CN108563937A - A kind of identity identifying method and bracelet based on vein - Google Patents
A kind of identity identifying method and bracelet based on vein Download PDFInfo
- Publication number
- CN108563937A CN108563937A CN201810359301.1A CN201810359301A CN108563937A CN 108563937 A CN108563937 A CN 108563937A CN 201810359301 A CN201810359301 A CN 201810359301A CN 108563937 A CN108563937 A CN 108563937A
- Authority
- CN
- China
- Prior art keywords
- vein pattern
- bracelet
- vein
- authentication
- vector
- 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
- 210000003462 vein Anatomy 0.000 title claims abstract description 265
- 238000000034 method Methods 0.000 title claims abstract description 36
- 239000013598 vector Substances 0.000 claims abstract description 123
- 230000000007 visual effect Effects 0.000 claims abstract description 88
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 33
- 238000013135 deep learning Methods 0.000 claims abstract description 27
- 230000008569 process Effects 0.000 claims description 19
- 230000004438 eyesight Effects 0.000 claims description 17
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 7
- 230000005611 electricity Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 7
- 238000004364 calculation method Methods 0.000 abstract description 6
- 210000000707 wrist Anatomy 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 5
- 210000001367 artery Anatomy 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 230000033001 locomotion Effects 0.000 description 4
- 230000007306 turnover Effects 0.000 description 4
- 238000013475 authorization Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 238000004321 preservation Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003278 mimic effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/34—User authentication involving the use of external additional devices, e.g. dongles or smart cards
- G06F21/35—User authentication involving the use of external additional devices, e.g. dongles or smart cards communicating wirelessly
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/14—Vascular patterns
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Input (AREA)
Abstract
The present invention provides a kind of identity identifying method and bracelet based on vein, acquires vein pattern using dynamic visual sensor, the dynamic visual sensor is linear array dynamic visual sensor;The vein pattern collector includes two linear array dynamic visual sensors, two linear array dynamic visual sensors are at the orthogonal arrangement of " ten " font, the image acquired by dynamic visual sensor includes only the effective informations such as the feature of vein, the invalid background information such as the skin not comprising redundancy, after receiving the vein pattern image, compared to the deep learning algorithm based on Normal visual sensor, only need seldom layer that can realize the calculating of vein pattern vector, the calculation amount of image procossing can largely be reduced, reduce power consumption, it is suitble to integrated, recognition effect is good simultaneously.
Description
Technical field
The present invention relates to identity intelligent identification technology field more particularly to a kind of identity identifying methods and hand based on vein
Ring.
Background technology
Medical research proves that the shape of vein has uniqueness and stability.Vein recognition system because have vivo identification,
The feature of internal feature and contactless three aspects, it is ensured that the vein pattern of user is difficult to be forged, highly safe
With far win the identification technologies such as fingerprint, iris, face on practical convenient, therefore, based on the authentication of vein particularly suitable for peace
High place is required to use entirely, especially the vein identity authorization system of wrist.
The existing wrist identity authorization system based on vein is usually all to first pass through imaging sensor acquisition fixed position
Vein image, then the vein image of acquisition is handled by image processing module, remove vein image background, extraction
Useful vein pattern image obtains vein pattern vector based on vein pattern image, finally by the vein pattern of acquisition vector
It is compared with the vein pattern vector to prestore, if identical, certification passes through, otherwise, authentification failure.
However, the existing wrist identity authorization system based on vein has the disadvantage that:First, it uses common
Imaging sensor, common imaging sensor to light require it is stringenter, under strong light or subdued light conditions, recognition effect is very
Difference.Also, in obtaining image process, if bracelet moves, the image of acquisition will be very fuzzy;Second, due to acquisition
Be the vein image for including background, there are acquired image high redundancy data, image processing module to need intricately to go
It except background, calculates to extraction vein pattern image, calculating process is complicated, and data processing amount is big, needs a large amount of computing resource.
Invention content
The technical problem to be solved by the present invention is to:There is provided that a kind of calculation amount is small, the good body based on vein of recognition effect
Identity authentication method and device.
In order to solve the above-mentioned technical problem, a kind of technical solution that the present invention uses for:
A kind of identity identifying method based on vein, including step:
S1, reception are set to the ID authentication request that the touch sensor on bracelet is sent, and are asked according to the authentication
It asks, starts timing;
S2, the vein pattern figure that bracelet is set to the vein pattern collector transmission of bracelet inner wall in rotation process is received
Picture obtains corresponding first vein pattern vector, the vein is special according to the vein pattern image using deep learning algorithm
It includes two linear array dynamic visual sensors to levy collector, and two linear array dynamic visual sensors are hung down mutually at " ten " font
In line row, the linear array dynamic visual sensor are formed by the arrangement of multiple dynamic vision pixels is in alignment;
S3, second whether had with the first vein pattern Vectors matching is retrieved in the vein pattern vector set to prestore
Feature vector, if so, authentication success, if it is not, then authentication mistake, and judge whether time-out, if it is not, then returning to step
Rapid S2.
In order to solve the above-mentioned technical problem, the another technical solution that the present invention uses for:
A kind of authentication bracelet based on vein, including touch sensor further include:
Vein pattern collector, the vein pattern collector are set to the bracelet inner wall, the vein pattern acquisition
Device includes two linear array dynamic visual sensors, and two linear array dynamic visual sensors are at the orthogonal row of " ten " font
Row;
Memory, processor and it is stored in the computer program that can be run on the memory and on the processor,
The processor realizes following steps when executing the computer program:
S1, the ID authentication request for receiving the touch sensor transmission start to count according to the ID authentication request
When;
S2, the vein pattern image that bracelet vein pattern collector described in rotation process is sent is received, according to described
Vein pattern image obtains corresponding first vein pattern vector, the vein pattern collector packet using deep learning algorithm
Two linear array dynamic visual sensors are included, two linear array dynamic visual sensors are at the orthogonal arrangement of " ten " font, institute
Linear array dynamic visual sensor is stated to be formed by the arrangement of multiple dynamic vision pixels is in alignment;
S3, second whether had with the first vein pattern Vectors matching is retrieved in the vein pattern vector set to prestore
Feature vector, if so, authentication success, if it is not, then authentication mistake, and judge whether time-out, if it is not, then returning to step
Rapid S2.
The beneficial effects of the present invention are:Vein pattern, the dynamic vision sensing are acquired using dynamic visual sensor
Device is linear array dynamic visual sensor;The vein pattern collector include two linear array dynamic visual sensors, two
The linear array dynamic visual sensor is at the orthogonal arrangement of " ten " font, since dynamic visual sensor is to be based on shooting area
Variation and the operation principle that is imaged, there is no the problem of traditional sensors, light is required it is very low, very low or very bright
It can work well under light condition, be that asynchronous event vector is generated by the variation of light intensity, by simply becoming
It changes and generates digitized vein distribution characteristics figure, acquired image includes only the effective informations such as the feature of vein, is not included superfluous
The invalid background information such as remaining skin, after receiving the vein pattern image, compared to based on Normal visual sensor
Deep learning algorithm, it is only necessary to seldom layer can realize the calculating of vein pattern vector, can largely reduce
The calculation amount of image procossing reduces power consumption, is suitble to integrate, while recognition effect is good.
Description of the drawings
Fig. 1 is a kind of flow chart of identity identifying method based on vein of the embodiment of the present invention;
Fig. 2 is a kind of structural schematic diagram of authentication bracelet based on vein of the embodiment of the present invention;
Fig. 3 is that a kind of structure of the dynamic visual sensor of authentication bracelet based on vein of the embodiment of the present invention is shown
It is intended to;
Fig. 4 is that the acquisition of the embodiment of the present invention prestores the flow chart of vein pattern vector;
Fig. 5 is the flow chart of the continuous authentication of progress of the embodiment of the present invention;
Label declaration:
1, a kind of authentication bracelet based on vein;2, touch sensor;3, vein pattern collector;4, processor;
5, memory;6, dynamic visual sensor.
Specific implementation mode
To explain the technical content, the achieved purpose and the effect of the present invention in detail, below in conjunction with embodiment and coordinate attached
Figure is explained.
The design of most critical of the present invention is:Vein pattern image, the dynamic vision are acquired using dynamic visual sensor
Feel sensor is linear array dynamic visual sensor;The vein pattern collector includes two linear array dynamic vision sensings
Device, two linear array dynamic visual sensors are at the orthogonal arrangement of " ten " font, according to collected vein pattern image,
Corresponding vein pattern vector is obtained using deep learning algorithm.
Please refer to Fig. 1, a kind of identity identifying method based on vein, including step:
S1, reception are set to the ID authentication request that the touch sensor on bracelet is sent, and are asked according to the authentication
It asks, starts timing;
S2, the vein pattern figure that bracelet is set to the vein pattern collector transmission of bracelet inner wall in rotation process is received
Picture obtains corresponding first vein pattern vector, the vein is special according to the vein pattern image using deep learning algorithm
It includes two linear array dynamic visual sensors to levy collector, and two linear array dynamic visual sensors are hung down mutually at " ten " font
In line row, the linear array dynamic visual sensor are formed by the arrangement of multiple dynamic vision pixels is in alignment;
S3, second whether had with the first vein pattern Vectors matching is retrieved in the vein pattern vector set to prestore
Feature vector, if so, authentication success, if it is not, then authentication mistake, and judge whether time-out, if it is not, then returning to step
Rapid S2.
As can be seen from the above description, the beneficial effects of the present invention are:Vein pattern, institute are acquired using dynamic visual sensor
It is linear array dynamic visual sensor to state dynamic visual sensor;The vein pattern collector includes two linear array dynamic visions
Feel sensor, two linear array dynamic visual sensors are at the orthogonal arrangement of " ten " font, due to dynamic visual sensor
Be based on the variation of shooting area and the operation principle that is imaged, there is no the problem of traditional sensors, light is required it is very low,
Can work well under very low or very bright light condition, be by the variation of light intensity generate asynchronous event to
Amount generates digitized vein distribution characteristics figure by simply converting, and acquired image, which includes only the feature etc. of vein, to be had
Imitate information, do not include the invalid background information such as skin of redundancy, after receiving the vein pattern image, compared to based on
The deep learning algorithm of Normal visual sensor, it is only necessary to which seldom layer can realize the calculating of vein pattern vector, can be with
The calculation amount for largely reducing image procossing, reduces power consumption, is suitble to integrate, while recognition effect is good.
Further, further include acquiring the vein pattern vector step that prestores before the step S1:
S0, judge whether bracelet uses for the first time, if so, thening follow the steps S01, otherwise, execute step S02;
S01, the vein pattern image that bracelet is sent along dynamic visual sensor described in orientation arm moving process is received,
According to the vein pattern image, corresponding third vein pattern vector is obtained using deep learning algorithm, the third is quiet
Arteries and veins feature vector is stored in the vein pattern vector set, and terminates to acquire the vein pattern vector step that prestores;
S02, it is determined whether to enable daily vein pattern vectors to acquire function, if so, executing step S021, otherwise, terminates
Acquire the vein pattern vector step that prestores;
S021, judge whether the vein pattern vector number in the vein pattern vector set is not less than the first preset value, if
It is no, S022 is thened follow the steps, otherwise, terminates to acquire the vein pattern vector step that prestores;
S022, judge otherwise whether the electricity of the bracelet, returns higher than the second preset value if so, thening follow the steps S023
Return step S021;
S023, the vein pattern figure that bracelet is sent along dynamic visual sensor described in orientation arm moving process is received
Picture obtains corresponding 4th vein pattern vector, by the described 4th according to the vein pattern image using deep learning algorithm
Vein pattern vector is stored in the vein pattern vector set, and return to step S021.
Seen from the above description, the acquisition realization of vein pattern vector of carrying out prestoring through a variety of ways prestores vein pattern
Vector is locally stored, and not only increases the flexibility for the vein pattern vector acquisition that prestores, and it is enough to ensure to prestore
Vein pattern vector, realize more rapidly safer authentication.
Further, further include step between the step S1 and step S2:
S11, judge whether the angle of the bracelet rotation is more than a predetermined angle, if so, S2 is thened follow the steps, otherwise,
Judge whether time-out, if it is not, return to step S11, otherwise, authentication failure.
Seen from the above description, what is received when the acquisition of the vein pattern vector to prestore is to move hand along orientation arm
The vein pattern image that dynamic visual sensor is sent after ring, when carrying out authentication, the dynamic after being bracelet rotation of reception
The vein pattern image that visual sensor is sent, therefore, the angle of bracelet rotation need to ensure that vein pattern collector can pass through
The wrist area corresponding to vein pattern vector to prestore just has enough information to be made whether being sentencing for correct identity in this way
It is disconnected, for example if vein pattern collector number is 1, to turn over more than a circle, if vein pattern collector is along bracelet
It is 6 that inner wall, which is circumferentially uniformly distributed number, then to turn over more than 60 degree, that is to say, that if vein pattern collector number is N,
The angle that bracelet turns over must be over 360 °/N just can guarantee enough information be made whether be correct identity judgement, from
And ensure the validity of the authentication, therefore, subsequent reception is just carried out when the angle of bracelet rotation is more than preset value
Extraction operation not only reduces calculating, and ensure that the validity of each authentication.
Further, further include the successful identity information of Registration Authentication in the step S3 after authentication success;
Further include step after the step S3:
S411, judge whether receive the ID authentication request of bluetooth or NFC or bracelet rotates or continuously struck
It hits under two, if so, starting timing;
S412, judge whether to be registered with the successful identity information of certification, if so, send the successful identity information of certification to
The bluetooth or NFC;
S413, judge whether to receive bluetooth or effective return information of NFC, if so, authentication is completed, otherwise,
Judge whether time-out, if it is not, then return to step S412.
Seen from the above description, after authentication success, the successful identity information of certification is registered, may be implemented
Continuous authentication, it is more convenient to use.
Further, further include step after the step S3:
S421, judge whether bracelet moves, if so, starting the proximity sensor being set on bracelet;
S422, the data that the proximity sensor is sent are received, judges whether bracelet is removed according to the data, if
It is the successful identity information of certification for then removing registration.
Seen from the above description, when sensing that bracelet is removed, the successful identity information of the certification of preservation is carried out clear
It removes, the safety of authentication can be improved.
Fig. 2, a kind of authentication bracelet based on vein, including touch sensor are please referred to, further includes:
Vein pattern collector, the vein pattern collector are set to the bracelet inner wall, the vein pattern acquisition
Device includes two linear array dynamic visual sensors, and two linear array dynamic visual sensors are at the orthogonal row of " ten " font
Row, the linear array dynamic visual sensor are formed by the arrangement of multiple dynamic vision pixels is in alignment;
Memory, processor and it is stored in the computer program that can be run on the memory and on the processor,
The processor realizes following steps when executing the computer program:
S1, the ID authentication request for receiving the touch sensor transmission start to count according to the ID authentication request
When;
S2, the vein pattern image that bracelet vein pattern collector described in rotation process is sent is received, according to described
Vein pattern image obtains corresponding first vein pattern vector, the vein pattern collector packet using deep learning algorithm
Two linear array dynamic visual sensors are included, two linear array dynamic visual sensors are at the orthogonal arrangement of " ten " font;
S3, second whether had with the first vein pattern Vectors matching is retrieved in the vein pattern vector set to prestore
Feature vector, if so, authentication success, if it is not, judge whether time-out, if it is not, then authentication mistake, and judge whether
Time-out, if it is not, then return to step S2.
As can be seen from the above description, the beneficial effects of the present invention are:Vein pattern, institute are acquired using dynamic visual sensor
It is linear array dynamic visual sensor to state dynamic visual sensor;The vein pattern collector includes two linear array dynamic visions
Feel sensor, two linear array dynamic visual sensors are at the orthogonal arrangement of " ten " font, due to dynamic visual sensor
Be based on the variation of shooting area and the operation principle that is imaged, there is no the problem of traditional sensors, light is required it is very low,
Can work well under very low or very bright light condition, be by the variation of light intensity generate asynchronous event to
Amount generates digitized vein distribution characteristics figure by simply converting, and acquired image, which includes only the feature etc. of vein, to be had
Imitate information, do not include the invalid background information such as skin of redundancy, after receiving the vein pattern image, compared to based on
The deep learning algorithm of Normal visual sensor, it is only necessary to which seldom layer can realize the calculating of vein pattern vector, can be with
The calculation amount for largely reducing image procossing, reduces power consumption, is suitble to integrate, while recognition effect is good.
Further, further include acquiring the vein pattern vector step that prestores before the step S1:
S0, judge whether bracelet uses for the first time, if so, thening follow the steps S01, otherwise, execute step S02;
S01, the vein pattern image that bracelet is sent along dynamic visual sensor described in orientation arm moving process is received,
According to the vein pattern image, corresponding third vein pattern vector is obtained using deep learning algorithm, the third is quiet
Arteries and veins feature vector is stored in the vein pattern vector set, and terminates to acquire the vein pattern vector step that prestores;
S02, it is determined whether to enable daily vein pattern vectors to acquire function, if so, executing step S021, otherwise, terminates
Acquire the vein pattern vector step that prestores;
S021, judge whether the vein pattern vector number in the vein pattern vector set is not less than the first preset value, if
It is no, S022 is thened follow the steps, otherwise, terminates to acquire the vein pattern vector step that prestores;
S022, judge otherwise whether the electricity of the bracelet, returns higher than the second preset value if so, thening follow the steps S023
Return step S021;
S023, the vein pattern figure that bracelet is sent along dynamic visual sensor described in orientation arm moving process is received
Picture obtains corresponding 4th vein pattern vector, by the described 4th according to the vein pattern image using deep learning algorithm
Vein pattern vector is stored in the vein pattern vector set, and return to step S021.
Seen from the above description, the acquisition realization of vein pattern vector of carrying out prestoring through a variety of ways prestores vein pattern
Vector is locally stored, and not only increases the flexibility for the vein pattern vector acquisition that prestores, and it is enough to ensure to prestore
Vein pattern vector, realize more rapidly safer authentication.
Further, further include step between the step S1 and step S2:
S11, judge whether the angle of the bracelet rotation is more than a predetermined angle, if so, S2 is thened follow the steps, otherwise,
Judge whether time-out, if it is not, return to step S11, otherwise, authentication failure.
Seen from the above description, what is received when the acquisition of the vein pattern vector to prestore is to move hand along orientation arm
The vein pattern image that dynamic visual sensor is sent after ring, when carrying out authentication, the dynamic after being bracelet rotation of reception
The vein pattern image that visual sensor is sent, therefore, the angle of bracelet rotation need to ensure that vein pattern collector can pass through
The wrist area corresponding to vein pattern vector to prestore just has enough information to be made whether being sentencing for correct identity in this way
It is disconnected, for example if vein pattern collector number is 1, to turn over more than a circle, if vein pattern collector is along bracelet
It is 6 that inner wall, which is circumferentially uniformly distributed number, then to turn over more than 60 degree, that is to say, that if vein pattern collector number is N,
The angle that bracelet turns over must be over 360 °/N just can guarantee enough information be made whether be correct identity judgement, from
And ensure the validity of the authentication, therefore, subsequent reception is just carried out when the angle of bracelet rotation is more than preset value
Extraction operation not only reduces calculating, and ensure that the validity of each authentication, while special if multiple veins are arranged
Collector is levied, then can extract the vein distribution at the multiple positions of wrist, including the back side of wrist, side and front, have more
Vein pattern point, have non-reproduction and higher safety.
Further, further include the successful identity information of Registration Authentication in the step S3 after authentication success;
Further include step after the step S3:
S411, judge whether receive the ID authentication request of bluetooth or NFC or bracelet rotates or continuously struck
It hits under two, if so, starting timing;
S412, judge whether to be registered with the successful identity information of certification, if so, send the successful identity information of certification to
The bluetooth or NFC;
S413, judge whether to receive bluetooth or effective return information of NFC, if so, authentication is completed, otherwise,
Judge whether time-out, if it is not, then return to step S412.
Seen from the above description, after authentication success, the successful identity information of certification is registered, may be implemented
Continuous authentication, it is more convenient to use.
Further, further include proximity sensor, the proximity sensor be set to the bracelet inner wall, the step S3 it
After further include step:
S421, judge whether bracelet moves, if so, starting the proximity sensor being set on bracelet;
S422, the data that the proximity sensor is sent are received, judges whether bracelet is removed according to the data, if
It is the successful identity information of certification for then removing registration.
Seen from the above description, when sensing that bracelet is removed, the successful identity information of the certification of preservation is carried out clear
It removes, the safety of authentication can be improved.
Embodiment one
Please refer to Fig. 1, a kind of identity identifying method based on vein, including step:
S1, reception are set to the ID authentication request that the touch sensor on bracelet is sent, and are asked according to the authentication
It asks, starts timing;
User can activate authentication procedures by pinning touch sensor, and maloperation in order to prevent can be described
A touch sensor is respectively arranged in the opposite both sides of bracelet, when only being pinned there are two touch sensor, just starts bracelet
Authentication procedures;
S2, the vein pattern figure that bracelet is set to the vein pattern collector transmission of bracelet inner wall in rotation process is received
Picture obtains corresponding first vein pattern vector according to the vein pattern image using deep learning algorithm, wherein can be with
The vein pattern image received is handled using existing deep learning algorithm, obtains vein pattern vector, the depth
It can be convolutional neural networks CNN algorithms, support vector machines algorithm, PDA (Penalized to spend learning algorithm
Discriminant Analysis) algorithm, random forests algorithm etc., wherein it is preferred that CNN algorithms;
As shown in figure 3, the vein pattern collector includes two linear array dynamic visual sensors, two linear arrays are dynamic
State visual sensor is at the orthogonal arrangement of " ten " font;The linear array dynamic visual sensor is by multiple dynamic vision pixels
Arrange in alignment form, it is preferred that 3 line battle array dynamic visual sensors can be selected, i.e., by 3 dynamic vision pixels
The straight line for being arranged in a straight line, and being formed after enabling the dynamic vision pixel of the linear array dynamic visual sensor arrange
Direction is parallel or vertical with the circumferential direction of the bracelet main body, since the dynamic vision that bracelet inner wall is equipped with " ten " word structure senses
Device so that either rotate bracelet and either move bracelet along orientation arm, can be imaged;
Dynamic visual sensor (Dynamic Vision Sensor, DVS) is a kind of event driven imaging sensor,
The only sensitive imaging sensor of the variation to captured object is a kind of mimic biology visual perception and handling principle, sampling
The novel photoelectric perception device that very large scale integration technology is realized, operation principle are as follows:The special construction of its pixel
Only change sensitive to the light intensity in scene and samples output, the light intensity variation that pixel independent detection is experienced, each pixel
Point continuously measures light intensity variable quantity, sends out signal when light variable quantity is more than the threshold value of setting, and be output asynchronously by bus,
Unrelated between pixel, there is no the limitations of " frame " in conventional image sensor.
During bracelet is rotated or moved along orientation arm, each pixel in dynamic visual sensor receives
Motion track on the infrared light of the backgrounds reflection such as arm skin do not change much, the variation for receiving light intensity is not above and sets
Fixed threshold value, pixel will not trigger signal, and when having vein on the track of pixel, because vein wants infrared absorption
Much larger than skin, when pixel is by above vein, the light of reception can change significantly, and be more than the threshold value of setting, therefore,
Pixel can trigger signal.Since dynamic visual sensor is continuous work on time and spatial domain, can effectively with
Track object of which movement, when with arm relative motion occurs for bracelet, all validity feature points on motion path can all be read,
Therefore, the picture shot by dynamic visual sensor includes only the effective informations such as the feature of vein, and the skin not comprising redundancy
The invalid background information such as skin, the vein pattern image transmitting collected through dynamic visual sensor to image processing module into
The calculating that deep learning algorithm realizes vein pattern vector may be used, due to being acquired by dynamic visual sensor in row processing
Vein spy characteristic image contain only vein distributed intelligence substantially, amount of redundant information is very small, data volume very little, therefore, phase
Than in the deep learning algorithm based on Normal visual sensor, the deep learning algorithm that image processing module uses only needs seldom
Layer can realize the calculating of vein pattern vector, and the requirement to calculating power, resource and power consumption will be much lower, thus, especially
Suitable for mobile wearable device.
S3, second whether had with the first vein pattern Vectors matching is retrieved in the vein pattern vector set to prestore
Feature vector, if so, authentication success, if it is not, judge whether time-out, if it is not, then authentication mistake, and judge whether
Time-out, if it is not, then return to step S2, if so, terminating authentication.
Embodiment two
The present embodiment is with one difference of embodiment:
Further include acquiring the vein pattern vector step that prestores before the step S1, it is specific as shown in Figure 4:
S0, judge whether bracelet uses for the first time, specifically, after initial charge, System self-test judges whether it is to make for the first time
With, if so, S01 is thened follow the steps, and otherwise, execution step S02;
S01, the vein pattern image that bracelet is sent along dynamic visual sensor described in orientation arm moving process is received,
According to the vein pattern image, corresponding third vein pattern vector is obtained using deep learning algorithm, the third is quiet
Arteries and veins feature vector is stored in the vein pattern vector set, and terminates to acquire the vein pattern vector step that prestores;
S02, it is determined whether to enable daily vein pattern vectors to acquire function, if so, executing step S021, otherwise, terminates
Acquire the vein pattern vector step that prestores;
S021, judge whether the vein pattern vector number in the vein pattern vector set is not less than the first preset value, if
It is no, S022 is thened follow the steps, otherwise, terminates to acquire the vein pattern vector step that prestores;
S022, judge otherwise whether the electricity of the bracelet, returns higher than the second preset value if so, thening follow the steps S023
Return step S021;
S023, the vein pattern figure that bracelet is sent along dynamic visual sensor described in orientation arm moving process is received
Picture obtains corresponding 4th vein pattern vector, by the described 4th according to the vein pattern image using deep learning algorithm
Vein pattern vector is stored in the vein pattern vector set, and return to step S021;
Wherein it is possible to prestore the function of vein pattern vector to open the acquisition of bracelet in the following way:It is mechanical, electrical in hand
Application program for controlling bracelet is installed in advance in the mobile terminals such as brain, pad, is carrying out the vein pattern vector acquisition that prestores
Before, bracelet is established by bluetooth and mobile terminal and is connected, and is connected to be established with the application program on mobile terminal, is then passed through
The prestore function of vein pattern vector of the acquisition of application program launching bracelet passes through closing application program if do not acquired.
Embodiment three
The present embodiment and the difference of embodiment two are:Further include step between the step S1 and step S2:
S11, judge whether the angle of the bracelet rotation is more than a predetermined angle, if so, S2 is thened follow the steps, otherwise,
Judge whether time-out, if it is not, return to step S11, otherwise, authentication failure.
Example IV
The present embodiment and the difference of embodiment one are:
In the step S3 after authentication success, further includes the successful identity information of Registration Authentication, pass through Registration Authentication
Successful identity information then shows that bracelet is in authentication success status;If authentication error, terminates and remove registered
The successful identity information of certification;
Further include step after the step S3, as shown in Figure 5:
S411, judge whether receive the ID authentication request of bluetooth or NFC or bracelet rotates or continuously struck
It hits under two, if so, starting timing, otherwise, bracelet keeps authentication success status;S412, judge whether to be registered with
The successful identity information of certification, if so, sending the successful identity information of certification to the bluetooth or NFC, if it is not, then prompting to use
Family carries out authentication, and user presses touch sensor and rotates, and carries out authentication;
Wherein it is determined that the mode of different activation bracelets, can improve the applicability of bracelet, bracelet can be made to be suitable for not
Same scene activates bracelet according to the difference of usage scenario there are two types of mode, to send user authentication success to external equipment
Identity information, open the door etc. usage scenarios, only when user rotate bracelet or continuously tap twice bracelets when, bracelet just can quilt
Activation, if bracelet is registered with the successful identity information of certification, bracelet just sends the successful identity information of certification to external equipment;
And under the usage scenarios such as such as NFC payment, by bracelet close to NFC device, bracelet receives the identity that NFC device is sent out to be recognized user
After card request, if bracelet is registered with the successful identity information of certification, directly the successful identity letter of certification will be sent to NFC device
Breath, bracelet vibration prompting user is to indicate to have carried out the transmission of information later;
S413, judge whether to receive bluetooth or effective return information of NFC, if so, authentication is completed, otherwise,
Judge whether time-out, if it is not, then return to step S412, otherwise, bracelet keep authentication success status;
S421, judge whether bracelet moves, specifically, acceleration transducer can be set on bracelet, pass through acceleration
Sensor judges whether bracelet moves, if so, starting the proximity sensor being set on bracelet;
S422, the data that the proximity sensor is sent are received, judges whether bracelet is removed according to the data, if
It is the successful identity information of certification for then removing registration;
Wherein, step S411-S413 and step S421-S422 is parallel flow.
Embodiment five
Fig. 2, a kind of authentication bracelet 1 based on vein, including touch sensor 2 are please referred to, further includes:
Vein pattern collector 3, the vein pattern collector 3 are set to 1 inner wall of the bracelet, and the vein pattern is adopted
Storage 3 includes two linear array dynamic visual sensors, and two linear array dynamic visual sensors are orthogonal at " ten " font
Arrangement;
Proximity sensor, the proximity sensor are set to 1 inner wall (not shown) of the bracelet;
It stores 4 devices, processor 5 and is stored in the computer journey that can be run on the memory and on the processor
Sequence, the processor 5 realize each step of any one embodiment in embodiment one to four when executing the computer program.
In conclusion a kind of identity identifying method and bracelet based on vein provided by the invention, are passed using dynamic vision
Sensor acquires vein pattern, and the dynamic visual sensor is linear array dynamic visual sensor;The vein pattern collector packet
Two linear array dynamic visual sensors are included, two linear array dynamic visual sensors are at the orthogonal row of " ten " font
Row, due to dynamic visual sensor is based on the variation of shooting area and the operation principle that is imaged, there is no traditional sensors
Problem, it is very low to light requirement, it can work well under very low or very bright light condition, be by light intensity
Variation generates asynchronous event vector, and digitized vein distribution characteristics figure, acquired image are generated by simply converting
The only effective informations such as feature comprising vein do not include the invalid background informations such as the skin of redundancy, are receiving the vein
After characteristic image, compared to the deep learning algorithm based on Normal visual sensor, it is only necessary to which seldom layer can be realized quiet
The calculating of arteries and veins feature vector can largely reduce the calculation amount of image procossing, reduce power consumption, be suitble to integrate, know simultaneously
It does not work well.
Example the above is only the implementation of the present invention is not intended to limit the scope of the invention, every to utilize this hair
Equivalents made by bright specification and accompanying drawing content are applied directly or indirectly in relevant technical field, include similarly
In the scope of patent protection of the present invention.
Claims (10)
1. a kind of identity identifying method based on vein, which is characterized in that including step:
The ID authentication request that the touch sensor that S1, reception are set on bracelet is sent is opened according to the ID authentication request
Beginning timing;
S2, the vein pattern image that bracelet is set to the vein pattern collector transmission of bracelet inner wall in rotation process is received,
According to the vein pattern image, corresponding first vein pattern vector, the vein pattern are obtained using deep learning algorithm
Collector includes two linear array dynamic visual sensors, and two linear array dynamic visual sensors are orthogonal at " ten " font
Arrangement, the linear array dynamic visual sensor are formed by the arrangement of multiple dynamic vision pixels is in alignment;
S3, the second feature whether having with the first vein pattern Vectors matching is retrieved in the vein pattern vector set to prestore
Vector, if so, authentication success, if it is not, then authentication mistake, and judge whether time-out, if it is not, then return to step
S2。
2. a kind of identity identifying method based on vein according to claim 1, which is characterized in that
Further include acquiring the vein pattern vector step that prestores before the step S1:
S0, judge whether bracelet uses for the first time, if so, thening follow the steps S01, otherwise, execute step S02;
S01, the vein pattern image that bracelet is sent along dynamic visual sensor described in orientation arm moving process is received, according to
The vein pattern image obtains corresponding third vein pattern vector, by third vein spy using deep learning algorithm
Sign vector is stored in the vein pattern vector set, and terminates to acquire the vein pattern vector step that prestores;
S02, it is determined whether to enable daily vein pattern vectors to acquire function, if so, executing step S021, otherwise, terminates acquisition
Prestore vein pattern vector step;
S021, judge whether the vein pattern vector number in the vein pattern vector set is not less than the first preset value, if it is not, then
Step S022 is executed, otherwise, terminates to acquire the vein pattern vector step that prestores;
S022, judge whether the electricity of the bracelet is higher than the second preset value, if so, thening follow the steps S023, otherwise, return to step
Rapid S021;
S023, the vein pattern image that bracelet is sent along dynamic visual sensor described in orientation arm moving process, root are received
According to the vein pattern image, corresponding 4th vein pattern vector is obtained using deep learning algorithm, by the 4th vein
Feature vector is stored in the vein pattern vector set, and return to step S021.
3. a kind of identity identifying method based on vein according to claim 2, which is characterized in that the step S1 and step
Further include step between rapid S2:
S11, judge whether the angle of the bracelet rotation is more than a predetermined angle, if so, thening follow the steps S2, otherwise, judge
It is whether overtime, if it is not, return to step S11, otherwise, authentication failure.
4. a kind of identity identifying method based on vein according to claim 1, which is characterized in that body in the step S3
Further include the successful identity information of Registration Authentication after part certification success;
Further include step after the step S3:
S411, judge whether receive the ID authentication request of bluetooth or NFC or bracelet rotates or continuously tapped two
Under, if so, starting timing;
S412, judge whether to be registered with the successful identity information of certification, if so, sending the successful identity information of certification to described
Bluetooth or NFC;
S413, judge whether to receive bluetooth or effective return information of NFC, if so, completing authentication, otherwise, judge
It is whether overtime, if it is not, then return to step S412.
5. a kind of identity identifying method based on vein according to claim 1, which is characterized in that after the step S3
It further include step:
S421, judge whether bracelet moves, if so, starting the proximity sensor being set on bracelet;
S422, the data that the proximity sensor is sent are received, judges whether bracelet is removed according to the data, if so,
Remove the successful identity information of certification of registration.
6. a kind of authentication bracelet based on vein, including touch sensor, which is characterized in that further include:
Vein pattern collector, the vein pattern collector are set to the bracelet inner wall, the vein pattern collector packet
Two linear array dynamic visual sensors are included, two linear array dynamic visual sensors are at the orthogonal arrangement of " ten " font;
Memory, processor and it is stored in the computer program that can be run on the memory and on the processor, it is described
Processor realizes following steps when executing the computer program:
S1, the ID authentication request that the touch sensor is sent is received, according to the ID authentication request, starts timing;
S2, the vein pattern image that bracelet vein pattern collector described in rotation process is sent is received, according to the vein
Characteristic image obtains corresponding first vein pattern vector using deep learning algorithm, and the vein pattern collector includes two
A linear array dynamic visual sensor, two linear array dynamic visual sensors are at the orthogonal arrangement of " ten " font, the line
Battle array dynamic visual sensor is formed by the arrangement of multiple dynamic vision pixels is in alignment;
S3, the second feature whether having with the first vein pattern Vectors matching is retrieved in the vein pattern vector set to prestore
Vector, if so, authentication success, if it is not, then authentication mistake, and judge whether time-out, if it is not, then return to step
S2。
7. a kind of authentication bracelet based on vein according to claim 6, which is characterized in that
Further include acquiring the vein pattern vector step that prestores before the step S1:
S0, judge whether bracelet uses for the first time, if so, thening follow the steps S01, otherwise, execute step S02;
S01, the vein pattern image that bracelet is sent along dynamic visual sensor described in orientation arm moving process is received, according to
The vein pattern image obtains corresponding third vein pattern vector, by third vein spy using deep learning algorithm
Sign vector is stored in the vein pattern vector set, and terminates to acquire the vein pattern vector step that prestores;
S02, it is determined whether to enable daily vein pattern vectors to acquire function, if so, executing step S021, otherwise, terminates acquisition
Prestore vein pattern vector step;
S021, judge whether the vein pattern vector number in the vein pattern vector set is not less than the first preset value, if it is not, then
Step S022 is executed, otherwise, terminates to acquire the vein pattern vector step that prestores;
S022, judge whether the electricity of the bracelet is higher than the second preset value, if so, thening follow the steps S023, otherwise, return to step
Rapid S021;
S023, the vein pattern image that bracelet is sent along dynamic visual sensor described in orientation arm moving process, root are received
According to the vein pattern image, corresponding 4th vein pattern vector is obtained using deep learning algorithm, by the 4th vein
Feature vector is stored in the vein pattern vector set, and return to step S021.
8. a kind of authentication bracelet based on vein according to claim 7, which is characterized in that the step S1 and step
Further include step between rapid S2:
S11, judge whether the angle of the bracelet rotation is more than a predetermined angle, if so, thening follow the steps S2, otherwise, judge
It is whether overtime, if it is not, return to step S11, otherwise, authentication failure.
9. a kind of authentication bracelet based on vein according to claim 6, which is characterized in that body in the step S3
Further include the successful identity information of Registration Authentication after part certification success;
Further include step after the step S3:
S411, judge whether receive the ID authentication request of bluetooth or NFC or bracelet rotates or continuously tapped two
Under, if so, starting timing;
S412, judge whether to be registered with the successful identity information of certification, if so, sending the successful identity information of certification to described
Bluetooth or NFC;
S413, judge whether to receive bluetooth or effective return information of NFC, if so, completing authentication, otherwise, judge
It is whether overtime, if it is not, then return to step S412.
10. a kind of authentication bracelet based on vein according to claim 6, which is characterized in that further include approaching biography
Sensor, the proximity sensor are set to the bracelet inner wall, further include step after the step S3:
S421, judge whether bracelet moves, if so, starting the proximity sensor;
S422, the data that the proximity sensor is sent are received, judges whether bracelet is removed according to the data, if so,
Remove the successful identity information of certification of registration.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810359301.1A CN108563937B (en) | 2018-04-20 | 2018-04-20 | Vein-based identity authentication method and wristband |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810359301.1A CN108563937B (en) | 2018-04-20 | 2018-04-20 | Vein-based identity authentication method and wristband |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108563937A true CN108563937A (en) | 2018-09-21 |
CN108563937B CN108563937B (en) | 2021-10-15 |
Family
ID=63535846
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810359301.1A Active CN108563937B (en) | 2018-04-20 | 2018-04-20 | Vein-based identity authentication method and wristband |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108563937B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111341403A (en) * | 2020-02-25 | 2020-06-26 | 泰康保险集团股份有限公司 | Patient state monitoring method, device, equipment and computer-readable storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103870986A (en) * | 2012-12-12 | 2014-06-18 | 周良文 | Physical store-based online shopping system and method |
US20140223374A1 (en) * | 2013-02-07 | 2014-08-07 | Samsung Electronics Co., Ltd. | Method of displaying menu based on depth information and space gesture of user |
CN104486306A (en) * | 2014-12-04 | 2015-04-01 | 北京邮电大学 | Method for identity authentication based on finger vein recognition and cloud service |
CN105844128A (en) * | 2015-01-15 | 2016-08-10 | 北京三星通信技术研究有限公司 | Method and device for identity identification |
CN107403154A (en) * | 2017-07-20 | 2017-11-28 | 四川大学 | A kind of gait recognition method based on dynamic visual sensor |
CN107481001A (en) * | 2017-07-28 | 2017-12-15 | 深圳先进技术研究院 | A kind of mobile-payment system based on vein identification technology and wearable smart machine |
-
2018
- 2018-04-20 CN CN201810359301.1A patent/CN108563937B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103870986A (en) * | 2012-12-12 | 2014-06-18 | 周良文 | Physical store-based online shopping system and method |
US20140223374A1 (en) * | 2013-02-07 | 2014-08-07 | Samsung Electronics Co., Ltd. | Method of displaying menu based on depth information and space gesture of user |
CN104486306A (en) * | 2014-12-04 | 2015-04-01 | 北京邮电大学 | Method for identity authentication based on finger vein recognition and cloud service |
CN105844128A (en) * | 2015-01-15 | 2016-08-10 | 北京三星通信技术研究有限公司 | Method and device for identity identification |
CN107403154A (en) * | 2017-07-20 | 2017-11-28 | 四川大学 | A kind of gait recognition method based on dynamic visual sensor |
CN107481001A (en) * | 2017-07-28 | 2017-12-15 | 深圳先进技术研究院 | A kind of mobile-payment system based on vein identification technology and wearable smart machine |
Non-Patent Citations (2)
Title |
---|
J.R. SPLETZER: "A framework for sensor planning and control with applications to vision guided multi-robot systems", 《IEEE》 * |
张成浩: "基于手背静脉的身份识别技术研究", 《万方数据》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111341403A (en) * | 2020-02-25 | 2020-06-26 | 泰康保险集团股份有限公司 | Patient state monitoring method, device, equipment and computer-readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN108563937B (en) | 2021-10-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107609383B (en) | 3D face identity authentication method and device | |
US11238270B2 (en) | 3D face identity authentication method and apparatus | |
US11580203B2 (en) | Method and apparatus for authenticating a user of a computing device | |
WO2019080579A1 (en) | 3d face identity authentication method and apparatus | |
JP7070588B2 (en) | Biometrics, systems, methods and programs | |
JP6722272B2 (en) | User identification and/or authentication using gaze information | |
CN108563936B (en) | Task execution method, terminal device and computer-readable storage medium | |
ES2859554T3 (en) | Impersonation detection for biometric authentication | |
JP3558025B2 (en) | Personal authentication device and method | |
CN109858316A (en) | System and method for biometric identification | |
EP2434372A2 (en) | Controlled access to functionality of a wireless device | |
CN109886080A (en) | Human face in-vivo detection method, device, electronic equipment and readable storage medium storing program for executing | |
CN111445640A (en) | Express delivery pickup method, device, equipment and storage medium based on iris recognition | |
Liu et al. | Line-scan system for continuous hand authentication | |
CN107209936B (en) | Information processing apparatus, information processing method, and program | |
CN108563937A (en) | A kind of identity identifying method and bracelet based on vein | |
Barra et al. | Have you permission to answer this phone? | |
CN109496308A (en) | The method, apparatus and electronic equipment of living things feature recognition | |
EP2875495B1 (en) | Method for authenticating a user of a contactless chip card | |
Shao et al. | Eye-based recognition for user identification on mobile devices | |
CN109635622A (en) | Personal identification method, device and electronic equipment | |
WO2022180890A1 (en) | Biometric authentication system, authentication terminal, and authentication method | |
CN208144609U (en) | A kind of wrist vein authentication bracelet | |
CN208156685U (en) | A kind of vein authentication finger ring | |
EP4398136A1 (en) | Electronic device for controlling biometric signal-based operation, and operating method therefor |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20191010 Address after: 100089 Room 101, floor 1, building 9, No. 28, gaoliangqiaoxie street, Haidian District, Beijing 114 Applicant after: Beijing Ruisi smart core technology Co., Ltd. Address before: 518000 Guangdong Shenzhen Baoan District Fuyong street Fuyong Vanke gold area 5D1302 room Applicant before: Deng Jian |
|
GR01 | Patent grant | ||
GR01 | Patent grant |