CN108563937B - Vein-based identity authentication method and wristband - Google Patents
Vein-based identity authentication method and wristband Download PDFInfo
- Publication number
- CN108563937B CN108563937B CN201810359301.1A CN201810359301A CN108563937B CN 108563937 B CN108563937 B CN 108563937B CN 201810359301 A CN201810359301 A CN 201810359301A CN 108563937 B CN108563937 B CN 108563937B
- Authority
- CN
- China
- Prior art keywords
- vein feature
- vein
- bracelet
- judging whether
- feature 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—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)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Collating Specific Patterns (AREA)
- Image Input (AREA)
Abstract
The invention provides an identity authentication method and a bracelet based on veins, which adopt a dynamic visual sensor to collect vein features, wherein the dynamic visual sensor is a linear array dynamic visual sensor; the vein feature collector comprises two linear array dynamic visual sensors which are vertically arranged in a cross shape, images collected by the dynamic visual sensors only contain effective information such as vein features and the like and do not contain redundant ineffective background information such as skin and the like, and after the vein feature images are received, compared with a deep learning algorithm based on a common visual sensor, the vein feature vector calculation can be realized by only few layers, so that the calculation amount of image processing can be greatly reduced, the power consumption is reduced, the vein feature collector is suitable for integration, and meanwhile, the identification effect is good.
Description
Technical Field
The invention relates to the technical field of intelligent identity recognition, in particular to an identity authentication method based on veins and a bracelet.
Background
Medical studies have demonstrated that the shape of veins is unique and stable. The vein identification system has the characteristics of living body identification, internal characteristics and non-contact, ensures that the vein characteristics of a user are difficult to forge, and is far superior to identification technologies such as fingerprints, irises, faces and the like in terms of high safety, practicability, convenience and the like, so the vein-based identity authentication is particularly suitable for places with high safety requirements, in particular to a wrist vein identity authentication system.
The existing wrist type identity authentication system based on veins usually collects vein images at fixed positions through an image sensor, then processes the collected vein images through an image processing module, removes vein image backgrounds, extracts useful vein feature images, obtains vein feature vectors based on the vein feature images, and finally compares the obtained vein feature vectors with pre-stored vein feature vectors, if the vein feature vectors are the same, the authentication is passed, otherwise, the authentication is failed.
However, the existing vein-based wrist authentication system has the following disadvantages: first, a common image sensor is used, which has strict requirements on light and has poor recognition effect under strong light or dark light conditions. In addition, in the process of acquiring the image, if the bracelet moves, the acquired image is very blurred; secondly, since the vein image containing the background is acquired, the acquired image has highly redundant data, the image processing module needs to perform complex calculation for removing the background and extracting the vein feature image, the calculation process is complex, the data processing amount is large, and a large amount of calculation resources are needed.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the vein-based identity authentication method and device are small in calculation amount and good in identification effect.
In order to solve the technical problems, the invention adopts a technical scheme that:
a vein-based identity authentication method, comprising the steps of:
s1, receiving an identity authentication request sent by a touch sensor arranged on the bracelet, and starting timing according to the identity authentication request;
s2, receiving a vein feature image sent by a vein feature collector arranged on the inner wall of the bracelet during rotation of the bracelet, and obtaining a corresponding first vein feature vector by adopting a deep learning algorithm according to the vein feature image, wherein the vein feature collector comprises two linear array dynamic vision sensors which are vertically arranged in a cross shape, and the linear array dynamic vision sensors are formed by arranging a plurality of dynamic vision pixels into a straight line;
s3, searching whether a second feature vector matched with the first vein feature vector exists in the pre-stored vein feature vector set, if yes, successfully authenticating the identity, if not, wrongly authenticating the identity, judging whether the time is out, and if not, returning to the step S2.
In order to solve the technical problem, the invention adopts another technical scheme as follows:
a vein-based authentication bracelet, comprising a touch sensor, further comprising:
the vein feature collector is arranged on the inner wall of the bracelet and comprises two linear array dynamic visual sensors which are vertically arranged in a cross shape;
a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
s1, receiving an identity authentication request sent by the touch sensor, and starting timing according to the identity authentication request;
s2, receiving a vein feature image sent by the vein feature collector in the rotation process of the bracelet, and obtaining a corresponding first vein feature vector by adopting a deep learning algorithm according to the vein feature image, wherein the vein feature collector comprises two linear array dynamic visual sensors which are vertically arranged in a cross shape, and the linear array dynamic visual sensors are formed by arranging a plurality of dynamic visual pixels into a straight line;
s3, searching whether a second feature vector matched with the first vein feature vector exists in the pre-stored vein feature vector set, if yes, successfully authenticating the identity, if not, wrongly authenticating the identity, judging whether the time is out, and if not, returning to the step S2.
The invention has the beneficial effects that: collecting vein characteristics by adopting a dynamic vision sensor, wherein the dynamic vision sensor is a linear array dynamic vision sensor; the vein feature collector comprises two linear array dynamic visual sensors which are arranged in a cross shape and are mutually perpendicular, and the dynamic visual sensors have the working principle of imaging based on the change of a shooting area, have no problems of the traditional sensors, have low light requirement, can well work under the condition of very low or very bright light, generate asynchronous event vectors through the change of light intensity, generate a digital vein distribution feature map through simple transformation, and the collected image only contains effective information such as vein features and the like and does not contain redundant background information such as skin and the like, and after receiving the vein feature image, compared with a deep learning algorithm based on a common visual sensor, the vein feature vector can be calculated by only needing few layers, so that the calculated amount of image processing can be greatly reduced, the power consumption is reduced, the integration is suitable, and meanwhile, the identification effect is good.
Drawings
FIG. 1 is a flow chart of a vein-based authentication method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a vein-based authentication bracelet according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a dynamic visual sensor of a vein-based authentication bracelet according to an embodiment of the present invention;
FIG. 4 is a flowchart of a method for collecting pre-stored vein feature vectors according to an embodiment of the present invention;
FIG. 5 is a flowchart of performing continuous identity authentication according to an embodiment of the present invention;
description of reference numerals:
1. a vein-based authentication bracelet; 2. a touch sensor; 3. a vein feature collector; 4. a processor; 5. a memory; 6. a dynamic vision sensor.
Detailed Description
In order to explain technical contents, achieved objects, and effects of the present invention in detail, the following description is made with reference to the accompanying drawings in combination with the embodiments.
The most key concept of the invention is as follows: acquiring a vein characteristic image by adopting a dynamic vision sensor, wherein the dynamic vision sensor is a linear array dynamic vision sensor; the vein feature collector comprises two linear array dynamic visual sensors, the two linear array dynamic visual sensors are vertically arranged in a cross shape, and corresponding vein feature vectors are obtained by adopting a deep learning algorithm according to collected vein feature images.
Referring to fig. 1, a vein-based identity authentication method includes the steps of:
s1, receiving an identity authentication request sent by a touch sensor arranged on the bracelet, and starting timing according to the identity authentication request;
s2, receiving a vein feature image sent by a vein feature collector arranged on the inner wall of the bracelet during rotation of the bracelet, and obtaining a corresponding first vein feature vector by adopting a deep learning algorithm according to the vein feature image, wherein the vein feature collector comprises two linear array dynamic vision sensors which are vertically arranged in a cross shape, and the linear array dynamic vision sensors are formed by arranging a plurality of dynamic vision pixels into a straight line;
s3, searching whether a second feature vector matched with the first vein feature vector exists in the pre-stored vein feature vector set, if yes, successfully authenticating the identity, if not, wrongly authenticating the identity, judging whether the time is out, and if not, returning to the step S2.
From the above description, the beneficial effects of the present invention are: collecting vein characteristics by adopting a dynamic vision sensor, wherein the dynamic vision sensor is a linear array dynamic vision sensor; the vein feature collector comprises two linear array dynamic visual sensors which are arranged in a cross shape and are mutually perpendicular, and the dynamic visual sensors have the working principle of imaging based on the change of a shooting area, have no problems of the traditional sensors, have low light requirement, can well work under the condition of very low or very bright light, generate asynchronous event vectors through the change of light intensity, generate a digital vein distribution feature map through simple transformation, and the collected image only contains effective information such as vein features and the like and does not contain redundant background information such as skin and the like, and after receiving the vein feature image, compared with a deep learning algorithm based on a common visual sensor, the vein feature vector can be calculated by only needing few layers, so that the calculated amount of image processing can be greatly reduced, the power consumption is reduced, the integration is suitable, and meanwhile, the identification effect is good.
Further, before the step S1, the method further includes the step of collecting pre-stored vein feature vectors:
s0, judging whether the bracelet is used for the first time, if so, executing a step S01, otherwise, executing a step S02;
s01, receiving a vein feature image sent by the dynamic vision sensor in the process that the bracelet moves along the arm direction, obtaining a corresponding third vein feature vector by adopting a deep learning algorithm according to the vein feature image, storing the third vein feature vector into the vein feature vector set, and finishing the step of collecting the pre-stored vein feature vectors;
s02, judging whether the daily vein feature vector collection function is started, if so, executing the step S021, otherwise, finishing the step of collecting the pre-stored vein feature vectors;
s021, judging whether the number of the vein feature vectors in the vein feature vector set is not less than a first preset value, if not, executing a step S022, otherwise, finishing the step of collecting the pre-stored vein feature vectors;
s022, judging whether the electric quantity of the bracelet is higher than a second preset value, if so, executing a step S023, otherwise, returning to the step S021;
s023, receiving a vein feature image sent by the dynamic vision sensor in the process that the bracelet moves along the arm direction, obtaining a corresponding fourth vein feature vector by adopting a deep learning algorithm according to the vein feature image, storing the fourth vein feature vector into the vein feature vector set, and returning to the step S021.
According to the description, the collection of the pre-stored vein feature vectors is carried out through various ways to realize the local storage of the pre-stored vein feature vectors, so that the flexibility of the collection of the pre-stored vein feature vectors is improved, and the pre-stored vein feature vectors can be ensured to be sufficient, thereby realizing the faster and safer identity authentication.
Further, the method between the step S1 and the step S2 further includes the steps of:
s11, judging whether the rotation angle of the bracelet is larger than a preset angle, if so, executing the step S2, otherwise, judging whether the rotation angle is overtime, if not, returning to the step S11, otherwise, failing to authenticate the identity.
As can be known from the above description, the vein feature image sent by the dynamic visual sensor after the bracelet is moved in the arm direction is received when the pre-stored vein feature vector is collected, and the vein feature image sent by the dynamic visual sensor after the bracelet is rotated is received when the identity authentication is performed, so that the rotation angle of the bracelet needs to ensure that the vein feature collector passes through the wrist region corresponding to the pre-stored vein feature vector, and thus enough information is available to determine whether the identity is correct, for example, if the number of the vein feature collectors is 1, more than one turn needs to be performed, if the number of the vein feature collectors uniformly distributed along the circumferential direction of the inner wall of the bracelet is 6, more than 60 degrees need to be performed, that is, if the number of the vein feature collectors is N, the angle of the turn of the bracelet needs to exceed 360 °/N to ensure that enough information is available to determine whether the identity is correct, therefore, the validity of the identity authentication is guaranteed, and therefore, when the rotating angle of the bracelet is larger than the preset value, subsequent receiving and extracting operations are carried out, calculation is reduced, and the validity of the identity authentication at each time is guaranteed.
Further, after the identity authentication in step S3 is successful, the method further includes registering the identity information that is successfully authenticated;
the step S3 is followed by the step of:
s411, judging whether an identity authentication request of Bluetooth or NFC is received or not, or whether the bracelet rotates or is continuously knocked for two times or not, and if so, starting timing;
s412, judging whether the identity information which is successfully authenticated is registered, if so, sending the identity information which is successfully authenticated to the Bluetooth or the NFC;
and S413, judging whether effective reply information of Bluetooth or NFC is received, if so, finishing identity authentication, otherwise, judging whether timeout occurs, and if not, returning to the step S412.
According to the description, after the identity authentication is successful, the identity information which is successfully authenticated is registered, so that the continuous identity authentication can be realized, and the use is more convenient.
Further, the step S3 is followed by the step of:
s421, judging whether the bracelet moves, and if so, starting a proximity sensor arranged on the bracelet;
s422, receiving the data sent by the proximity sensor, judging whether the bracelet is taken down or not according to the data, and if so, clearing the registered identity information which is successfully authenticated.
According to the description, when the bracelet is sensed to be taken down, the stored identity information which is successfully authenticated is cleared, and the security of identity authentication can be improved.
Referring to fig. 2, an authentication bracelet based on vein includes a touch sensor, and further includes:
the vein feature collector is arranged on the inner wall of the bracelet and comprises two linear array dynamic vision sensors which are vertically arranged in a cross shape, and the linear array dynamic vision sensors are formed by arranging a plurality of dynamic vision pixels into a straight line;
a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
s1, receiving an identity authentication request sent by the touch sensor, and starting timing according to the identity authentication request;
s2, receiving a vein feature image sent by the vein feature collector in the rotation process of the bracelet, and obtaining a corresponding first vein feature vector by adopting a deep learning algorithm according to the vein feature image, wherein the vein feature collector comprises two linear array dynamic visual sensors which are vertically arranged in a cross shape;
s3, searching whether a second feature vector matched with the first vein feature vector exists in the pre-stored vein feature vector set, if yes, successfully authenticating, if not, judging whether the second feature vector is overtime, if not, mistakenly authenticating, judging whether the second feature vector is overtime, and if not, returning to the step S2.
From the above description, the beneficial effects of the present invention are: collecting vein characteristics by adopting a dynamic vision sensor, wherein the dynamic vision sensor is a linear array dynamic vision sensor; the vein feature collector comprises two linear array dynamic visual sensors which are arranged in a cross shape and are mutually perpendicular, and the dynamic visual sensors have the working principle of imaging based on the change of a shooting area, have no problems of the traditional sensors, have low light requirement, can well work under the condition of very low or very bright light, generate asynchronous event vectors through the change of light intensity, generate a digital vein distribution feature map through simple transformation, and the collected image only contains effective information such as vein features and the like and does not contain redundant background information such as skin and the like, and after receiving the vein feature image, compared with a deep learning algorithm based on a common visual sensor, the vein feature vector can be calculated by only needing few layers, so that the calculated amount of image processing can be greatly reduced, the power consumption is reduced, the integration is suitable, and meanwhile, the identification effect is good.
Further, before the step S1, the method further includes the step of collecting pre-stored vein feature vectors:
s0, judging whether the bracelet is used for the first time, if so, executing a step S01, otherwise, executing a step S02;
s01, receiving a vein feature image sent by the dynamic vision sensor in the process that the bracelet moves along the arm direction, obtaining a corresponding third vein feature vector by adopting a deep learning algorithm according to the vein feature image, storing the third vein feature vector into the vein feature vector set, and finishing the step of collecting the pre-stored vein feature vectors;
s02, judging whether the daily vein feature vector collection function is started, if so, executing the step S021, otherwise, finishing the step of collecting the pre-stored vein feature vectors;
s021, judging whether the number of the vein feature vectors in the vein feature vector set is not less than a first preset value, if not, executing a step S022, otherwise, finishing the step of collecting the pre-stored vein feature vectors;
s022, judging whether the electric quantity of the bracelet is higher than a second preset value, if so, executing a step S023, otherwise, returning to the step S021;
s023, receiving a vein feature image sent by the dynamic vision sensor in the process that the bracelet moves along the arm direction, obtaining a corresponding fourth vein feature vector by adopting a deep learning algorithm according to the vein feature image, storing the fourth vein feature vector into the vein feature vector set, and returning to the step S021.
According to the description, the collection of the pre-stored vein feature vectors is carried out through various ways to realize the local storage of the pre-stored vein feature vectors, so that the flexibility of the collection of the pre-stored vein feature vectors is improved, and the pre-stored vein feature vectors can be ensured to be sufficient, thereby realizing the faster and safer identity authentication.
Further, the method between the step S1 and the step S2 further includes the steps of:
s11, judging whether the rotation angle of the bracelet is larger than a preset angle, if so, executing the step S2, otherwise, judging whether the rotation angle is overtime, if not, returning to the step S11, otherwise, failing to authenticate the identity.
As can be known from the above description, the vein feature image sent by the dynamic visual sensor after the bracelet is moved in the arm direction is received when the pre-stored vein feature vector is collected, and the vein feature image sent by the dynamic visual sensor after the bracelet is rotated is received when the identity authentication is performed, so that the rotation angle of the bracelet needs to ensure that the vein feature collector passes through the wrist region corresponding to the pre-stored vein feature vector, and thus enough information is available to determine whether the identity is correct, for example, if the number of the vein feature collectors is 1, more than one turn needs to be performed, if the number of the vein feature collectors uniformly distributed along the circumferential direction of the inner wall of the bracelet is 6, more than 60 degrees need to be performed, that is, if the number of the vein feature collectors is N, the angle of the turn of the bracelet needs to exceed 360 °/N to ensure that enough information is available to determine whether the identity is correct, therefore, the validity of the identity authentication is guaranteed, subsequent receiving and extracting operations are carried out when the rotating angle of the bracelet is larger than the preset value, not only is the calculation reduced, but also the validity of the identity authentication at each time is guaranteed, and meanwhile if a plurality of vein feature collectors are arranged, the vein distribution of a plurality of parts of the wrist can be extracted, including the back, the side and the front of the wrist, more vein feature points are provided, and the wrist has irreproducibility and higher safety.
Further, after the identity authentication in step S3 is successful, the method further includes registering the identity information that is successfully authenticated;
the step S3 is followed by the step of:
s411, judging whether an identity authentication request of Bluetooth or NFC is received or not, or whether the bracelet rotates or is continuously knocked for two times or not, and if so, starting timing;
s412, judging whether the identity information which is successfully authenticated is registered, if so, sending the identity information which is successfully authenticated to the Bluetooth or the NFC;
and S413, judging whether effective reply information of Bluetooth or NFC is received, if so, finishing identity authentication, otherwise, judging whether timeout occurs, and if not, returning to the step S412.
According to the description, after the identity authentication is successful, the identity information which is successfully authenticated is registered, so that the continuous identity authentication can be realized, and the use is more convenient.
Further, still include proximity sensor, proximity sensor locates bracelet inner wall, still include the step after step S3:
s421, judging whether the bracelet moves, and if so, starting a proximity sensor arranged on the bracelet;
s422, receiving the data sent by the proximity sensor, judging whether the bracelet is taken down or not according to the data, and if so, clearing the registered identity information which is successfully authenticated.
According to the description, when the bracelet is sensed to be taken down, the stored identity information which is successfully authenticated is cleared, and the security of identity authentication can be improved.
Example one
Referring to fig. 1, a vein-based identity authentication method includes the steps of:
s1, receiving an identity authentication request sent by a touch sensor arranged on the bracelet, and starting timing according to the identity authentication request;
the user can activate the identity authentication process by pressing the touch sensors, in order to prevent misoperation, the two opposite sides of the bracelet can be respectively provided with one touch sensor, and the identity authentication process of the bracelet is started only when the two touch sensors are pressed;
s2, receiving a vein feature image sent by a vein feature collector arranged on the inner wall of the bracelet during rotation of the bracelet, and obtaining a corresponding first vein feature vector by adopting a deep learning algorithm according to the vein feature image, wherein the received vein feature image can be processed by adopting the existing deep learning algorithm to obtain the vein feature vector, the deep learning algorithm can be a Convolutional Neural Network (CNN) algorithm, a Support Vector Machine (SVM) algorithm, a Personal Digital Assistant (PDA) (classified cognitive analysis) algorithm, a random forest algorithm and the like, and the CNN algorithm is preferably selected;
as shown in fig. 3, the vein feature collector includes two linear array dynamic vision sensors, and the two linear array dynamic vision sensors are arranged in a cross shape and are perpendicular to each other; the linear array dynamic vision sensor is formed by arranging a plurality of dynamic vision pixel points into a straight line, preferably, a 3-row linear array dynamic vision sensor can be selected, namely, 3 dynamic vision pixel points are arranged into a straight line, the direction of the straight line formed after the dynamic vision pixel points of the linear array dynamic vision sensor are arranged is parallel to or vertical to the circumferential direction of the bracelet main body, and the dynamic vision sensor with a cross-shaped structure is arranged on the inner wall of the bracelet, so that the bracelet can be imaged no matter the bracelet is rotated or moved along the arm direction;
a Dynamic Vision Sensor (DVS) is an event-driven image Sensor, which is only sensitive to the change of a photographed object, and is a novel photoelectric sensing device that simulates the biological visual sensing and processing principle and is implemented by sampling the super-large-scale integrated circuit technology, and the working principle is as follows: the special structure of the pixel points is only sensitive to the light intensity change in a scene and samples and outputs the light intensity change, the pixel points independently detect the sensed light intensity change, each pixel point continuously measures the light intensity change, when the light change exceeds a set threshold value, signals are sent out and asynchronously output through a bus, the pixel points are not related, and the limitation of frames in the traditional image sensor does not exist.
In the bracelet rotates or moves along the arm direction in-process, the infrared light of background reflection such as arm skin on the removal orbit that every pixel received among the dynamic vision sensor does not have too big change, the change of received light intensity does not exceed the threshold value of setting for, the pixel can not trigger signal, and when there is the vein on the orbit of pixel, because the vein will be far greater than skin to infrared absorption, the pixel has obvious change when the vein top, the received light can have, exceed the threshold value of setting for, therefore, the pixel can trigger signal. Because the dynamic visual sensor works continuously in time and space domains and can effectively track the motion of an object, when the bracelet and the arm move relatively, all effective characteristic points on the motion path can be read out, therefore, a picture shot by the dynamic visual sensor only contains effective information such as vein characteristics and the like, but does not contain redundant ineffective background information such as skin and the like, a vein characteristic image acquired by the dynamic visual sensor is transmitted to the image processing module for processing, the calculation of the vein characteristic vector can be realized by adopting a deep learning algorithm, because the vein characteristic image acquired by the dynamic visual sensor basically only contains vein distribution information, the redundant information quantity is very small, the data quantity is very small, compared with the deep learning algorithm based on the common visual sensor, the calculation of the vein characteristic vector can be realized by only few layers by adopting the deep learning algorithm adopted by the image processing module, the requirements on computing power, resources and power consumption are much lower, and therefore, the method is particularly suitable for mobile wearable devices.
S3, searching whether a second feature vector matched with the first vein feature vector exists in a pre-stored vein feature vector set, if yes, successfully authenticating, if not, judging whether the second feature vector is overtime, if not, mistakenly authenticating, judging whether the second feature vector is overtime, if not, returning to the step S2, and if yes, ending the identity authentication.
Example two
The difference between the present embodiment and the first embodiment is:
before step S1, the method further includes a step of collecting pre-stored vein feature vectors, as shown in fig. 4:
s0, judging whether the bracelet is used for the first time, specifically, after initial charging, performing system self-checking, judging whether the bracelet is used for the first time, if so, executing a step S01, otherwise, executing a step S02;
s01, receiving a vein feature image sent by the dynamic vision sensor in the process that the bracelet moves along the arm direction, obtaining a corresponding third vein feature vector by adopting a deep learning algorithm according to the vein feature image, storing the third vein feature vector into the vein feature vector set, and finishing the step of collecting the pre-stored vein feature vectors;
s02, judging whether the daily vein feature vector collection function is started, if so, executing the step S021, otherwise, finishing the step of collecting the pre-stored vein feature vectors;
s021, judging whether the number of the vein feature vectors in the vein feature vector set is not less than a first preset value, if not, executing a step S022, otherwise, finishing the step of collecting the pre-stored vein feature vectors;
s022, judging whether the electric quantity of the bracelet is higher than a second preset value, if so, executing a step S023, otherwise, returning to the step S021;
s023, receiving a vein feature image sent by the dynamic vision sensor in the process that the bracelet moves along the arm direction, obtaining a corresponding fourth vein feature vector by adopting a deep learning algorithm according to the vein feature image, storing the fourth vein feature vector into the vein feature vector set, and returning to the step S021;
wherein, can open the function of the collection prestore vein eigenvector of bracelet through following mode: the application program used for controlling the bracelet is installed in the mobile terminals such as the mobile phone, the computer and the pad in advance, before vein eigenvector collection prestores, the bracelet is connected with the mobile terminal through the Bluetooth, so that the connection with the application program on the mobile terminal is established, then the function of the collection prestore vein eigenvector of the bracelet is started through the application program, and if the collection is not performed, the collection is closed through the application program.
EXAMPLE III
The difference between this embodiment and the second embodiment is: the method between the step S1 and the step S2 further comprises the steps of:
s11, judging whether the rotation angle of the bracelet is larger than a preset angle, if so, executing the step S2, otherwise, judging whether the rotation angle is overtime, if not, returning to the step S11, otherwise, failing to authenticate the identity.
Example four
The difference between the present embodiment and the first embodiment is:
after the identity authentication in the step S3 is successful, the identity authentication method further includes registering identity information that the authentication is successful, and if the identity information that the authentication is successful is registered, it indicates that the bracelet is in a successful state of the identity authentication; if the authentication is wrong, finishing and clearing the registered identity information which is successfully authenticated;
the step S3 is further followed by steps, as shown in fig. 5:
s411, judging whether an identity authentication request of Bluetooth or NFC is received or not, or whether the bracelet rotates or is continuously knocked for two times or not, if so, starting timing, and if not, continuing to be in an identity authentication success state; s412, judging whether the identity information which is successfully authenticated is registered, if so, sending the identity information which is successfully authenticated to the Bluetooth or the NFC, otherwise, prompting the user to perform identity authentication, and pressing down and rotating the touch sensor by the user to perform identity authentication;
the bracelet is activated in two modes according to different use scenes, so that identity information of successful user authentication is sent to external equipment, the bracelet is activated only when a user rotates the bracelet or continuously taps two bracelets in the use scenes such as door opening, and the identity information of successful authentication is sent to the external equipment by the bracelet if the bracelet is registered with the identity information of successful authentication; in a using scene such as NFC payment, a user enables the bracelet to be close to the NFC equipment, after the bracelet receives an identity authentication request sent by the NFC equipment, if the bracelet registers identity information which is successfully authenticated, the identity information which is successfully authenticated is directly sent to the NFC equipment, and then the bracelet vibrates to prompt the user to send information;
s413, determining whether an effective reply message of bluetooth or NFC is received, if yes, completing the identity authentication, otherwise, determining whether the response message is overtime, if no, returning to step S412, otherwise, the bracelet continues to be in an identity authentication success state;
s421, judging whether the bracelet moves, specifically, arranging an acceleration sensor on the bracelet, judging whether the bracelet moves through the acceleration sensor, and if so, starting a proximity sensor arranged on the bracelet;
s422, receiving data sent by the proximity sensor, judging whether the bracelet is taken down or not according to the data, and if so, clearing the registered identity information which is successfully authenticated;
steps S411 to S413 and steps S421 to S422 are parallel flows.
EXAMPLE five
Referring to fig. 2, a vein-based authentication bracelet 1 includes a touch sensor 2, and further includes:
the vein feature collector 3 is arranged on the inner wall of the bracelet 1, and the vein feature collector 3 comprises two linear array dynamic vision sensors which are vertically arranged in a cross shape;
a proximity sensor disposed on an inner wall (not shown) of the bracelet 1;
a memory 4, a processor 5 and a computer program stored on the memory and executable on the processor, wherein the processor 5 implements the steps of any one of the first to fourth embodiments when executing the computer program.
In summary, the vein-based identity authentication method and the wristband provided by the invention adopt the dynamic visual sensor to acquire the vein features, wherein the dynamic visual sensor is a linear array dynamic visual sensor; the vein feature collector comprises two linear array dynamic visual sensors which are arranged in a cross shape and are mutually perpendicular, and the dynamic visual sensors have the working principle of imaging based on the change of a shooting area, have no problems of the traditional sensors, have low light requirement, can well work under the condition of very low or very bright light, generate asynchronous event vectors through the change of light intensity, generate a digital vein distribution feature map through simple transformation, and the collected image only contains effective information such as vein features and the like and does not contain redundant background information such as skin and the like, and after receiving the vein feature image, compared with a deep learning algorithm based on a common visual sensor, the vein feature vector can be calculated by only needing few layers, so that the calculated amount of image processing can be greatly reduced, the power consumption is reduced, the integration is suitable, and meanwhile, the identification effect is good.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all equivalent changes made by using the contents of the present specification and the drawings, or applied directly or indirectly to the related technical fields, are included in the scope of the present invention.
Claims (8)
1. A vein-based identity authentication method, comprising the steps of:
s1, receiving an identity authentication request sent by a touch sensor arranged on the bracelet, and starting timing according to the identity authentication request;
s2, receiving a vein feature image sent by a vein feature collector arranged on the inner wall of a bracelet during rotation of the bracelet, wherein the vein feature image does not contain invalid background information, and a corresponding first vein feature vector is obtained by adopting a deep learning algorithm according to the vein feature image, the vein feature collector comprises two linear array dynamic visual sensors, the two linear array dynamic visual sensors are vertically arranged in a cross shape, and the linear array dynamic visual sensors are formed by arranging a plurality of dynamic visual pixels into a straight line;
s3, searching whether a second feature vector matched with the first vein feature vector exists in a pre-stored vein feature vector set, if yes, successfully authenticating the identity, if not, wrongly authenticating the identity, judging whether the time is out, and if not, returning to the step S2;
the method between the step S1 and the step S2 further comprises the steps of:
s11, judging whether the rotation angle of the bracelet is larger than a preset angle, if so, executing the step S2, otherwise, judging whether the rotation angle is overtime, if not, returning to the step S11, otherwise, failing to authenticate the identity.
2. A vein-based identity authentication method according to claim 1,
the step S1 is preceded by the step of collecting pre-stored vein feature vectors:
s0, judging whether the bracelet is used for the first time, if so, executing a step S01, otherwise, executing a step S02;
s01, receiving a vein feature image sent by the dynamic vision sensor in the process that the bracelet moves along the arm direction, obtaining a corresponding third vein feature vector by adopting a deep learning algorithm according to the vein feature image, storing the third vein feature vector into the vein feature vector set, and finishing the step of collecting the pre-stored vein feature vectors;
s02, judging whether the daily vein feature vector collection function is started, if so, executing the step S021, otherwise, finishing the step of collecting the pre-stored vein feature vectors;
s021, judging whether the number of the vein feature vectors in the vein feature vector set is not less than a first preset value, if not, executing a step S022, otherwise, finishing the step of collecting the pre-stored vein feature vectors;
s022, judging whether the electric quantity of the bracelet is higher than a second preset value, if so, executing a step S023, otherwise, returning to the step S021;
s023, receiving a vein feature image sent by the dynamic vision sensor in the process that the bracelet moves along the arm direction, obtaining a corresponding fourth vein feature vector by adopting a deep learning algorithm according to the vein feature image, storing the fourth vein feature vector into the vein feature vector set, and returning to the step S021.
3. The vein-based identity authentication method of claim 1, wherein after the identity authentication in step S3 is successful, the method further comprises registering identity information of the successful authentication;
the step S3 is followed by the step of:
s411, judging whether an identity authentication request of Bluetooth or NFC is received or not, or whether the bracelet rotates or is continuously knocked for two times or not, and if so, starting timing;
s412, judging whether the identity information which is successfully authenticated is registered, if so, sending the identity information which is successfully authenticated to the Bluetooth or the NFC;
and S413, judging whether effective reply information of Bluetooth or NFC is received, if so, finishing identity authentication, otherwise, judging whether timeout occurs, and if not, returning to the step S412.
4. The vein-based identity authentication method according to claim 1, wherein the step S3 is followed by the further steps of:
s421, judging whether the bracelet moves, and if so, starting a proximity sensor arranged on the bracelet;
s422, receiving the data sent by the proximity sensor, judging whether the bracelet is taken down or not according to the data, and if so, clearing the registered identity information which is successfully authenticated.
5. The utility model provides an authentication bracelet based on vein, includes touch sensor, its characterized in that still includes:
the vein feature collector is arranged on the inner wall of the bracelet and comprises two linear array dynamic visual sensors which are vertically arranged in a cross shape;
a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
s1, receiving an identity authentication request sent by the touch sensor, and starting timing according to the identity authentication request;
s2, receiving a vein feature image sent by the vein feature collector in the rotation process of the bracelet, obtaining a corresponding first vein feature vector by adopting a deep learning algorithm according to the vein feature image, wherein the vein feature image does not contain invalid background information, the vein feature collector comprises two linear array dynamic vision sensors, the two linear array dynamic vision sensors are vertically arranged in a cross shape, and the linear array dynamic vision sensors are formed by arranging a plurality of dynamic vision pixel points into a straight line;
s3, searching whether a second feature vector matched with the first vein feature vector exists in a pre-stored vein feature vector set, if yes, successfully authenticating the identity, if not, wrongly authenticating the identity, judging whether the time is out, and if not, returning to the step S2;
the method between the step S1 and the step S2 further comprises the steps of:
s11, judging whether the rotation angle of the bracelet is larger than a preset angle, if so, executing the step S2, otherwise, judging whether the rotation angle is overtime, if not, returning to the step S11, otherwise, failing to authenticate the identity.
6. A vein-based authentication bracelet according to claim 5,
the step S1 is preceded by the step of collecting pre-stored vein feature vectors:
s0, judging whether the bracelet is used for the first time, if so, executing a step S01, otherwise, executing a step S02;
s01, receiving a vein feature image sent by the dynamic vision sensor in the process that the bracelet moves along the arm direction, obtaining a corresponding third vein feature vector by adopting a deep learning algorithm according to the vein feature image, storing the third vein feature vector into the vein feature vector set, and finishing the step of collecting the pre-stored vein feature vectors;
s02, judging whether the daily vein feature vector collection function is started, if so, executing the step S021, otherwise, finishing the step of collecting the pre-stored vein feature vectors;
s021, judging whether the number of the vein feature vectors in the vein feature vector set is not less than a first preset value, if not, executing a step S022, otherwise, finishing the step of collecting the pre-stored vein feature vectors;
s022, judging whether the electric quantity of the bracelet is higher than a second preset value, if so, executing a step S023, otherwise, returning to the step S021;
s023, receiving a vein feature image sent by the dynamic vision sensor in the process that the bracelet moves along the arm direction, obtaining a corresponding fourth vein feature vector by adopting a deep learning algorithm according to the vein feature image, storing the fourth vein feature vector into the vein feature vector set, and returning to the step S021.
7. The vein-based identity authentication bracelet of claim 5, further comprising registering identity information of successful authentication after successful identity authentication in step S3;
the step S3 is followed by the step of:
s411, judging whether an identity authentication request of Bluetooth or NFC is received or not, or whether the bracelet rotates or is continuously knocked for two times or not, and if so, starting timing;
s412, judging whether the identity information which is successfully authenticated is registered, if so, sending the identity information which is successfully authenticated to the Bluetooth or the NFC;
and S413, judging whether effective reply information of Bluetooth or NFC is received, if so, finishing identity authentication, otherwise, judging whether timeout occurs, and if not, returning to the step S412.
8. The vein-based authentication bracelet of claim 5, further comprising a proximity sensor disposed on an inner wall of the bracelet, and further comprising, after step S3, the steps of:
s421, judging whether the bracelet moves, and if so, starting the proximity sensor;
s422, receiving the data sent by the proximity sensor, judging whether the bracelet is taken down or not according to the data, and if so, clearing the registered identity information which is successfully authenticated.
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 CN108563937A (en) | 2018-09-21 |
| CN108563937B true 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) |
Families Citing this family (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 (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
Family Cites Families (3)
| 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 |
| US9983779B2 (en) * | 2013-02-07 | 2018-05-29 | Samsung Electronics Co., Ltd. | Method of displaying menu based on depth information and space gesture of user |
| CN107403154B (en) * | 2017-07-20 | 2020-10-16 | 四川大学 | Gait recognition method based on dynamic vision sensor |
-
2018
- 2018-04-20 CN CN201810359301.1A patent/CN108563937B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108563937A (en) | 2018-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107609383B (en) | 3D face identity authentication method and device | |
| CN107748869B (en) | 3D face identity authentication method and device | |
| CN107633165B (en) | 3D face identity authentication method and device | |
| US11074466B2 (en) | Anti-counterfeiting processing method and related products | |
| US10824849B2 (en) | Method, apparatus, and system for resource transfer | |
| US9607138B1 (en) | User authentication and verification through video analysis | |
| Das et al. | Recent advances in biometric technology for mobile devices | |
| US10769417B2 (en) | Payment method, apparatus, and system | |
| CN109461003A (en) | Plurality of human faces scene brush face payment risk preventing control method and equipment based on multi-angle of view | |
| US9930525B2 (en) | Method and system for eyeprint recognition unlocking based on environment-filtering frames | |
| WO2019011072A1 (en) | Iris live detection method and related product | |
| CN112613475B (en) | Code scanning interface display method and device, mobile terminal and storage medium | |
| CN104598870A (en) | Living fingerprint detection method based on intelligent mobile information equipment | |
| CN105426730A (en) | Login authentication processing method and device as well as terminal equipment | |
| WO2019011073A1 (en) | Human face live detection method and related product | |
| JP2011078009A (en) | Imaging device and program for imaging device | |
| CN105068646A (en) | Terminal control method and system | |
| CN111445640A (en) | Express delivery pickup method, device, equipment and storage medium based on iris recognition | |
| KR20150069799A (en) | Method for certifying face and apparatus thereof | |
| CN108563937B (en) | Vein-based identity authentication method and wristband | |
| JP2000123186A5 (en) | Object recognition apparatus and object recognition method | |
| CN109635622A (en) | Personal identification method, device and electronic equipment | |
| US10726259B2 (en) | Image processing method and system for iris recognition | |
| KR101718244B1 (en) | Apparatus and method of processing wide angle image for recognizing face | |
| CN208144609U (en) | A kind of wrist vein authentication bracelet |
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 |
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 |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |