CN107657289A - Multimodal Biometrics device and its recognition methods - Google Patents
Multimodal Biometrics device and its recognition methods Download PDFInfo
- Publication number
- CN107657289A CN107657289A CN201710933786.6A CN201710933786A CN107657289A CN 107657289 A CN107657289 A CN 107657289A CN 201710933786 A CN201710933786 A CN 201710933786A CN 107657289 A CN107657289 A CN 107657289A
- Authority
- CN
- China
- Prior art keywords
- module
- information
- central processing
- user
- processing unit
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention belongs to biometrics identification technology field, more particularly to multimodal Biometrics device and its recognition methods, display module, finger print acquisition module, facial image acquisition module, iris image acquiring module, voice acquisition module, Password Input module, communication module are connected with central processing unit respectively；Central processing unit is used for the information for handling collection, and is contrasted with the information of database purchase, and comparing result is shown by display, and the control device of correlation is sent to by communication module.Reasonable combination or fusion of the present invention by a variety of biological characteristics, recognition performance more more preferable than single creature Feature Recognition System and reliability can be obtained, and increase the difficulty and complexity for forging human body biological characteristics, the security of system is improved, can be applied to many application scenarios such as the higher institutional settings of the daily management of enterprise, security protection level requirements, financial industry.
Description
Technical field
The invention belongs to biometrics identification technology field, and in particular to multimodal Biometrics device and its identification side
Method.
Background technology
With the fast development of current information-intensive society computer technology and new theory, modern biometrics identification technology obtains
Quick development and application have been arrived, on the other hand, personal identification is also constantly being increased with the demand managed.Biological characteristic
Identification is exactly to carry out the technology of automatic identity discriminating, including hand vein recognition, people with behavioural characteristic using the unique physiology of human body
Face identification, speech recognition, iris recognition, wage checking system, gate control system, safety supervision system, government affairs have been widely used in it
In system, and the various aspects of the social life such as digital terminal access, authentication of network resource accession, to improve constantly
The quality of human lives is made that contribution.
But, the research to biometrics identification technology at present, it is generally concentrated in the research to single mode identifying system,
Although the characteristics of with quick identification, also there is the problem of much can not only overcoming by single mode identification.Because using
When monotechnics and module, it is difficult to accomplish effectively to identify, its accuracy is not also high, such as somatic fingerprint can relatively easily by
Replicate and forge, so as to there is a possibility that to cheat fingerprint recognition system using the fingerprint copy of forgery, have not
Stability；Such as recognition result is also had a certain impact in the case that fingerprint is destroyed or exception occurs in iris again.
The content of the invention
For above-mentioned technical problem, the shortcomings that it is an object of the invention to overcome above-mentioned existing single mode identification technology with not
Foot part, there is provided a kind of multimodal Biometrics devices and methods therefor, pass through the identification side for taking a variety of biological characteristics to blend
Formula, come the antifalsification for improving the accuracy of system, ensureing system.
Specifically technical scheme is：
Multimodal Biometrics device, including power supply module, display module, central processing unit, finger print acquisition module, face
Image capture module, iris image acquiring module, voice acquisition module, Password Input module and communication module；
Described display module, finger print acquisition module, facial image acquisition module, iris image acquiring module, voice are adopted
Collection module, Password Input module, communication module are connected with central processing unit respectively；
Described display module is used for information, the information comparing result for showing collection；
Described finger print acquisition module is used for the fingerprint for gathering user；
Described facial image acquisition module is used for the face image for gathering user；
Described iris image acquiring module is used for the iris image for gathering user；
Described voice acquisition module is used for the sound for gathering user；
Described Password Input module is used for user and inputs password；
Described communication module is used for central processing unit and connected with the control device of correlation；
Described central processing unit is used for the information for handling collection, and is contrasted with the information of database purchase, and will
Comparing result is shown by display, and the control device of correlation is sent to by communication module；
Power supply module is that other electricity consumption modules and central processing unit are powered.
Further, in addition to monitoring camera module, apart from induction module, lighting module；Described monitoring camera module,
It is connected respectively with central processing unit apart from induction module, lighting module；
Described monitoring camera module is used to monitor；
It is described to be used to judge whether the location of user meets acquisition request message apart from induction module；
Described lighting module is used to provide illumination.
Specifically, also include memory and bio-identification processor in described central processing unit；In described memory
Store the preset password information and bio-identification comparative information that are used to contrast gathered in advance；
The bio-identification processor is built-in to compare threshold setting unit and the storage list for storing bio-identification algorithm
Member, the threshold setting unit that compares can compare threshold value, the biology according to the biological characteristic adjustment bio-identification that success identifies
Recognizer includes fingerprint algorithm, facial algorithm, iris algorithm and vocal print algorithm.
Decision design, the frequency adjustment for comparing the different biological features that threshold setting unit can identify according to success is not
With the comparison threshold value of biological characteristic, comparison threshold value can also be manually set.
Present invention multimodal Biometrics method also corresponding to offer, including procedure below：
Finger print acquisition module, facial image acquisition module, iris image acquiring module, voice acquisition module gather use respectively
Biological information corresponding to family, user obtain encrypted message by Password Input module；
The encrypted message of acquisition and biological information are respectively sent to central processing unit, central processing unit first carries out letter
Quality evaluation is ceased, after assessment is qualified, information pre-processing is carried out, carries out feature extraction after pretreatment again, the information characteristics of extraction are again
Contrasted with Sample Storehouse data, characteristic matching, which is then shown, is verified result, mismatches and carries out encrypted message, biology spy again
Levy information gathering.
Wherein, collecting biological feature information process also includes：
Make to obtain user and facial image acquisition module, iris image acquiring module, voice collecting mould apart from induction module
The distance value of the collecting device of block；
Judge whether the distance value of user and collecting device meets collection requirement, if undesirable, prompt user's adjustment
With collecting device distance, until the distance value of user and collecting device meets the requirements；
Judge whether the angle of collecting device meets collection and require, if undesirable, prompt user to adjust collecting device,
It is set to turn an angle, until the angle of collecting device meets collection and required.
Further, after the biological information pretreatment of collection, between the comparison threshold value that sets is 30% -95%, often
The discrimination of item biological information, which is more than 30%, can assert that this is by not passed through then less than 30%；But such as
The discrimination that fruit is all is higher than 95%, does not also regard as passing through.
It is required that algorithm wherein two reach more than 70% in the case of, then other identification items can lower the requirement.
Compared with prior art, multimodal Biometrics device provided by the invention and its recognition methods, have following excellent
Point and effect.Reasonable combination or fusion by a variety of biological characteristics, with respect to single mode feature in noise immunity, big storehouse performance degradation
Degree, universality, anti-impersonation attack, the aspect of big data recognition time efficiency, all obtain the improvement in performance.Using the multimode
State or a variety of biological characteristic integration technology method and apparatus, can obtain identity more more preferable than single creature Feature Recognition System
Energy and reliability, and increase the difficulty and complexity for forging human body biological characteristics, the security of system is improved, represents biology
The development trend of feature recognition, suitable for the higher application environment of level of security, there is low cost, ease for use, users'comfort
The advantages that high, it can be applied to many applications such as the higher institutional settings of the daily management of enterprise, security protection level requirements, financial industry
Occasion.
Brief description of the drawings
Fig. 1 is the structural representation of the present invention；
Fig. 2 is flow chart of the method for the present invention.
Embodiment
It is described in conjunction with the embodiments the concrete technical scheme of the present invention：
As shown in figure 1, multimodal Biometrics device, including power supply module, display module, central processing unit, fingerprint are adopted
Collect module, facial image acquisition module, iris image acquiring module, voice acquisition module, Password Input module and communication module；
Described display module, finger print acquisition module, facial image acquisition module, iris image acquiring module, voice are adopted
Collection module, Password Input module, communication module are connected with central processing unit respectively；Also including monitoring camera module, distance perspective should
Module, lighting module；Described monitoring camera module, it is connected respectively with central processing unit apart from induction module, lighting module；
Described display module is used for information, the information comparing result for showing collection；
Described finger print acquisition module is used for the fingerprint for gathering user；
Described facial image acquisition module is used for the face image for gathering user；
Described iris image acquiring module is used for the iris image for gathering user；
Described voice acquisition module is used for the sound for gathering user；
Described Password Input module is used for user and inputs password；
Described communication module is used for central processing unit and connected with the control device of correlation；
Described central processing unit is used for the information for handling collection, and is contrasted with the information of database purchase, and will
Comparing result is shown by display, and the control device of correlation is sent to by communication module；
Power supply module is that other electricity consumption modules and central processing unit are powered.
Described monitoring camera module is used to monitor；
It is described to be used to judge whether the location of user meets acquisition request message apart from induction module；
Described lighting module is used to provide illumination.
Wherein, memory and bio-identification processor are also included in described central processing unit；Described memory internal memory
Store up the preset password information and bio-identification comparative information that are used to contrast gathered in advance；
The bio-identification processor is built-in to compare threshold setting unit and the storage list for storing bio-identification algorithm
Member, the threshold setting unit that compares can compare threshold value, the biology according to the biological characteristic adjustment bio-identification that success identifies
Recognizer includes fingerprint algorithm, facial algorithm, iris algorithm and vocal print algorithm.
It is special that the frequency for comparing the different biological features that threshold setting unit can identify according to success adjusts different biologies
The comparison threshold value of sign, comparison threshold value can also be manually set.
As shown in Fig. 2 change multimodal Biometrics method corresponding to multimodal Biometrics device, including procedure below：
Finger print acquisition module, facial image acquisition module, iris image acquiring module, voice acquisition module gather use respectively
Biological information corresponding to family, user obtain encrypted message by Password Input module；
The encrypted message of acquisition and biological information are respectively sent to central processing unit, central processing unit first carries out letter
Quality evaluation is ceased, after assessment is qualified, information pre-processing is carried out, carries out feature extraction after pretreatment again, the information characteristics of extraction are again
Contrasted with Sample Storehouse data, characteristic matching, which is then shown, is verified result, mismatches and carries out encrypted message, biology spy again
Levy information gathering.Ask whether to continue next user's checking again after being verified.
Wherein, collecting biological feature information process also includes：
Make to obtain user and facial image acquisition module, iris image acquiring module, voice collecting mould apart from induction module
The distance value of the collecting device of block；
Judge whether the distance value of user and collecting device meets collection requirement, if undesirable, prompt user's adjustment
With collecting device distance, until the distance value of user and collecting device meets the requirements；
Judge whether the angle of collecting device meets collection and require, if undesirable, prompt user to adjust collecting device,
It is set to turn an angle, until the angle of collecting device meets collection and required.
Wherein, after the biological information pretreatment of collection, between the comparison threshold value that sets is as 30% -95%, each is given birth to
The discrimination of thing characteristic information, which is more than 30%, can assert that this is by not passed through then less than 30%；But if institute
The discrimination for having item is higher than 95%, does not also regard as passing through.Or desired algorithm two feelings for reaching more than 70% wherein
Under condition, then other identification items can lower the requirement.
Claims (8)
1. multimodal Biometrics device, it is characterised in that including power supply module, display module, central processing unit, fingerprint collecting
Module, facial image acquisition module, iris image acquiring module, voice acquisition module, Password Input module and communication module；
Described display module, finger print acquisition module, facial image acquisition module, iris image acquiring module, voice collecting mould
Block, Password Input module, communication module are connected with central processing unit respectively；
Described display module is used for information, the information comparing result for showing collection；
Described finger print acquisition module is used for the fingerprint for gathering user；
Described facial image acquisition module is used for the face image for gathering user；
Described iris image acquiring module is used for the iris image for gathering user；
Described voice acquisition module is used for the sound for gathering user；
Described Password Input module is used for user and inputs password；
Described communication module is used for central processing unit and connected with the control device of correlation；
Described central processing unit is used for the information for handling collection, and is contrasted with the information of database purchase, and will contrast
As a result shown by display, the control device of correlation is sent to by communication module；
Power supply module is that other electricity consumption modules and central processing unit are powered.
2. multimodal Biometrics device according to claim 1, it is characterised in that also including monitoring camera module, away from
From induction module, lighting module；Described monitoring camera module, apart from induction module, lighting module respectively with central processing unit
Connection；
Described monitoring camera module is used to monitor；
It is described to be used to judge whether the location of user meets acquisition request message apart from induction module；
Described lighting module is used to provide illumination.
3. multimodal Biometrics device according to claim 1, it is characterised in that also wrapped in described central processing unit
Include memory and bio-identification processor；Described memory memory storage gather in advance be used for contrast preset password information and
Bio-identification comparative information；
The bio-identification processor is built-in to compare threshold setting unit and the memory cell for storing bio-identification algorithm, institute
Threshold value, the bio-identification calculation can be compared according to the biological characteristic adjustment bio-identification that success identifies by stating comparison threshold setting unit
Method includes fingerprint algorithm, facial algorithm, iris algorithm and vocal print algorithm.
4. multimodal Biometrics device according to claim 3, it is characterised in that the comparison threshold setting unit can
The comparison threshold value of the frequency adjustment different biological features of the different biological features identified according to success, can also manually set comparison
Threshold value.
5. multimodal Biometrics method, it is characterised in that including procedure below：
Finger print acquisition module, facial image acquisition module, iris image acquiring module, voice acquisition module gather user couple respectively
The biological information answered, user obtain encrypted message by Password Input module；
The encrypted message of acquisition and biological information are respectively sent to central processing unit, the advanced row information matter of central processing unit
Amount is assessed, assess it is qualified after, carry out information pre-processing, carry out feature extraction after pretreatment again, the information characteristics of extraction again with sample
This storehouse data is contrasted, and characteristic matching, which is then shown, is verified result, is mismatched and is carried out encrypted message, biological characteristic letter again
Breath collection.
6. multimodal Biometrics method according to claim 5, it is characterised in that collecting biological feature information process is also
Including：
Make to obtain user and facial image acquisition module, iris image acquiring module, voice acquisition module apart from induction module
The distance value of collecting device；
Judge whether the distance value of user and collecting device meets collection requirement, if undesirable, prompt user that adjustment is with adopting
Collect equipment distance, until the distance value of user and collecting device meets the requirements；
Judge whether the angle of collecting device meets collection and require, if undesirable, prompt user to adjust collecting device, make it
Turn an angle, until the angle of collecting device meets collection and required.
7. multimodal Biometrics method according to claim 5, it is characterised in that the biological information of collection is located in advance
After reason, between the comparison threshold value that sets is 30% -95%, the discrimination of each biological information, which is more than 30%, to be assert
This is by not passed through then less than 30%；But if the discrimination of all is higher than 95%, also do not regard as leading to
Cross.
8. multimodal recognition method according to claim 5, it is characterised in that it is required that algorithm reach for two wherein
In the case of more than 70%, then other identification items can lower the requirement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710933786.6A CN107657289A (en) | 2017-10-10 | 2017-10-10 | Multimodal Biometrics device and its recognition methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710933786.6A CN107657289A (en) | 2017-10-10 | 2017-10-10 | Multimodal Biometrics device and its recognition methods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107657289A true CN107657289A (en) | 2018-02-02 |
Family
ID=61117724
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710933786.6A Pending CN107657289A (en) | 2017-10-10 | 2017-10-10 | Multimodal Biometrics device and its recognition methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107657289A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110427829A (en) * | 2019-07-08 | 2019-11-08 | 北京虹安翔宇信息科技有限公司 | A kind of device and method based on multi-modal identification |
| CN110519061A (en) * | 2019-09-02 | 2019-11-29 | 国网电子商务有限公司 | A kind of identity identifying method based on biological characteristic, equipment and system |
| CN111445604A (en) * | 2020-04-03 | 2020-07-24 | 深圳市阿尔垎智能科技有限公司 | Intelligent door and door lock opening method |
-
2017
- 2017-10-10 CN CN201710933786.6A patent/CN107657289A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110427829A (en) * | 2019-07-08 | 2019-11-08 | 北京虹安翔宇信息科技有限公司 | A kind of device and method based on multi-modal identification |
| CN110519061A (en) * | 2019-09-02 | 2019-11-29 | 国网电子商务有限公司 | A kind of identity identifying method based on biological characteristic, equipment and system |
| CN111445604A (en) * | 2020-04-03 | 2020-07-24 | 深圳市阿尔垎智能科技有限公司 | Intelligent door and door lock opening method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104834849B (en) | Dual-factor identity authentication method and system based on Application on Voiceprint Recognition and recognition of face | |
| WO2017162076A1 (en) | Face identification method and system | |
| US7606396B2 (en) | Multimodal biometric platform | |
| US9122913B2 (en) | Method for logging a user in to a mobile device | |
| CN105825176A (en) | Identification method based on multi-mode non-contact identity characteristics | |
| WO2018082011A1 (en) | Living fingerprint recognition method and device | |
| US20070183634A1 (en) | Auto Individualization process based on a facial biometric anonymous ID Assignment | |
| CN104851140A (en) | Face recognition-based attendance access control system | |
| CN107657289A (en) | Multimodal Biometrics device and its recognition methods | |
| CN106709417A (en) | Multimodal biological recognition system and use method thereof | |
| CN205427946U (en) | Hotel moves in management system | |
| CN106981119A (en) | Entrance guard management system and method based on body shape | |
| AU2005307863B2 (en) | Multimodal biometric platform | |
| CN103856614A (en) | Method and device for avoiding error hibernation of mobile terminal | |
| Meraoumia et al. | An automated ear identification system using Gabor filter responses | |
| CN101464945A (en) | Identification characteristic identification method based on finger back arthrosis veins | |
| CN107911371A (en) | A kind of identity identifying method and system based on a variety of biological characteristics | |
| CN109858366A (en) | Identity identifying method and device | |
| CN110866234A (en) | Identity verification system based on multiple biological characteristics | |
| US20140025624A1 (en) | System and method for demographic analytics based on multimodal information | |
| CN110598522A (en) | Identity comparison method based on face and palm print palm vein recognition | |
| CN111339885A (en) | User identity determination method based on iris recognition and related device | |
| Agbinya et al. | Design and implementation of multimodal digital identity management system using fingerprint matching and face recognition | |
| CN206788947U (en) | Access control system based on body shape | |
| CN206757655U (en) | A kind of identity authorization system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180202 |
|
| WD01 | Invention patent application deemed withdrawn after publication |