CN109145750A - A kind of driver identity rapid authentication method and system - Google Patents

A kind of driver identity rapid authentication method and system Download PDF

Info

Publication number
CN109145750A
CN109145750A CN201810812209.6A CN201810812209A CN109145750A CN 109145750 A CN109145750 A CN 109145750A CN 201810812209 A CN201810812209 A CN 201810812209A CN 109145750 A CN109145750 A CN 109145750A
Authority
CN
China
Prior art keywords
face
characteristic point
authentication
gravity
mouth
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201810812209.6A
Other languages
Chinese (zh)
Inventor
武立辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jin Xun (beijing) Technology Co Ltd
Original Assignee
Jin Xun (beijing) Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jin Xun (beijing) Technology Co Ltd filed Critical Jin Xun (beijing) Technology Co Ltd
Priority to CN201810812209.6A priority Critical patent/CN109145750A/en
Publication of CN109145750A publication Critical patent/CN109145750A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • 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
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • 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
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • 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
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • B60W2040/0809—Driver authorisation; Driver identity check

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Automation & Control Theory (AREA)
  • Mathematical Physics (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Collating Specific Patterns (AREA)

Abstract

The invention discloses a kind of driver identity rapid authentication method and systems, comprising: the infrared gradation data and 3D depth data of 3D depth camera acquisition face；Face detection is carried out to infrared gradation data, obtains human face region；Characteristic point detection is carried out to human face region, obtains human face characteristic point；Face In vivo detection is carried out based on the 3D depth data of human face characteristic point and human face characteristic point, authentication exports result.The present invention is not necessarily to driver and completes a series of actions during carrying out face In vivo detection using 3D depth camera, living body authentication process CIMS is simple and certification rate is high；3D depth camera is affected by the external environment small, and it is high that driver identity authenticates success rate.

Description

A kind of driver identity rapid authentication method and system
Technical field
The present invention relates to identity identification technical field more particularly to a kind of driver identity rapid authentication method and systems.
Background technique
Driver information is transported safely shipping field in occupation of critically important factor, thus how efficiently, accurately, fastly Whether the identity of the verifying driver of speed is true and false to be just particularly important.
The identity technological means of detection driver mainly passes through two steps mainly by way of machine vision at present It is rapid: 1, to carry out face In vivo detection；2, pass through and database carries out information comparison, carry out authentication identification.Presently mainly By the front video of traditional 2D video camera especially mobile phone, the 2D image information got carries out face In vivo detection And identification.Current method is primarily present following problems:
1, the process for carrying out face In vivo detection by 2D camera is more complicated and relatively stringenter, and driver is needed to match It closes, against the stringent completion a series of actions of camera, living body authentication process CIMS is complicated, and certification rate is not high；
2,2D video camera is more sensitive to extraneous ambient light, especially by cockpit ambient lighting etc. it is complicated and changeable because Element influences, and as a result can frequently occur driver identity authentification failure.
Summary of the invention
Aiming at the shortcomings existing in the above problems, the present invention provides a kind of driver identity rapid authentication method and is System.
To achieve the above object, the present invention provides a kind of driver identity rapid authentication method, comprising:
Step 1,3D depth camera obtain the infrared gradation data and 3D depth data of face；
Step 2 carries out Face detection to infrared gradation data, obtains human face region；
Step 3 carries out characteristic point detection to human face region, obtains human face characteristic point；
Step 4 carries out face In vivo detection based on the 3D depth data of the human face characteristic point and human face characteristic point；
Step 5, authentication；
Step 6, output result.
As a further improvement of the present invention, the step 4 includes:
Step 41 obtains human face characteristic point information, and the human face characteristic point information includes the infrared gray scale of human face characteristic point Data and 3D depth data；
Step 42 extracts 6 characteristic point informations of left eye, 20 characteristic point informations of mouth, 2 characteristic point informations of the wing of nose and the right side 6 characteristic point informations of eye；
Step 43 calculates left eye grey scale centre of gravity, according to 20 characteristic point information meters of mouth according to 6 characteristic point informations of left eye It calculates mouth grey scale centre of gravity, calculate nose grey scale centre of gravity according to 2 characteristic point informations of the wing of nose and and according to 6 characteristic point informations of right eye Calculate right eye grey scale centre of gravity；
Step 44 is counted respectively according to left eye grey scale centre of gravity, mouth grey scale centre of gravity, nose grey scale centre of gravity and right eye grey scale centre of gravity Calculate three-dimensional distance d2, right eye and the mouth at gray scale center between the three-dimensional distance d1, left eye and mouth at gray scale center between two Between gray scale center three-dimensional distance d3 and nose and mouth between Z-direction difference d4；
Step 45 judges whether d1, d2, d3 and d4 meet respective threshold condition；
If step 46 is all satisfied, the success of face In vivo detection；Otherwise, face In vivo detection fails.
As a further improvement of the present invention, at step 43, the calculation formula of grey scale centre of gravity (x, y) are as follows:
In formula:
I ∈ (1, n), n are the feature point number of left eye, mouth, nose ash or right eye, xiFor the horizontal seat of ith feature point Mark, yiFor the ordinate of ith feature point, miFor the gray value of ith feature point.
As a further improvement of the present invention, the step 5 includes:
Step 51 carries out face alignment based on the human face region that step 2 obtains；
Step 52,128 dimensional feature of face extract；
The feature of extraction is compared step 53 with the face database of driver, and it is pre- to judge whether similarity is greater than If threshold value；
If step 54, similarity are greater than preset threshold, authentication success；Otherwise, authentication fails.
As a further improvement of the present invention, if the success of face In vivo detection, carries out authentication；If face living body is examined Dendrometry loses, then exports face In vivo detection failure result；
If authentication success, exports authentication successful result；If authentication fails, authentication mistake is exported Lose result.
The present invention also provides a kind of driver identity rapid authentication systems, comprising:
3D depth camera, for obtaining the infrared gradation data and 3D depth data of face；
Processing unit, the processing unit include Face detection module, characteristic point detection module, face In vivo detection module And authentication module, the Face detection module are used to carry out Face detection to infrared gradation data, obtain human face region；Institute Characteristic point detection module is stated for carrying out characteristic point detection to human face region, obtains human face characteristic point；The face In vivo detection Module is used to carry out face In vivo detection based on the 3D depth data of the human face characteristic point and human face characteristic point, and the identity is recognized It demonstrate,proves module and is used for authentication；
As a result output unit, for exporting result.
As a further improvement of the present invention, the face In vivo detection module includes:
Module is obtained, for obtaining human face characteristic point information, the human face characteristic point information includes the red of human face characteristic point Outer gradation data and 3D depth data；
First extraction module, for extracting 26 characteristic point informations of left eye, 20 characteristic point informations of mouth, wing of nose features Point 6 characteristic point informations of information and right eye；
First computing module, for calculating left eye grey scale centre of gravity, according to 20 spies of mouth according to 6 characteristic point informations of left eye Sign point information calculates mouth grey scale centre of gravity, calculates nose grey scale centre of gravity according to 2 characteristic point informations of the wing of nose and and according to right eye 6 Characteristic point information calculates right eye grey scale centre of gravity；
Second computing module, for according to left eye grey scale centre of gravity, mouth grey scale centre of gravity, nose grey scale centre of gravity and right eye gray scale Center of gravity calculate separately gray scale center between three-dimensional distance d1, left eye and the mouth at gray scale center between two three-dimensional distance d2, Between right eye and mouth between the three-dimensional distance d3 and nose and mouth at gray scale center Z-direction difference d4；
First judgment module, for judging whether d1, d2, d3 and d4 meet respective threshold condition, if being all satisfied, people The success of face In vivo detection；Otherwise, face In vivo detection fails.
As a further improvement of the present invention, in the grey scale centre of gravity computing module, the calculating of grey scale centre of gravity (x, y) is public Formula are as follows:
In formula:
I ∈ (1, n), n are the feature point number of left eye, mouth, nose ash or right eye, xiFor the horizontal seat of ith feature point Mark, yiFor the ordinate of ith feature point, miFor the gray value of ith feature point.
As a further improvement of the present invention, the authentication module includes:
Face alignment module, the human face region for being obtained based on Face detection module carry out face alignment；
Second extraction module, for extracting 128 dimensional feature of face；
Second judgment module judges similarity for the feature of extraction to be compared with the face database of driver Whether preset threshold is greater than；If similarity is greater than preset threshold, authentication success；Otherwise, authentication fails.
As a further improvement of the present invention, in the result output module:
If the success of face In vivo detection, carries out authentication；If face In vivo detection fails, the inspection of face living body is exported Survey failure result；
If authentication success, exports authentication successful result；If authentication fails, authentication mistake is exported Lose result.
Compared with prior art, the invention has the benefit that
1, a series of actions, living body authentication are completed without driver during 3D depth camera progress face In vivo detection Process CIMS is simple and certification rate is high；
2,3D depth camera is affected by the external environment small, and it is high that driver identity authenticates success rate.
Detailed description of the invention
Fig. 1 is the flow chart of driver identity rapid authentication method disclosed in an embodiment of the present invention；
Fig. 2 is the flow chart of face In vivo detection disclosed in an embodiment of the present invention；
Fig. 3 is the flow chart of authentication disclosed in an embodiment of the present invention；
Fig. 4 is the frame diagram of driver identity rapid authentication system disclosed in an embodiment of the present invention；
Fig. 5 is the frame diagram of processing unit disclosed in an embodiment of the present invention；
Fig. 6 is the frame diagram of face In vivo detection module disclosed in an embodiment of the present invention；
Fig. 7 is the frame diagram of authentication module disclosed in an embodiment of the present invention.
In figure:
10,3D depth camera；20, wireless communication module；30, processing unit；31, Face detection module；32, characteristic point is examined Survey module；33, face In vivo detection module；331, module is obtained；332, the first extraction module；333, the first computing module； 334, the second computing module；335, first judgment module；34, authentication module；341, face alignment module；342, it second mentions Modulus block；343, the second judgment module；40, result output unit.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is A part of the embodiments of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people Member's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
The present invention is described in further detail with reference to the accompanying drawing:
As shown in Figure 1, the present invention provides a kind of driver identity rapid authentication method, comprising:
Step 1,3D depth camera obtain the infrared gradation data and 3D depth data of face；
Step 2 carries out Face detection in infrared gradation data, obtains human face region；
Step 3 carries out characteristic point detection to human face region, obtains human face characteristic point (LandMark point)；
Step 4, the human face characteristic point based on acquisition obtain the 3D depth number of the human face characteristic point from 3D depth data According to；The 3D depth data for being then based on human face characteristic point and human face characteristic point carries out face In vivo detection；
Step 5, authentication；
Step 6, output result；Wherein, if the success of face In vivo detection, carries out authentication；If face In vivo detection Failure, then export face In vivo detection failure result；If authentication success, exports authentication successful result；If identity Authentification failure then exports authentication failure result.
As shown in Fig. 2, the present invention carries out the specific method of face In vivo detection in step 4, comprising:
Step 41 obtains human face characteristic point information, and human face characteristic point information includes the infrared gradation data of human face characteristic point With 3D depth data；
Step 42 extracts 6 characteristic point informations of left eye, 20 characteristic point informations of mouth, 2 characteristic point informations of the wing of nose and the right side 6 characteristic point informations of eye；6 characteristic points of left eye are 22, canthus characteristic point, 2 characteristic points of superior orbit and inferior orbit features Point, 6 characteristic points are uniformly distributed；20 characteristic points of mouth are 2 characteristic points of the corners of the mouth, 9 characteristic points of upper mouth socket of the eye and lower mouth socket of the eye 9 A characteristic point, 20 characteristic points are uniformly distributed；2 characteristic points of the wing of nose be nose the wing of nose at 2 characteristic points, 6 of right eye Characteristic point is 22, canthus characteristic point, 2 characteristic points of superior orbit and inferior orbit characteristic points, and 6 characteristic points are uniformly distributed；
Step 43 calculates left eye grey scale centre of gravity, according to 20 characteristic point information meters of mouth according to 6 characteristic point informations of left eye It calculates mouth grey scale centre of gravity, calculate nose grey scale centre of gravity according to 2 characteristic point informations of the wing of nose and and according to 6 characteristic point informations of right eye Calculate right eye grey scale centre of gravity；It is specific:
The calculation formula of grey scale centre of gravity (x, y) are as follows:
In formula:
I ∈ (1, n), n are the feature point number of left eye, mouth, nose ash or right eye, xiFor the horizontal seat of ith feature point Mark, yiFor the ordinate of ith feature point, miFor the gray value of ith feature point；N takes 6 when calculating left eye grey scale centre of gravity, calculates N takes 20 when mouth grey scale centre of gravity, and n takes 2 when calculating nose grey scale centre of gravity, and n takes 6 when calculating right eye grey scale centre of gravity.
Step 44 is counted respectively according to left eye grey scale centre of gravity, mouth grey scale centre of gravity, nose grey scale centre of gravity and right eye grey scale centre of gravity Calculate three-dimensional distance d2, right eye and the mouth at gray scale center between the three-dimensional distance d1, left eye and mouth at gray scale center between two Between gray scale center three-dimensional distance d3 and nose and mouth between Z-direction difference d4；
Step 45 judges whether d1, d2, d3 and d4 meet respective threshold condition；
If step 46 is all satisfied, the success of face In vivo detection；Otherwise, face In vivo detection fails.
As shown in figure 3, the present invention carries out the specific method of authentication in steps of 5, comprising:
Step 51 carries out face alignment based on the human face region that step 2 obtains；
Step 52,128 dimensional feature of face extract；
The feature of extraction is compared step 53 with the face database of driver, and it is pre- to judge whether similarity is greater than If threshold value；
If step 54, similarity are greater than preset threshold, authentication success；Otherwise, authentication fails.
As illustrated in figures 4-5, the present invention provides a kind of driver identity rapid authentication system, comprising: 3D depth camera 10, nothing Line communication module 20, processing unit 30 and result output unit 40；Wherein:
ToF camera or structure light camera can be selected in 3D depth camera 10, for obtaining the infrared gradation data and 3D of face Depth data；
Module 20 is connected processing unit 30 with 3D depth camera 10 by wireless communication, obtains for receiving 3D depth camera 10 The infrared gradation data of the face taken and 3D depth data.WiFi or indigo plant can be selected in the communication of wireless communication module 20 Mobile phone, vehicle-mounted computer or vehicle-mounted middle control platform can be selected in tooth, processing unit 30.
As shown in figure 5, processing unit 30 of the invention includes Face detection module 31, characteristic point detection module 32, face In vivo detection module 33 and authentication module 34；Wherein, Face detection module 31 is used to carry out face to infrared gradation data Positioning obtains human face region；Characteristic point detection module 32 is used to carry out characteristic point detection to human face region, obtains face characteristic Point；Face In vivo detection module 33 is used to carry out the inspection of face living body based on the 3D depth data of human face characteristic point and human face characteristic point It surveys, authentication module 34 is used for authentication.
As shown in fig. 6, face In vivo detection module 33 of the invention includes:
Module 331 is obtained, for obtaining human face characteristic point information, human face characteristic point information includes the infrared of human face characteristic point Gradation data and 3D depth data；
First extraction module 332, for extracting 6 characteristic point informations of left eye, 20 characteristic point informations of mouth, the wing of nose 2 6 characteristic point informations of characteristic point information and right eye；6 characteristic points of left eye are 22, canthus characteristic point, superior orbit characteristic points With 2 characteristic points of inferior orbit, 6 characteristic points are uniformly distributed；20 characteristic points of mouth are 2 characteristic points of the corners of the mouth, upper mouth socket of the eye 9 Characteristic point and lower 9 characteristic points of mouth socket of the eye, 20 characteristic points are uniformly distributed；2 characteristic points of the wing of nose are 2 spies at the wing of nose of nose Point is levied, 6 characteristic points of right eye are 22, canthus characteristic point, 2 characteristic points of superior orbit and inferior orbit characteristic points, 6 features Point is uniformly distributed；
First computing module 333, for calculating left eye grey scale centre of gravity, according to mouth 20 according to 6 characteristic point informations of left eye A characteristic point information calculates mouth grey scale centre of gravity, calculates nose grey scale centre of gravity according to 2 characteristic point informations of the wing of nose and and according to the right side 6 characteristic point informations of eye calculate right eye grey scale centre of gravity；It is specific:
The calculation formula of grey scale centre of gravity (x, y) are as follows:
In formula:
I ∈ (1, n), n are the feature point number of left eye, mouth, nose ash or right eye, xiFor the horizontal seat of ith feature point Mark, yiFor the ordinate of ith feature point, miFor the gray value of ith feature point；N takes 6 when calculating left eye grey scale centre of gravity, calculates N takes 20 when mouth grey scale centre of gravity, and n takes 2 when calculating nose grey scale centre of gravity, and n takes 6 when calculating right eye grey scale centre of gravity；
Second computing module 334, for according to left eye grey scale centre of gravity, mouth grey scale centre of gravity, nose grey scale centre of gravity and right eye Grey scale centre of gravity calculates separately the three-dimensional distance at gray scale center between three-dimensional distance d1, left eye and the mouth at gray scale center between two Between d2, right eye and mouth between the three-dimensional distance d3 and nose and mouth at gray scale center Z-direction difference d4；
First judgment module 334, for judging whether d1, d2, d3 and d4 meet respective threshold condition, if being all satisfied, Then face In vivo detection success；Otherwise, face In vivo detection fails.
As shown in fig. 7, authentication module 34 of the invention includes:
Face alignment module 341, the human face region for being obtained based on Face detection module carry out face alignment；
Second extraction module 342, for extracting 128 dimensional feature of face；
Second judgment module 343 judges similar for the feature of extraction to be compared with the face database of driver Whether degree is greater than preset threshold；If similarity is greater than preset threshold, authentication success；Otherwise, authentication fails.
As a result output unit 40 is connected with processing unit 30, for exporting result；If the success of face In vivo detection, carries out Authentication；If face In vivo detection fails, face In vivo detection failure result is exported；If authentication success, exports Authentication successful result；If authentication fails, authentication failure result is exported.Wherein, language can be used in the way of output Sound or APP are shown.
The present invention is not necessarily to driver during carrying out face In vivo detection using 3D depth camera and completes a series of actions, Living body authentication process CIMS is simple and certification rate is high；3D depth camera is affected by the external environment small, and driver identity authenticates successfully Rate is high.
These are only the preferred embodiment of the present invention, is not intended to restrict the invention, for those skilled in the art For member, the invention may be variously modified and varied.All within the spirits and principles of the present invention, it is made it is any modification, Equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.

Claims (10)

1. a kind of driver identity rapid authentication method characterized by comprising
Step 1,3D depth camera obtain the infrared gradation data and 3D depth data of face；
Step 2 carries out Face detection to infrared gradation data, obtains human face region；
Step 3 carries out characteristic point detection to human face region, obtains human face characteristic point；
Step 4 carries out face In vivo detection based on the 3D depth data of the human face characteristic point and human face characteristic point；
Step 5, authentication；
Step 6, output result.
2. driver identity rapid authentication method as described in claim 1, which is characterized in that the step 4 includes:
Step 41 obtains human face characteristic point information, and the human face characteristic point information includes the infrared gradation data of human face characteristic point With 3D depth data；
Step 42 extracts 6 characteristic point informations of left eye, 20 characteristic point informations of mouth, 2 characteristic point informations of the wing of nose and right eye 6 A characteristic point information；
Step 43 calculates left eye grey scale centre of gravity according to 6 characteristic point informations of left eye, calculates mouth according to 20 characteristic point informations of mouth Bar grey scale centre of gravity calculates nose grey scale centre of gravity according to 2 characteristic point informations of the wing of nose and and is calculated according to 6 characteristic point informations of right eye Right eye grey scale centre of gravity；
Step 44 calculates separately two according to left eye grey scale centre of gravity, mouth grey scale centre of gravity, nose grey scale centre of gravity and right eye grey scale centre of gravity Between eye between the three-dimensional distance d1, left eye and mouth at gray scale center between the three-dimensional distance d2, right eye and mouth at gray scale center The difference d4 of Z-direction between the three-dimensional distance d3 and nose and mouth at gray scale center；
Step 45 judges whether d1, d2, d3 and d4 meet respective threshold condition；
If step 46 is all satisfied, the success of face In vivo detection；Otherwise, face In vivo detection fails.
3. driver identity rapid authentication method as claimed in claim 2, which is characterized in that at step 43, grey scale centre of gravity The calculation formula of (x, y) are as follows:
In formula:
I ∈ (1, n), n are the feature point number of left eye, mouth, nose ash or right eye, xiFor the abscissa of ith feature point, yi For the ordinate of ith feature point, miFor the gray value of ith feature point.
4. driver identity rapid authentication method as described in claim 1, which is characterized in that the step 5 includes:
Step 51 carries out face alignment based on the human face region that step 2 obtains；
Step 52,128 dimensional feature of face extract；
The feature of extraction is compared step 53 with the face database of driver, judges whether similarity is greater than default threshold Value；
If step 54, similarity are greater than preset threshold, authentication success；Otherwise, authentication fails.
5. driver identity rapid authentication method as described in claim 1, which is characterized in that if the success of face In vivo detection, Then carry out authentication；If face In vivo detection fails, face In vivo detection failure result is exported；
If authentication success, exports authentication successful result；If authentication fails, exports authentication and unsuccessfully tie Fruit.
6. a kind of driver identity rapid authentication system characterized by comprising
3D depth camera, for obtaining the infrared gradation data and 3D depth data of face；
Processing unit, the processing unit include Face detection module, characteristic point detection module, face In vivo detection module and body Part authentication module, the Face detection module are used to carry out Face detection to infrared gradation data, obtain human face region；The spy Sign point detection module is used to carry out characteristic point detection to human face region, obtains human face characteristic point；The face In vivo detection module Face In vivo detection, the authentication mould are carried out for the 3D depth data based on the human face characteristic point and human face characteristic point Block is used for authentication；
As a result output unit, for exporting result.
7. driver identity rapid authentication system as claimed in claim 6, which is characterized in that the face In vivo detection module Include:
Module is obtained, for obtaining human face characteristic point information, the human face characteristic point information includes the infrared ash of human face characteristic point Degree evidence and 3D depth data；
First extraction module, for extracting 26 characteristic point informations of left eye, 20 characteristic point informations of mouth, wing of nose characteristic point letters Breath and 6 characteristic point informations of right eye；
First computing module, for calculating left eye grey scale centre of gravity, according to 20 characteristic points of mouth according to 6 characteristic point informations of left eye Information calculates mouth grey scale centre of gravity, calculates nose grey scale centre of gravity according to 2 characteristic point informations of the wing of nose and and according to 6 features of right eye Point information calculates right eye grey scale centre of gravity；
Second computing module, for according to left eye grey scale centre of gravity, mouth grey scale centre of gravity, nose grey scale centre of gravity and right eye grey scale centre of gravity Calculate separately three-dimensional distance d2, the right eye at gray scale center between three-dimensional distance d1, left eye and the mouth at gray scale center between two Between mouth between the three-dimensional distance d3 and nose and mouth at gray scale center Z-direction difference d4；
First judgment module, for judging whether d1, d2, d3 and d4 meet respective threshold condition, if being all satisfied, face is living Physical examination is surveyed successfully；Otherwise, face In vivo detection fails.
8. driver identity rapid authentication system as claimed in claim 7, which is characterized in that calculate mould in the grey scale centre of gravity In block, the calculation formula of grey scale centre of gravity (x, y) are as follows:
In formula:
I ∈ (1, n), n are the feature point number of left eye, mouth, nose ash or right eye, xiFor the abscissa of ith feature point, yi For the ordinate of ith feature point, miFor the gray value of ith feature point.
9. driver identity rapid authentication system as claimed in claim 6, which is characterized in that the authentication module packet It includes:
Face alignment module, the human face region for being obtained based on Face detection module carry out face alignment；
Second extraction module, for extracting 128 dimensional feature of face；
Whether second judgment module judges similarity for the feature of extraction to be compared with the face database of driver Greater than preset threshold；If similarity is greater than preset threshold, authentication success；Otherwise, authentication fails.
10. driver identity rapid authentication system as claimed in claim 6, which is characterized in that in the result output module In:
If the success of face In vivo detection, carries out authentication；If face In vivo detection fails, the mistake of face In vivo detection is exported Lose result；
If authentication success, exports authentication successful result；If authentication fails, exports authentication and unsuccessfully tie Fruit.
CN201810812209.6A 2018-07-23 2018-07-23 A kind of driver identity rapid authentication method and system Pending CN109145750A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810812209.6A CN109145750A (en) 2018-07-23 2018-07-23 A kind of driver identity rapid authentication method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810812209.6A CN109145750A (en) 2018-07-23 2018-07-23 A kind of driver identity rapid authentication method and system

Publications (1)

Publication Number Publication Date
CN109145750A true CN109145750A (en) 2019-01-04

Family

ID=64801463

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810812209.6A Pending CN109145750A (en) 2018-07-23 2018-07-23 A kind of driver identity rapid authentication method and system

Country Status (1)

Country Link
CN (1) CN109145750A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109977929A (en) * 2019-04-28 2019-07-05 北京超维度计算科技有限公司 A kind of face identification system and method based on TOF
CN109977771A (en) * 2019-02-22 2019-07-05 杭州飞步科技有限公司 Verification method, device, equipment and the computer readable storage medium of driver identification
CN110070062A (en) * 2019-04-28 2019-07-30 北京超维度计算科技有限公司 A kind of system and method for the recognition of face based on binocular active infrared
WO2020215283A1 (en) * 2019-04-25 2020-10-29 深圳市汇顶科技股份有限公司 Facial recognition method, processing chip and electronic device
CN112364759A (en) * 2020-11-10 2021-02-12 易显智能科技有限责任公司 Method and related device for driver identity biological recognition
CN113128320A (en) * 2020-01-16 2021-07-16 浙江舜宇智能光学技术有限公司 Face living body detection method and device based on TOF camera and electronic equipment
US20220161888A1 (en) * 2020-11-26 2022-05-26 Hyundai Motor Company Personal Mobility and Control Method Thereof

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2645302A2 (en) * 2012-03-27 2013-10-02 Fujitsu Limited Noncontact biometric identification device
CN105740781A (en) * 2016-01-25 2016-07-06 北京天诚盛业科技有限公司 Three-dimensional human face in-vivo detection method and device
CN105740778A (en) * 2016-01-25 2016-07-06 北京天诚盛业科技有限公司 Improved three-dimensional human face in-vivo detection method and device thereof
CN105956518A (en) * 2016-04-21 2016-09-21 腾讯科技（深圳）有限公司 Face identification method, device and system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2645302A2 (en) * 2012-03-27 2013-10-02 Fujitsu Limited Noncontact biometric identification device
CN105740781A (en) * 2016-01-25 2016-07-06 北京天诚盛业科技有限公司 Three-dimensional human face in-vivo detection method and device
CN105740778A (en) * 2016-01-25 2016-07-06 北京天诚盛业科技有限公司 Improved three-dimensional human face in-vivo detection method and device thereof
CN105956518A (en) * 2016-04-21 2016-09-21 腾讯科技（深圳）有限公司 Face identification method, device and system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
马少鹏 等: "《力学专业程序实践 用MATLAB解决力学问题的方法与实例》", 30 April 2013 *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109977771A (en) * 2019-02-22 2019-07-05 杭州飞步科技有限公司 Verification method, device, equipment and the computer readable storage medium of driver identification
WO2020215283A1 (en) * 2019-04-25 2020-10-29 深圳市汇顶科技股份有限公司 Facial recognition method, processing chip and electronic device
CN109977929A (en) * 2019-04-28 2019-07-05 北京超维度计算科技有限公司 A kind of face identification system and method based on TOF
CN110070062A (en) * 2019-04-28 2019-07-30 北京超维度计算科技有限公司 A kind of system and method for the recognition of face based on binocular active infrared
CN113128320A (en) * 2020-01-16 2021-07-16 浙江舜宇智能光学技术有限公司 Face living body detection method and device based on TOF camera and electronic equipment
CN113128320B (en) * 2020-01-16 2023-05-16 浙江舜宇智能光学技术有限公司 Human face living body detection method and device based on TOF camera and electronic equipment
CN112364759A (en) * 2020-11-10 2021-02-12 易显智能科技有限责任公司 Method and related device for driver identity biological recognition
CN112364759B (en) * 2020-11-10 2022-07-01 易显智能科技有限责任公司 Method and related device for driver identity biological recognition
US20220161888A1 (en) * 2020-11-26 2022-05-26 Hyundai Motor Company Personal Mobility and Control Method Thereof
US11554830B2 (en) * 2020-11-26 2023-01-17 Hyundai Motor Company Personal mobility and control method thereof

Similar Documents

Publication Publication Date Title
CN109145750A (en) A kind of driver identity rapid authentication method and system
CN105574518B (en) Method and device for detecting living human face
CN108764071A (en) It is a kind of based on infrared and visible images real human face detection method and device
CN103914686B (en) A kind of face alignment authentication method and system shone based on certificate photo with collection
CN103324879B (en) Mobile device is based on recognition of face and the authentication system of smart card and method
CN105740778B (en) Improved three-dimensional human face in-vivo detection method and device
RU2431190C2 (en) Facial prominence recognition method and device
KR20210046653A (en) Identification and verification of entities using facial recognition
CN107633165A (en) 3D face identity authentications and device
CN108537131B (en) Face recognition living body detection method based on face characteristic points and optical flow field
EP3905104B1 (en) Living body detection method and device
CN108734235A (en) A kind of personal identification method and system for electronic prescription
CN105868690A (en) Method and apparatus for identifying mobile phone use behavior of driver
CN106503645A (en) Monocular distance-finding method and system based on Android
AU2019272041A1 (en) Device with biometric system
CN113920491A (en) Fatigue detection system, method, medium and detection device based on facial skeleton model
CN108647621A (en) A kind of video analysis processing system and method based on recognition of face
CN106570899A (en) Target object detection method and device
CN114894337B (en) Temperature measurement method and device for outdoor face recognition
CN107844742A (en) Facial image glasses minimizing technology, device and storage medium
CN110544333A (en) Access control system and control method thereof
CN106937532A (en) System and method for detecting actual user
CN109785446A (en) Image identification system and its method
CN105678290A (en) Face payment platform based on image detection
CN107609515A (en) A kind of face alignment system and method for the double verification based on platform of soaring

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20190104