CN109858425A - A kind of offline In vivo detection system - Google Patents
A kind of offline In vivo detection system Download PDFInfo
- Publication number
- CN109858425A CN109858425A CN201910076351.3A CN201910076351A CN109858425A CN 109858425 A CN109858425 A CN 109858425A CN 201910076351 A CN201910076351 A CN 201910076351A CN 109858425 A CN109858425 A CN 109858425A
- Authority
- CN
- China
- Prior art keywords
- module
- face
- information
- detection
- acquisition module
- 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.)
- Withdrawn
Links
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The invention discloses a kind of offline In vivo detection systems, including action command module, dynamic acquisition module, face detection module, finger print detecting module, iris detection module, static acquisition module, information extraction modules, central control unit, characteristics analysis module, validation database, comparison module and result display module.The beneficial effects of the present invention are: information extraction modules are divided into multiple nonoverlapping zonules to the collected face information of dynamic acquisition module and static acquisition module institute, and it is targetedly extracted, real human face and attack face can be distinguished, improve the accuracy of In vivo detection, the face characteristic information for indicating face characteristic is calculated in the face information extracted by central control unit with three-dimensional coordinate information, interference information can effectively be removed, face characteristic information can preferably characterize face characteristic, erroneous detection is avoided, detection accuracy is improved.
Description
Technical field
The present invention relates to a kind of In vivo detection, specially a kind of offline In vivo detection system belongs to biological identification technology neck
Domain.
Background technique
With the further leap of artificial intelligence technology, artificial intelligence product more and more applies to real daily life, such as
Recognition of face and human face identification technology widely apply to the fields such as security protection, finance, In vivo detection be one of its key technology and
Important component, In vivo detection are for determining that target is that the technology of lived individual can be identified by In vivo detection
Target is living body, and the abiotic object such as non-photograph, is to guarantee the safe and reliable important means of face authentication result.Living body inspection
Survey purpose is i.e. correct to be distinguished real human face and attacks face, wherein attack face includes human face photo attack, the playback of face screen
The various attacks means such as attack, the attack of 3D face mask.
Existing offline In vivo detection system, one, detection approach are more single, therefore cause the practicality poor, no
Convenient for promoting, secondly, for the collected face information of institute, can not targetedly be extracted, and then will lead to and detecting
When will receive interference, influence detection precision, thirdly, using three-dimensional depth information carry out face In vivo detection when, calculation amount
It is larger, it is therefore desirable to which that the height of user cooperates, and user experience is poor, and identification process is long, so that face recognition technology is optional
Property feature it is no longer prominent.
Summary of the invention
The object of the invention is that providing a kind of offline In vivo detection system to solve the above-mentioned problems.
The present invention is through the following technical solutions to achieve the above objectives: a kind of offline In vivo detection system, including movement refer to
Enable module, dynamic acquisition module, face detection module, finger print detecting module, iris detection module, static acquisition module, information
Extraction module, central control unit, characteristics analysis module, validation database, comparison module and result display module；The movement
The output end of instruction module and the input terminal of dynamic acquisition module are attached, the face detection module, finger print detecting module
With iris detection module in being arranged in parallel, and the face detection module, finger print detecting module and iris detection module with it is quiet
The input terminal of state acquisition module is attached, and the dynamic acquisition module and static acquisition module are and described dynamic in being arranged in parallel
The output end of state acquisition module and static acquisition module is separately connected to be attached with information extraction modules, the information extraction mould
The output end of block is attached with central control unit, and output end and the central control unit of the characteristics analysis module are connected
It connects, the validation database is in be arranged in parallel, and the validation database and the input terminal of comparison module are in comparison module
The output end of centre control unit electrically connects, and the result display module is connected to the output end of central control unit.
Preferably, in order to make the system have a variety of detection approach, the action command module to face turn left, turn right,
The instruction actions such as open one's mouth, blink are detected, and face detection module carries out the information such as the movement, breathing, red-eye effect on head
Detection, finger print detecting module to the temperature of finger, perspire, the information such as electric conductivity detect, iris detection module is to iris
Chatter characteristic, the motion information of eyelashes and eyelid, pupil carry out the information such as the shrinkage expansion response characteristic of visible light source intensity
Detection.
Preferably, in order to targetedly be extracted, the information extraction modules are to dynamic acquisition module and static state
The collected face information of acquisition module institute is divided into multiple nonoverlapping zonules.
Preferably, in order to improve detection accuracy, the central control unit sits the face information extracted with three-dimensional
The face characteristic information for indicating face characteristic is calculated in mark information.
Preferably, in order to improve the practicability of In vivo detection, the comparison module is to new accredited personnel and registered people
The face sample of member is compared, and by new accredited personnel's Sample preservation to validation database.
Preferably, when carrying out face In vivo detection to solve three-dimensional depth information, computationally intensive problem, the feature
Analysis module is according to the picture frame number of acquisition and the calculation times of feature average difference values compared with preset value and mean difference
Different value determines compared with threshold value.
The beneficial effects of the present invention are: offline In vivo detection system design is rationally, action command module turns left to face,
The instruction actions such as turn right, open one's mouth, blinking are detected, and face detection module is to information such as the movements, breathing, red-eye effect on head
Detected, finger print detecting module to the temperature of finger, perspire, the information such as electric conductivity detect, iris detection module pair
Iris chatter characteristic, the motion information of eyelashes and eyelid, pupil are to information such as the shrinkage expansion response characteristics of visible light source intensity
It is detected, makes the system that there are a variety of detection approach, improve the detection efficiency of the system, information extraction modules are to dynamic acquisition
The collected face information of module and static acquisition module institute is divided into multiple nonoverlapping zonules, and is targetedly mentioned
It takes, real human face and attack face can be distinguished, improve the accuracy of In vivo detection, the face that central control unit will extract
The face characteristic information for indicating face characteristic is calculated with three-dimensional coordinate information for information, can effectively remove interference information,
Face characteristic information can preferably characterize face characteristic, avoid erroneous detection, improve detection accuracy, comparison module is to new registration
The face sample of personnel and registered personnel are compared, and by new accredited personnel's Sample preservation to validation database, improve
The practicability of In vivo detection, to help In vivo detection in the popularization of face identification system, characteristics analysis module is according to acquisition
The calculation times of picture frame number and feature average difference values are compared with preset value and average difference values come compared with threshold value
Determine, when solving using three-dimensional depth information progress face In vivo detection, computationally intensive problem.
Detailed description of the invention
Fig. 1 is schematic structural view of the invention.
In figure: 1, action command module, 2, dynamic acquisition module, 3, face detection module, 4, finger print detecting module, 5, rainbow
Film detection module, 6, static acquisition module, 7, information extraction modules, 8, central control unit, 9, characteristics analysis module, 10, test
Demonstrate,prove database, 11, comparison module and 12, result display module.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, a kind of offline In vivo detection system, including the inspection of action command module 1, dynamic acquisition module 2, face
Survey module 3, finger print detecting module 4, iris detection module 5, static acquisition module 6, information extraction modules 7, central control unit
8, characteristics analysis module 9, validation database 10, comparison module 11 and result display module 12；The action command module 1 it is defeated
The input terminal of outlet and dynamic acquisition module 2 is attached, the face detection module 3, finger print detecting module 4 and iris detection
Module 5 is in be arranged in parallel, and the face detection module 3, finger print detecting module 4 and iris detection module 5 are acquired with static state
The input terminal of module 6 is attached, and the dynamic acquisition module 2 is in be arranged in parallel, and the dynamic is adopted with static acquisition module 6
The output end of collection module 2 and static acquisition module 6 is separately connected to be attached with information extraction modules 7, the information extraction mould
The output end of block 7 is attached with central control unit 8, the output end of the characteristics analysis module 9 and central control unit 8 into
Row connection, the validation database 10 and comparison module 11 are in being arranged in parallel, and the validation database 10 and comparison module 11
Input terminal electrically connect with the output end of central control unit 8, it is single that the result display module 12 is connected to center control
The output end of member 8.
The action command module 1 instruction actions such as turn left to face, turn right, opening one's mouth, blinking detect, Face datection
Module 3 detects the information such as the movement, breathing, red-eye effect on head, finger print detecting module 4 to the temperature of finger, perspire,
The information such as electric conductivity are detected, motion information, pupil of the iris detection module 5 to iris chatter characteristic, eyelashes and eyelid
The information such as the shrinkage expansion response characteristic to visible light source intensity detect, and the system is made to have a variety of detection approach, improve
The detection efficiency of the system, the information extraction modules 7 are to the 6 collected people of institute of dynamic acquisition module 2 and static acquisition module
Face information is divided into multiple nonoverlapping zonules, and is targetedly extracted, and real human face and attack face can be distinguished,
The accuracy of In vivo detection is improved, the central control unit 8 calculates the face information extracted with three-dimensional coordinate information
To the face characteristic information for indicating face characteristic, interference information can be effectively removed, face characteristic information being capable of better table
Face characteristic is levied, avoids erroneous detection, improves detection accuracy, the comparison module 11 is to new accredited personnel and registered personnel
Face sample is compared, and by new accredited personnel's Sample preservation to validation database 10, improves the practicability of In vivo detection,
To help In vivo detection in the popularization of face identification system, the characteristics analysis module 9 is according to the picture frame number of acquisition and spy
Levy average difference values calculation times are compared with preset value and average difference values determine compared with threshold value, solve
When carrying out face In vivo detection using three-dimensional depth information, computationally intensive problem.
Working principle: when using the offline In vivo detection system, action command module 1 is turned left to face, turns right, is opened
The instruction actions such as mouth, blink are detected, and face detection module 3 examines the information such as the movement, breathing, red-eye effect on head
Survey, finger print detecting module 4 to the temperature of finger, perspire, the information such as electric conductivity detect, iris detection module 5 is to iris
Chatter characteristic, the motion information of eyelashes and eyelid, pupil carry out the information such as the shrinkage expansion response characteristic of visible light source intensity
Detection, the face information detected is divided into multiple nonoverlapping zonules by information extraction modules 7, and is targetedly mentioned
It takes, and using characteristics analysis module 9 according to the picture frame number of acquisition and the calculation times of feature average difference values and preset value
Compare and average difference values determine compared with threshold value, real human face and attack face can be distinguished, improve In vivo detection
Accuracy, finally will test result and shown via result display module 12.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included within the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (6)
1. a kind of offline In vivo detection system, it is characterised in that: including action command module (1), dynamic acquisition module (2), people
Face detection module (3), finger print detecting module (4), iris detection module (5), static acquisition module (6), information extraction modules
(7), central control unit (8), characteristics analysis module (9), validation database (10), comparison module (11) and result display module
(12)；The output end of the action command module (1) and the input terminal of dynamic acquisition module (2) are attached, the face inspection
Survey module (3), finger print detecting module (4) and iris detection module (5) are in be arranged in parallel, and the face detection module (3), refer to
The input terminal of line detection module (4) and iris detection module (5) with static acquisition module (6) is attached, and the dynamic is adopted
Collection module (2) and static acquisition module (6) are in being arranged in parallel, and the dynamic acquisition module (2) and static state acquisition module (6)
Output end is separately connected to be attached with information extraction modules (7), and the output end of the information extraction modules (7) and center control
Unit (8) is attached, and output end and the central control unit (8) of the characteristics analysis module (9) are attached, the verifying
Database (10) and comparison module (11) are in being arranged in parallel, and the input terminal of the validation database (10) and comparison module (11)
It is electrically connect with the output end of central control unit (8), the result display module (12) is connected to central control unit (8)
Output end.
2. a kind of offline In vivo detection system according to claim 1, it is characterised in that: the action command module (1)
The instruction actions such as turn left to face, turn right, opening one's mouth, blinking detect, face detection module (3) to the movement on head, breathing,
The information such as red-eye effect are detected, finger print detecting module (4) to the temperature of finger, perspire, the information such as electric conductivity are examined
It surveys, iris detection module (5) is to the motion information of iris chatter characteristic, eyelashes and eyelid, pupil to the receipts of visible light source intensity
The information such as reducing and expansion response characteristic are detected.
3. a kind of offline In vivo detection system according to claim 1, it is characterised in that: the information extraction modules (7)
Multiple nonoverlapping zonules are divided into the collected face information of dynamic acquisition module (2) and static acquisition module (6) institute.
4. a kind of offline In vivo detection system according to claim 1, it is characterised in that: the central control unit (8)
The face information extracted is calculated to the face characteristic information for indicating face characteristic with three-dimensional coordinate information.
5. a kind of offline In vivo detection system according to claim 1, it is characterised in that: the comparison module (11) is to new
Accredited personnel and the face sample of registered personnel be compared, and by new accredited personnel's Sample preservation to validation database
(10).
6. a kind of offline In vivo detection system according to claim 1, it is characterised in that: the characteristics analysis module (9)
According to the calculation times of the picture frame number of acquisition and feature average difference values compared with preset value and average difference values and threshold
The comparison of value determines.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910076351.3A CN109858425A (en) | 2019-01-26 | 2019-01-26 | A kind of offline In vivo detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910076351.3A CN109858425A (en) | 2019-01-26 | 2019-01-26 | A kind of offline In vivo detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109858425A true CN109858425A (en) | 2019-06-07 |
Family
ID=66896261
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910076351.3A Withdrawn CN109858425A (en) | 2019-01-26 | 2019-01-26 | A kind of offline In vivo detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109858425A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114869242A (en) * | 2022-07-12 | 2022-08-09 | 吉林大学 | Experimental animals cardiopulmonary exercise function detection device |
-
2019
- 2019-01-26 CN CN201910076351.3A patent/CN109858425A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114869242A (en) * | 2022-07-12 | 2022-08-09 | 吉林大学 | Experimental animals cardiopulmonary exercise function detection device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105447466B (en) | A kind of identity integrated recognition method based on Kinect sensor | |
| CN105138954B (en) | A kind of image automatic screening inquiry identifying system | |
| CN103440479B (en) | A kind of method and system for detecting living body human face | |
| CN109635697A (en) | Electric operating personnel safety dressing detection method based on YOLOv3 target detection | |
| CN109543526A (en) | True and false facial paralysis identifying system based on depth difference opposite sex feature | |
| CN110268444A (en) | A kind of number of people posture tracing system for transcranial magnetic stimulation diagnosis and treatment | |
| CN109886080A (en) | Human face in-vivo detection method, device, electronic equipment and readable storage medium storing program for executing | |
| CN104952221B (en) | Myopia-proof intelligent desk lamp | |
| CN107194361A (en) | Two-dimentional pose detection method and device | |
| Huang et al. | Hand vein recognition based on oriented gradient maps and local feature matching | |
| CN203644047U (en) | Open finger vein authentication device | |
| CN104615993B (en) | The certification device and method that a kind of finger vena identification combines with face hand vein recognition | |
| Wang et al. | Automatic recognition of facial movement for paralyzed face | |
| CN107480716A (en) | A kind of combination EOG and video pan signal recognition method and system | |
| Hossain et al. | Facial emotion verification by infrared image | |
| CN109858425A (en) | A kind of offline In vivo detection system | |
| CN109977756A (en) | A kind of online In vivo detection system | |
| CN115953822A (en) | Face video false distinguishing method and device based on rPPG physiological signal | |
| Feng | Biometric identification technology and development trend of physiological characteristics | |
| Zhang et al. | Pupil detection based on oblique projection using a binocular camera | |
| Hsu et al. | Extraction of visual facial features for health management | |
| Wang et al. | Real-time stereo face recognition by fusing appearance and depth fisherfaces | |
| CN204423392U (en) | Based on the authenticate device that finger vena identification combines with facial hand vein recognition | |
| CN204314933U (en) | A kind of entry and exit identity management system based on three-dimensional face identification | |
| Mehmood et al. | A survey on various unimodal biometric techniques |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190607 |