair, which was educated by the 13rd week, to be started to occur, and is formed within the 19th week or so, and constant throughout one's life, is not easy to be stolen for identification, is quasi-
Exactness is high, stability is high；Refer to that band folding line is coarse, direction is single, not vulnerable to noise jamming, is not easy to be stolen for identification
It takes, accuracy is high, stability is high；The finger band of identical finger is almost identical in different acquisition, steady for identification
Qualitative height；And the Fingers band of different people has apparent difference, it is unique, be not easy to be stolen for identification,
Accuracy is high.
The finger-joint print refers to that the second articulations digitorum manus of finger refers to that back pleat curly grain, the second articulations digitorum manus refer to from the palm of the hand past between finger
Second articulations digitorum manus of number；Finger-joint print texture structure is relatively single, is mostly made of vertical line, oblique line, camber line etc., easily knows
Not；Finger-joint print has uniqueness because that the congenital heredity gene of human individual, posteriori living habit are from the difference of environment is different
Property, be not easy to be stolen for identification, accuracy it is high.
The target identification is used for one target to be identified of unique identification, for example, target identification is acquisition hand-characteristic
The mark of number and the acquisition time composition of imaging device, is not especially limited in this citing.
S104, the hand-characteristic image is pre-processed, pretreated hand-characteristic image zooming-out is obtained in one's hands
The feature vector of portion's feature, the feature vector of the hand-characteristic include finger pulp vein pattern vector, dorsal digital vein feature vector,
Refer to striations characteristic vector, finger-joint print feature vector；
Specifically, the hand-characteristic image after binary conversion treatment obtains binaryzation is carried out to the hand-characteristic image,
The feature vector of hand-characteristic is obtained to the hand-characteristic image zooming-out after binaryzation.
S106, hand will be registered in the feature vector of hand-characteristic corresponding with target identification and registration hand-characteristic database
Portion's feature samples are matched, and matching result is obtained；
The registration hand-characteristic data-base recording chartered hand-characteristic sample, chartered hand-characteristic sample
Originally carry registrant's mark, registrant's mark for identifying the registrant, such as: accession designation number, title etc. can be used for only
One identifies the mark of the registrant.Wherein, chartered hand-characteristic sample includes feature vector fusion value；Another
In a embodiment, chartered hand-characteristic sample includes finger pulp vein pattern vector, dorsal digital vein feature vector, refers to
Striations characteristic vector, finger-joint print feature vector.
Specifically, by same in the feature vector of hand-characteristic corresponding with target identification and registration hand-characteristic database
The registration hand-characteristic sample of one registrant matches, and obtains matching result.
S108, the corresponding identity authentication result of the target to be identified is determined according to the matching result.
Specifically, obtain preset matching threshold, when matching result is more than the matching threshold then authentication success,
When lower than the matching threshold, then authentication fails matching result.
As shown in Fig. 2, in one embodiment, the feature vector and note by hand-characteristic corresponding with target identification
Registration hand-characteristic sample is matched in volume hand-characteristic database, obtains matching result, comprising:
S202, by and the feature vector of the corresponding hand-characteristic of target identification merge to obtain hand corresponding with target identification
The feature vector fusion value of feature；
Specifically, will finger pulp vein pattern vector corresponding with target identification, dorsal digital vein feature vector, refer to band spy
Sign vector, finger-joint print feature vector merge to obtain the feature vector fusion value of hand-characteristic corresponding with target identification.Feature
Vector Fusion algorithm includes based on Bayesian decision theory algorithm, is based on sparse representation theory algorithm, theoretical based on deep learning
Any one of algorithm, citing is not especially limited herein.
S204, by the feature vector fusion value of the hand-characteristic corresponding with target identification and registration hand-characteristic data
Feature vector fusion value is matched in library, obtains matching result.
Specifically, by the feature vector fusion value of the hand-characteristic corresponding with target identification and registration hand-characteristic
Feature vector fusion value is matched to obtain matching score in database, and the matching score is matching result.
It is understood that showing that the feature vector of the feature vector fusion value of hand-characteristic corresponding with target identification is melted
Hop algorithm is identical as the feature vector blending algorithm of feature vector fusion value in registration hand-characteristic database.
As shown in figure 3, in another embodiment, the feature vector by hand-characteristic corresponding with target identification with
Registration hand-characteristic sample is matched in registration hand-characteristic database, obtains matching result, comprising:
S302, the feature vector for calculating the corresponding hand-characteristic of the target identification and the registration hand-characteristic database
In it is each registration hand-characteristic sample vector between Vectors matching value, the Vectors matching value includes: finger pulp vein vector
With value, dorsal digital vein Vectors matching value, refer to band Vectors matching value, finger-joint print Vectors matching value；
Specifically, calculate separately the corresponding finger pulp vein pattern vector of the target identification, dorsal digital vein feature vector,
Refer to striations characteristic vector, finger-joint print feature vector and the same registration hand-characteristic sample in the registration hand-characteristic database
This corresponding finger pulp vein pattern vector, refers between striations characteristic vector, finger-joint print feature vector dorsal digital vein feature vector
Vectors matching value.Refer to it is understood that calculating register hand-characteristic sample in the registration hand-characteristic database one by one
Abdomen vein Vectors matching value, dorsal digital vein Vectors matching value refer to band Vectors matching value, finger-joint print Vectors matching value, selection
For the highest Vectors matching value of the same registration hand-characteristic sample matches degree as final matching result.
S304, according to the Vectors matching value be calculated it is corresponding with each registration hand-characteristic sample vector matching melt
Conjunction value determines the matching result according to the matching fusion value.
Specifically, will finger pulp vein Vectors matching value corresponding with target identification, dorsal digital vein Vectors matching value, refer to cross
Line Vectors matching value, finger-joint print Vectors matching value merge to obtain the corresponding matching fusion of each registration hand-characteristic sample vector
Value, the matching fusion value is the matching result.
Blending algorithm includes based on Bayesian decision theory algorithm, is based on sparse representation theory algorithm, based on deep learning
Any one of theoretical algorithm, citing is not especially limited herein.
As shown in figure 4, in one embodiment, it is described to be calculated and each registration hand according to the Vectors matching value
The corresponding matching fusion value of feature samples vector determines the matching result according to the matching fusion value, comprising:
S402, Vectors matching threshold value is obtained, the Vectors matching threshold value includes: finger pulp vein Vectors matching threshold value, refers to back
Vein Vectors matching threshold value refers to band Vectors matching threshold value, finger-joint print Vectors matching threshold value；
The Vectors matching threshold value refer to the corresponding hand-characteristic of the target identification feature vector and the registration hand
The same matched critical value of feature vector for registering the corresponding hand-characteristic of hand-characteristic sample in portion's property data base.
The abdomen vein Vectors matching threshold value refers to the corresponding finger pulp vein pattern vector of the target identification and the note
The critical value of the corresponding finger pulp vein pattern vector Vectors matching of registration hand-characteristic sample in volume hand-characteristic database.
The dorsal digital vein Vectors matching threshold value refer to the corresponding dorsal digital vein feature vector of the target identification with it is described
Register the critical value of the corresponding dorsal digital vein feature vector Vectors matching of registration hand-characteristic sample in hand-characteristic database.
The finger band Vectors matching threshold value refers to the corresponding finger striations characteristic vector of the target identification and the registration
The corresponding critical value for referring to striations characteristic vector Vectors matching of hand-characteristic sample is registered in hand-characteristic database.
The finger-joint print Vectors matching threshold value refer to the corresponding finger-joint print feature vector of the target identification with it is described
Register the critical value of the corresponding finger-joint print feature vector Vectors matching of registration hand-characteristic sample in hand-characteristic database.
S404, finger pulp vein Vectors matching value and finger pulp vein Vectors matching threshold value, dorsal digital vein Vectors matching value with
Dorsal digital vein Vectors matching threshold value refers to band Vectors matching value and refers to band Vectors matching threshold value, finger-joint print Vectors matching value
It is compared to obtain comparison result with finger-joint print Vectors matching threshold value；
It is understood that for compare finger pulp vein Vectors matching value, dorsal digital vein Vectors matching value, refer to band to
Flux matched value, finger-joint print Vectors matching value refer to the feature vector and the registration hand-characteristic corresponding with target identification
In hand-characteristic database the feature vector of the corresponding hand-characteristic of same registration hand-characteristic sample match one by one obtain to
Flux matched value.To improve accuracy, the safety of authentication.
The comparison result be include finger pulp vein Vectors matching value with finger pulp vein Vectors matching threshold value comparison result, refer to
Dorsal vein Vectors matching value and dorsal digital vein Vectors matching threshold value comparison result refer to band Vectors matching value and refer to band vector
With threshold value comparison result, finger-joint print Vectors matching value and finger-joint print Vectors matching threshold value comparison result.
S406, when comparison result be any one of be lower than Vectors matching threshold value when, the matching fusion value is assigned a value of zero；
The matching fusion value is then assigned a value of zero lower than corresponding Vectors matching threshold by comparing any one of result, thus
In part, hand-characteristic, which is stolen, by authentication, can not further improve accuracy, the safety of authentication.
S408, when comparison result be all not less than Vectors matching threshold value when, with the same registration hand-characteristic sample
Corresponding finger pulp vein Vectors matching value, refers to band Vectors matching value, finger-joint print Vectors matching at dorsal digital vein Vectors matching value
Value is merged to obtain matching fusion value.
Wherein, blending algorithm uses based on Bayesian decision theory algorithm, is based on sparse representation theory algorithm, based on depth
Any one of theories of learning algorithm, citing is not especially limited herein.In another embodiment, blending algorithm is using weighting
Summation algorithm.
In one embodiment, the feature vector by hand-characteristic corresponding with target identification and registration hand-characteristic
Hand-characteristic sample is registered in database when being matched, the finger pulp vein pattern vector weight not less than refer to striations characteristic to
Weight and finger-joint print feature vector weight are measured, the dorsal digital vein feature vector weight is not less than finger striations characteristic vector weight
And finger-joint print feature vector weight.Based on finger pulp vein and dorsal digital vein, refers to band, give birth to supplemented by finger-joint print
The certification of object characteristic identity, further improves accuracy, safety, the stability of authentication.
In one embodiment, described that the hand-characteristic image is pre-processed, to pretreated hand-characteristic
Image zooming-out obtains the feature vector of hand-characteristic, and the feature vector of the hand-characteristic includes finger pulp vein pattern vector, refers to
Dorsal vein feature vector refers to striations characteristic vector, finger-joint print feature vector, comprising: is obtained according to the hand-characteristic image
Hand-characteristic image after binaryzation；Finger pulp vein image after binaryzation is extracted to obtain finger pulp vein pattern vector；To two
Dorsal digital vein image zooming-out after value obtains dorsal digital vein feature vector；Finger band image zooming-out after binaryzation is referred to
Striations characteristic vector；Finger-joint print image after binaryzation is extracted to obtain finger-joint print feature vector.Pass through the two-value of image
Change makes whole image show apparent black and white effect, is conducive to the accuracy of subsequent extracted feature vector, to improve body
The accuracy of part certification.
Wherein, the hand-characteristic image obtained after binaryzation according to the hand-characteristic image includes by floating Fujian
Value method carries out binaryzation to hand characteristic image, extracts feature vector to hand characteristic image after binaryzation.In another implementation
Example in, according to after binaryzation finger band image and finger-joint print image by OPTA thinning algorithm carry out micronization processes after again into
The extraction of row feature vector improves the accuracy of authentication to further improve the accuracy for extracting feature vector.
It is understood that by blur direction ability characteristics extract abdomen vein pattern vector, dorsal digital vein feature to
Amount；Refer to striations characteristic out by the minutiae extraction to bifurcation, isolated point, ramification point, endpoint, circling point, short-term several types
Vector, finger-joint print feature vector.
As shown in figure 5, in one embodiment, the hand-characteristic image for obtaining target to be identified, the hand spy
Sign image carries target identification, and the hand-characteristic image includes finger pulp vein image, dorsal digital vein image, refers to band figure
Picture, finger-joint print image, comprising:
S502, the finger of target to be identified is put into image capturing area；
It is understood that finger pulp loss is put into behind image capturing area by preset direction to be needed to stretch, to improve image
The quality of shooting.
S504, the abdomen of the finger of the target to be identified and back are shot simultaneously, obtains digital signal form
Finger pulp vein image, dorsal digital vein image, refer to band image, finger-joint print image, the finger pulp vein image, dorsal digital vein
Image refers to that band image, finger-joint print image carry identical target identification.
In order to improve the safety of authentication, finger pulp vein image, refers to band image, articulations digitorum manus at dorsal digital vein image
Print image need to ensure be same target to be identified hand-characteristic image.Wherein, by shooting finger pulp vein image simultaneously, referring to back
Vein image refers to that image that band image, finger-joint print image ensure is the hand-characteristic image of same target to be identified.
As shown in fig. 6, in another embodiment, the hand-characteristic image for obtaining target to be identified, the hand
Characteristic image carries target identification, and the hand-characteristic image includes finger pulp vein image, dorsal digital vein image, refers to band figure
Picture, finger-joint print image, comprising:
S602, it the palm of target to be identified is opened naturally is put into image capturing area；
Specifically, palm is in certainly after the palm centre of the palm of target to be identified is put into image capturing area by preset direction
Right open configuration, to improve the quality of image taking.In another embodiment, two palms of target to be identified are slapped
After the heart is put into image capturing area by preset direction, palm is in nature open configuration, is conducive to extract two palms simultaneously
Hand-characteristic image.It is understood that can also be using the hand-characteristic image for being put into finger shooting finger one by one, this side
Formula is conducive to the simplification of imaging device, reduces costs.
S604, the abdomen of all fingers of target to be identified and back are shot simultaneously, obtains digital signal shape
The finger pulp vein image of all fingers of formula, refers to band image, finger-joint print image at dorsal digital vein image；
In order to improve the safety of authentication, finger pulp vein image, refers to band image, articulations digitorum manus at dorsal digital vein image
Print image need to ensure be same target to be identified hand-characteristic image.
It is understood that shooting finger pulp vein image can be carried out to every finger respectively, dorsal digital vein image, refer to cross
Print image, finger-joint print image；The finger pulp vein image of all fingers can also be shot on an image, all fingers
One image of dorsal digital vein image taking on, on one images of finger band image taking of all finger, a Zhang Suoyou
The finger-joint print image of finger is shot on an image.
S606, according to the finger pulp vein image of all fingers, dorsal digital vein image, refer to band image, finger-joint print image
It identifies the corresponding finger pulp vein image of same root finger, dorsal digital vein image, refer to band image, finger-joint print image, it is same
The corresponding finger pulp vein image of root finger, dorsal digital vein image, to refer to that band image, finger-joint print image carry identical
Target identification.
It is understood that the target identification includes the unique identification of the target to be identified, finger mark.
In one embodiment, the method also includes: according to application scenarios, multiple Permission Levels, different rights etc. are set
The finger hand-characteristic of grade acquisition various combination carries out authentication.Specifically, being required that a left side can be acquired according to Permission Levels
Finger pulp vein image, dorsal digital vein image in hand, the right hand in arbitrary finger refer to that band image, finger-joint print image carry out
Identification.In another embodiment, it is required that left hand, arbitrary finger pulp vein figure in the right hand can be acquired according to Permission Levels
Picture, dorsal digital vein image refer to that band image, finger-joint print image carry out identification.
As shown in fig. 7, in one embodiment, the present invention also provides a kind of authentication system based on hand-characteristic
System, the system pass through the finger pulp vein image of hand-characteristic, dorsal digital vein image, refer to that band image, finger-joint print image are located in advance
Finger pulp vein pattern vector is extracted after reason, dorsal digital vein feature vector, refers to striations characteristic vector, finger-joint print feature vector,
By finger pulp vein pattern vector, dorsal digital vein feature vector, refer to striations characteristic vector, finger-joint print feature vector and registration hand
Hand-characteristic sample is registered in property data base carries out matching realization authentication.Due to referring to that band is determined by gene, roll over
Trace is coarse, direction is single, not vulnerable to noise jamming, is not easy to be stolen for identification, accuracy is high, stability is high；Refer to and closes
It is relatively single to save line texture structure, is mostly made of vertical line, oblique line, camber line etc., due to the congenital heredity of human individual
The difference that the difference of gene, posteriori living habit and environment is formed by finger-joint print has preferable distinction, is used for body
Part identification is not easy to be stolen, accuracy is high；Finger pulp vein, dorsal digital vein are used by mixing, refer to that band, finger-joint print carry out body
Part identification, is not easy to be stolen, further improves identification accuracy, stability.The system comprises:
Hand-characteristic sample module 701 is registered, for recording the registration hand-characteristic sample；
Image capture module 702, for obtaining the hand-characteristic image of target to be identified, the hand-characteristic image is carried
There is target identification, the hand-characteristic image includes finger pulp vein image, dorsal digital vein image, refers to band image, finger-joint print
Image；
Characteristic vector pickup module 703, for being pre-processed to the hand-characteristic image, to pretreated hand
Characteristic image extracts to obtain the feature vector of hand-characteristic, the feature vector of the hand-characteristic include finger pulp vein pattern to
Amount, refers to striations characteristic vector, finger-joint print feature vector at dorsal digital vein feature vector；
Authentication module 704, for the feature vector of hand-characteristic corresponding with target identification and registration hand is special
Registration hand-characteristic sample is matched in sign database, obtains matching result；It is determined according to the matching result described wait know
The corresponding identity authentication result of other target.
Fig. 8 shows the internal structure chart of computer equipment in one embodiment.The computer equipment specifically can be clothes
Business device and terminal device, the server include but is not limited to high-performance computer and high-performance computer cluster；The terminal
Equipment includes but is not limited to mobile terminal device and terminal console equipment, the mobile terminal device include but is not limited to mobile phone,
Tablet computer, smartwatch and laptop, the terminal console equipment includes but is not limited to desktop computer and vehicle-mounted computer.
As shown in figure 8, the computer equipment includes processor, memory and the network interface connected by system bus.Wherein, it stores
Device includes non-volatile memory medium and built-in storage.The non-volatile memory medium of the computer equipment is stored with operation system
System, can also be stored with computer program, and when which is executed by processor, it is special based on hand to may make that processor is realized
The identity identifying method of sign.Computer program can also be stored in the built-in storage, when which is executed by processor,
Processor may make to execute the identity identifying method based on hand-characteristic.It will be understood by those skilled in the art that shown in Fig. 8
Structure, only the block diagram of part-structure relevant to application scheme, does not constitute and is applied thereon to application scheme
Computer equipment restriction, specific computer equipment may include than more or fewer components as shown in the figure or group
Certain components are closed, or with different component layouts.
In one embodiment, the identity identifying method provided by the present application by hand-characteristic can be implemented as it is a kind of based on
The form of calculation machine program, computer program can be run in computer equipment as shown in Figure 8.In the memory of computer equipment
Each process template of identity authorization system of the composition based on hand-characteristic can be stored.For example, registration hand-characteristic sample module
701, image capture module 702, characteristic vector pickup module 703, authentication module 704.
In one embodiment, the present invention also provides a kind of storage mediums, are stored with computer program of instructions, the meter
When calculation machine instruction repertorie is executed by processor, so that the processor realizes following steps when executing: obtaining target to be identified
Hand-characteristic image, the hand-characteristic image carry target identification, the hand-characteristic image include finger pulp vein image,
Dorsal digital vein image refers to band image, finger-joint print image；The hand-characteristic image is pre-processed, after pretreatment
Hand-characteristic image zooming-out obtain the feature vector of hand-characteristic, the feature vector of the hand-characteristic includes that finger pulp vein is special
Sign vector, dorsal digital vein feature vector refer to striations characteristic vector, finger-joint print feature vector；It will hand corresponding with target identification
The feature vector of portion's feature is matched with registration hand-characteristic sample in registration hand-characteristic database, obtains matching result；
The corresponding identity authentication result of the target to be identified is determined according to the matching result.
In one embodiment, the present invention also provides a kind of computer equipments, including at least one processor, at least one
A processor, the memory is stored with computer program of instructions, when the computer program of instructions is executed by the processor,
So that the processor realizes following steps when executing: obtaining the hand-characteristic image of target to be identified, the hand is special
Sign image carries target identification, and the hand-characteristic image includes finger pulp vein image, dorsal digital vein image, refers to band figure
Picture, finger-joint print image；The hand-characteristic image is pre-processed, pretreated hand-characteristic image zooming-out is obtained
The feature vector of hand-characteristic, the feature vector of the hand-characteristic include finger pulp vein pattern vector, dorsal digital vein feature to
It measures, refer to striations characteristic vector, finger-joint print feature vector；By the feature vector and registration of hand-characteristic corresponding with target identification
Hand-characteristic sample is registered in hand-characteristic database to be matched, and matching result is obtained；Institute is determined according to the matching result
State the corresponding identity authentication result of target to be identified.
It should be noted that the above-mentioned identity identifying method based on hand-characteristic, the authentication system based on hand-characteristic
System, computer equipment and computer readable storage medium belong to a total inventive concept, the authentication based on hand-characteristic
Content in method, the identity authorization system based on hand-characteristic, computer equipment and computer readable storage medium embodiment
It can mutually be applicable in.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a non-volatile computer and can be read
In storage medium, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, provided herein
Each embodiment used in any reference to memory, storage, database or other media, may each comprise non-volatile
And/or volatile memory.Nonvolatile memory may include that read-only memory (ROM), programming ROM (PROM), electricity can be compiled
Journey ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include random access memory
(RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms, such as static state RAM
(SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhanced SDRAM
(ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) directly RAM (RDRAM), straight
Connect memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
In conclusion a kind of identity identifying method based on hand-characteristic of the invention passes through the finger pulp vein of hand-characteristic
Image, dorsal digital vein image refer to that band image, finger-joint print image extract finger pulp vein pattern vector after pre-processing, refer to back
Vein pattern vector refers to striations characteristic vector, finger-joint print feature vector, by finger pulp vein pattern vector, dorsal digital vein feature
Vector, refer to striations characteristic vector, finger-joint print feature vector and registration hand-characteristic database in registration hand-characteristic sample into
Authentication is realized in row matching.Due to referring to that band determines that folding line is coarse, direction is single by gene, not vulnerable to noise jamming,
It is not easy to be stolen for identification, accuracy is high, stability is high；Finger-joint print texture structure is relatively single, mostly
It is made of vertical line, oblique line, camber line etc., due to the congenital heredity gene of human individual, the difference of posteriori living habit and environment
The difference for being formed by finger-joint print has preferable distinction, be not easy to be stolen for identification, accuracy it is high；By mixed
It closes using finger pulp vein, dorsal digital vein, refer to that band, finger-joint print carry out identification, be not easy to be stolen, further improve body
Part recognition accuracy, stability.Therefore, the identity identifying method of the invention based on hand-characteristic is not easy to be stolen, and identity is known
Other accuracy is high, and identification result remains stability.
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
The limitation to the application the scope of the patents therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the concept of this application, various modifications and improvements can be made, these belong to the guarantor of the application
Protect range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (12)
1. a kind of identity identifying method based on hand-characteristic, which comprises
The hand-characteristic image of target to be identified is obtained, the hand-characteristic image carries target identification, the hand-characteristic
Image includes finger pulp vein image, dorsal digital vein image, refers to band image, finger-joint print image；
The hand-characteristic image is pre-processed, the spy of hand-characteristic is obtained to pretreated hand-characteristic image zooming-out
Vector is levied, the feature vector of the hand-characteristic includes finger pulp vein pattern vector, dorsal digital vein feature vector, refers to striations characteristic
Vector, finger-joint print feature vector；
Hand-characteristic sample will be registered in the feature vector of hand-characteristic corresponding with target identification and registration hand-characteristic database
This is matched, and matching result is obtained；
The corresponding identity authentication result of the target to be identified is determined according to the matching result.
2. the identity identifying method according to claim 1 based on hand-characteristic, which is characterized in that
Registration hand is special in the feature vector by hand-characteristic corresponding with target identification and registration hand-characteristic database
Sign sample is matched, and matching result is obtained, comprising:
By and the feature vector of the corresponding hand-characteristic of target identification merge to obtain the spy of hand-characteristic corresponding with target identification
Levy Vector Fusion value；
By feature in the feature vector fusion value of the hand-characteristic corresponding with target identification and registration hand-characteristic database
Vector Fusion value is matched, and matching result is obtained.
3. the identity identifying method according to claim 1 based on hand-characteristic, which is characterized in that
Registration hand is special in the feature vector by hand-characteristic corresponding with target identification and registration hand-characteristic database
Sign sample is matched, and matching result is obtained, comprising:
Calculate each note in the feature vector and the registration hand-characteristic database of the corresponding hand-characteristic of the target identification
Vectors matching value between volume hand-characteristic sample vector, the Vectors matching value include: finger pulp vein Vectors matching value, refer to back
Vein Vectors matching value refers to band Vectors matching value, finger-joint print Vectors matching value；
Matching fusion value corresponding with each registration hand-characteristic sample vector is calculated according to the Vectors matching value, according to
The matching fusion value determines the matching result.
4. the identity identifying method according to claim 3 based on hand-characteristic, which is characterized in that
It is described that matching fusion value corresponding with each registration hand-characteristic sample vector is calculated according to the Vectors matching value,
The matching result is determined according to the matching fusion value, comprising:
Vectors matching threshold value is obtained, the Vectors matching threshold value includes: finger pulp vein Vectors matching threshold value, dorsal digital vein vector
With threshold value, refer to band Vectors matching threshold value, finger-joint print Vectors matching threshold value；
Finger pulp vein Vectors matching value and finger pulp vein Vectors matching threshold value, dorsal digital vein Vectors matching value and dorsal digital vein to
Flux matched threshold value refers to band Vectors matching value and refers to band Vectors matching threshold value, finger-joint print Vectors matching value and finger-joint print
Vectors matching threshold value is compared to obtain comparison result；
When comparison result is that any one is lower than Vectors matching threshold value, the matching fusion value is assigned a value of zero；
When comparison result is all not less than Vectors matching threshold value, finger pulp corresponding with the same registration hand-characteristic sample
Vein Vectors matching value, dorsal digital vein Vectors matching value refer to that band Vectors matching value, finger-joint print Vectors matching value are merged
Obtain matching fusion value.
5. the identity identifying method according to any one of claims 1 to 4 based on hand-characteristic, which is characterized in that
Registration hand is special in the feature vector by hand-characteristic corresponding with target identification and registration hand-characteristic database
When sign sample is matched, the finger pulp vein pattern vector weight is special not less than finger striations characteristic vector weight and finger-joint print
Vector weight is levied, the dorsal digital vein feature vector weight is not less than finger striations characteristic vector weight and finger-joint print feature vector
Weight.
6. the identity identifying method according to any one of claims 1 to 4 based on hand-characteristic, which is characterized in that
It is described that the hand-characteristic image is pre-processed, hand-characteristic is obtained to pretreated hand-characteristic image zooming-out
Feature vector, the feature vector of the hand-characteristic includes finger pulp vein pattern vector, dorsal digital vein feature vector, refers to band
Feature vector, finger-joint print feature vector, comprising:
Hand-characteristic image after obtaining binaryzation according to the hand-characteristic image；
Finger pulp vein image after binaryzation is extracted to obtain finger pulp vein pattern vector；
Dorsal digital vein feature vector is obtained to the dorsal digital vein image zooming-out after binaryzation；
Finger band image zooming-out after binaryzation is obtained to refer to striations characteristic vector；
Finger-joint print image after binaryzation is extracted to obtain finger-joint print feature vector.
7. the identity identifying method according to any one of claims 1 to 4 based on hand-characteristic, which is characterized in that
The hand-characteristic image for obtaining target to be identified, the hand-characteristic image carry target identification, the hand
Characteristic image includes finger pulp vein image, dorsal digital vein image, refers to band image, finger-joint print image, comprising:
The finger of target to be identified is put into image capturing area；
Abdomen and back to the finger of the target to be identified are shot simultaneously, obtain the finger pulp vein of digital signal form
Image, dorsal digital vein image refer to that band image, finger-joint print image, the finger pulp vein image, refer to cross at dorsal digital vein image
Print image, finger-joint print image carry identical target identification.
8. the identity identifying method according to any one of claims 1 to 4 based on hand-characteristic, which is characterized in that
The hand-characteristic image for obtaining target to be identified, the hand-characteristic image carry target identification, the hand
Characteristic image includes finger pulp vein image, dorsal digital vein image, refers to band image, finger-joint print image, comprising:
The palm of target to be identified is opened naturally and is put into image capturing area；
Abdomen and back to all fingers of target to be identified are shot simultaneously, obtain all hands of digital signal form
The finger pulp vein image of finger, refers to band image, finger-joint print image at dorsal digital vein image；
According to the finger pulp vein image of all fingers, dorsal digital vein image, to refer to that band image, finger-joint print image identify same
The corresponding finger pulp vein image of root finger, dorsal digital vein image refer to that band image, finger-joint print image, same root finger are corresponding
The finger pulp vein image, dorsal digital vein image, refer to that band image, finger-joint print image carry identical target identification.
9. the identity identifying method according to any one of claims 1 to 4 based on hand-characteristic, which is characterized in that described
Method further include: multiple Permission Levels are set according to application scenarios, the finger hand that different rights grade acquires various combination is special
Sign carries out authentication.
10. a kind of identity authorization system based on hand-characteristic, which is characterized in that the system comprises:
Hand-characteristic sample module is registered, for recording the registration hand-characteristic sample；
Image capture module, for obtaining the hand-characteristic image of target to be identified, the hand-characteristic image carries target
Mark, the hand-characteristic image include finger pulp vein image, dorsal digital vein image, refer to band image, finger-joint print image；
Characteristic vector pickup module, for being pre-processed to the hand-characteristic image, to pretreated hand-characteristic figure
The feature vector of hand-characteristic is obtained as extracting, the feature vector of the hand-characteristic includes finger pulp vein pattern vector, refers to back
Vein pattern vector refers to striations characteristic vector, finger-joint print feature vector；
Authentication module, for by the feature vector of hand-characteristic corresponding with target identification and registration hand-characteristic database
Middle registration hand-characteristic sample is matched, and matching result is obtained；The target pair to be identified is determined according to the matching result
The identity authentication result answered.
11. a kind of storage medium, is stored with computer program of instructions, which is characterized in that the computer program of instructions is processed
When device executes, so that the processor is executed such as the step of any one of claims 1 to 9 the method.
12. a kind of computer equipment, which is characterized in that including at least one processor, at least one processor, the memory
It is stored with computer program of instructions, when the computer program of instructions is executed by the processor, so that the processor executes
Such as the step of any one of claims 1 to 9 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910616396.5A CN110472498B (en) | 2019-07-09 | 2019-07-09 | Identity authentication method, system, storage medium and equipment based on hand characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910616396.5A CN110472498B (en) | 2019-07-09 | 2019-07-09 | Identity authentication method, system, storage medium and equipment based on hand characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110472498A true CN110472498A (en) | 2019-11-19 |
| CN110472498B CN110472498B (en) | 2023-09-19 |
Family
ID=68507183
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910616396.5A Active CN110472498B (en) | 2019-07-09 | 2019-07-09 | Identity authentication method, system, storage medium and equipment based on hand characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110472498B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111209851A (en) * | 2020-01-04 | 2020-05-29 | 圣点世纪科技股份有限公司 | Finger vein identification method based on finger ventral vein and finger dorsal vein deep fusion |
| CN111582190A (en) * | 2020-05-11 | 2020-08-25 | 广州微盾科技股份有限公司 | Texture and vein-based identification method, identification device and storage medium |
| CN113269029A (en) * | 2021-04-07 | 2021-08-17 | 张烨 | Multi-modal and multi-characteristic finger vein image recognition method |
| CN113722692A (en) * | 2021-09-07 | 2021-11-30 | 墨奇科技（北京）有限公司 | Identity recognition device and method thereof |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101539995A (en) * | 2009-04-24 | 2009-09-23 | 清华大学深圳研究生院 | Imaging device based on vein pattern and backside pattern of finger and multimode identity authentication method |
| CN101908294A (en) * | 2010-08-30 | 2010-12-08 | 西安超人高仿真机器人科技有限公司 | Method for designing high-emulation silica gel intelligent acupuncture and moxibustion teaching robot |
| CN102184387A (en) * | 2011-05-10 | 2011-09-14 | 陈庆武 | Finger vein authentication system |
-
2019
- 2019-07-09 CN CN201910616396.5A patent/CN110472498B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101539995A (en) * | 2009-04-24 | 2009-09-23 | 清华大学深圳研究生院 | Imaging device based on vein pattern and backside pattern of finger and multimode identity authentication method |
| CN101908294A (en) * | 2010-08-30 | 2010-12-08 | 西安超人高仿真机器人科技有限公司 | Method for designing high-emulation silica gel intelligent acupuncture and moxibustion teaching robot |
| CN102184387A (en) * | 2011-05-10 | 2011-09-14 | 陈庆武 | Finger vein authentication system |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111209851A (en) * | 2020-01-04 | 2020-05-29 | 圣点世纪科技股份有限公司 | Finger vein identification method based on finger ventral vein and finger dorsal vein deep fusion |
| CN111582190A (en) * | 2020-05-11 | 2020-08-25 | 广州微盾科技股份有限公司 | Texture and vein-based identification method, identification device and storage medium |
| CN111582190B (en) * | 2020-05-11 | 2024-03-01 | 广州微盾科技股份有限公司 | Identification method, identification equipment and storage medium based on texture and vein |
| CN113269029A (en) * | 2021-04-07 | 2021-08-17 | 张烨 | Multi-modal and multi-characteristic finger vein image recognition method |
| CN113269029B (en) * | 2021-04-07 | 2022-09-13 | 张烨 | Multi-modal and multi-characteristic finger vein image recognition method |
| CN113722692A (en) * | 2021-09-07 | 2021-11-30 | 墨奇科技（北京）有限公司 | Identity recognition device and method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110472498B (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lin et al. | A CNN-based framework for comparison of contactless to contact-based fingerprints | |
| CN110472498A (en) | Identity identifying method, system, storage medium and equipment based on hand-characteristic | |
| US9613428B2 (en) | Fingerprint authentication using stitch and cut | |
| CN113614731B (en) | Authentication verification using soft biometrics | |
| US9508122B2 (en) | Creating templates for fingerprint authentication | |
| KR100997616B1 (en) | Rotating fingerprint acquisition device and method using matching and synthesis | |
| JP7251000B2 (en) | Method, apparatus, device, medium, and computer program for identifying authenticity of face image | |
| CN107977559A (en) | A kind of identity identifying method, device, equipment and computer-readable recording medium | |
| Kim et al. | Reconstruction of fingerprints from minutiae using conditional adversarial networks | |
| KR102205495B1 (en) | Method and apparatus for recognizing finger print | |
| KR102558736B1 (en) | Method and apparatus for recognizing finger print | |
| Cho et al. | GAN-based blur restoration for finger wrinkle biometrics system | |
| US11721132B1 (en) | System and method for generating region of interests for palm liveness detection | |
| US10430629B2 (en) | Non-transitory computer-readable medium storing information processing program and information processing device | |
| KR101450247B1 (en) | Method for authenticating based on finger vein using SIFT keypoint | |
| JP2017010419A (en) | Information processing program and information processing device | |
| CN111583168A (en) | Image synthesis method, image synthesis device, computer equipment and storage medium | |
| US11941911B2 (en) | System and method for detecting liveness of biometric information | |
| US11688204B1 (en) | System and method for robust palm liveness detection using variations of images | |
| US12190629B2 (en) | Deep learning based fingerprint minutiae extraction | |
| KR101012596B1 (en) | Rotating Fingerprint Matching / Synthesis Device and Method Using Baseline | |
| Kim et al. | Check for Reconstruction of Fingerprints from Minutiae Using Conditional Adversarial Networks Hakil Kim (), Xuenan Cui, Man-Gyu Kim, and Thi Hai Binh Nguyen | |
| Ma et al. | Saliency preprocessing for person re-identification images | |
| Malinowski et al. | Iris recognition based on local grey extremum values with CNN-based approaches | |
| Mantecón et al. | Access control based on visual face recognition using Depth Spatiograms of Local Quantized Patterns |
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 |