CN108648312A - Recognition of face Intelligent greeting method and system - Google Patents
Recognition of face Intelligent greeting method and system Download PDFInfo
- Publication number
- CN108648312A CN108648312A CN201810445348.XA CN201810445348A CN108648312A CN 108648312 A CN108648312 A CN 108648312A CN 201810445348 A CN201810445348 A CN 201810445348A CN 108648312 A CN108648312 A CN 108648312A
- Authority
- CN
- China
- Prior art keywords
- face
- recognition
- visitor
- module
- server
- 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
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/20—Individual registration on entry or exit involving the use of a pass
- G07C9/22—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a kind of recognition of face Intelligent greeting methods, include the following steps：Visitor comes foreground and carries out visitor's registration by visitor's terminating machine；Enter in the identification range of video camera after the completion of visitor's registration, video camera shoots visitor；Recognition of face server extracts a top-quality facial image from the video flowing of thecamera head；Recognition of face server is compared head portrait is captured with photo in database；Determine whether to open the door according to the comparison result in S4；It compares consistent prompt to identify successfully, and opens the door simultaneously, the inconsistent prompt identification of comparison is inconsistent, then does not open the door.The present invention also provides a kind of recognition of face Intelligent greeting systems.The present invention while retaining original recognition of face entrance guard management, increase by convenience, face verification is carried out using the non-fit system of dynamic and is passed through, it is more convenient to compare traditional gate inhibition that swipes the card.Due to the uniqueness of face characteristic, while solving personnel and leaving behind certificate, falsely use the problems such as other people certificates.
Description
Technical field
The present invention relates to face recognition technologies, more specifically to a kind of recognition of face Intelligent greeting method and system.
Background technology
With going deep into for social electronic intelligent degree, now we have seen that access control system according to input equipment, medium
It can be divided into the difference of method：Password access system, access control system of swiping the card, bio-identification access control system.
Password access system：By inputting password, system judges password, and correctly just driving electric lock, opening door are let pass.
Advantage：Only it need to remember password, without carrying other media, cost is minimum.
Disadvantage：Speed is slow, and input password generally required in several seconds, if disengaging is overstaffed, needed to be lined up.If
Input error also needs to re-enter, and takes longer.Safety is poor, and bystander is easy to remember others' password by gesture, close
Code is easy to forget or reveal.Trend：The occasion that password access uses is fewer and fewer, only in, cost low to security requirement
It is low, it is also being used using occasion infrequently.Such as：Safety cabinet.
It swipes the card access control system：It is divided into as contact card access control system (magnetic stripe card, bar code card) and non-contact according to the type of card
Block (being called contactless card radio-frequency card) access control system.
Card access control system is contacted since contact card is easy to wear, access times are few, and card is easily damaged, and use
Range is fewer and fewer, is only used in the related occasion with bank card (magnetic stripe card), such as：Bank VIP channel gate inhibition
System, the part such as unattended cash dispenser access control system professional field are also using.
Contactless IC card, due to its durability, cost performance is good, reading speed is fast, safety is high etc., and advantages are current gate inhibitions
The mainstream of system.So contactless ic card access control system is just referred to as access control system by current many people.
Bio-identification access control system：The access control system of identity is identified according to the difference of human body biological characteristics.It common are：
Fingerprint entrance guard system (everyone having differences property of fingerprint patterned feature), the palm shape instrument access control system (bone of everyone palm
Having differences property of bone shape), iris entrance guard system (everyone retina passes through having differences property of optical scanner), Identification of Images
Access control system (everyone face feature and position difference) etc..
Advantage is：Without carrying the media such as card, the probability repeated is few, it is not easy to it is replicated, it is safe.
The disadvantage is that：It is of high cost.Since bio-identification needs to compare many parameter attributes, comparison speed is slow, is unfavorable for personnel
The excessive occasion of number.The biological characteristic of human body can change with the variation of environment and time, therefore easy to produce reject rate
(it is obviously this people, but his biological characteristic becomes, and it is me not to think), such as：Fingerprint is due to season and humidity
Different and different, palm shape and portrait change due to the growth at age, and iris changes due to eye illness.So biology
Identification gate control system is although advanced and safe, but that applies is limited in scope, and only small, security requirement is high, does not carry on a shoulder pole
The heart equal a small number of fields of high cost are applied, and are not the mainstreams of current access control system.
Invention content
The present invention is directed to the problem of being proposed in background technology, provides a kind of recognition of face Intelligent greeting method and system,
While retaining original recognition of face entrance guard management, increase by convenience, due to the uniqueness of face characteristic, simultaneously
Solution personnel leave behind certificate, falsely use the problems such as other people certificates.
In order to achieve the above object, the present invention provides a kind of recognition of face Intelligent greeting method, include the following steps：
S1, visitor come foreground and carry out visitor's registration by visitor's terminating machine；
Enter in the identification range of video camera after the completion of S2, visitor's registration, video camera shoots visitor；
S3, recognition of face server extract a top-quality facial image from the video flowing of thecamera head；
S4, recognition of face server will be captured photo in head portrait and database and compared；
S5, determine whether to open the door according to the comparison result in S4；It compares consistent prompt to identify successfully, and opens the door simultaneously, than
It is inconsistent to inconsistent prompt identification, then it does not open the door.
Above-mentioned recognition of face Intelligent greeting method, under preferred embodiment, when carrying out the step S3, the recognition of face clothes
Device be engaged in portrait progress true man's identification in video, and is carried out at the same time quality testing.
Above-mentioned recognition of face Intelligent greeting method, under preferred embodiment, after carrying out the step S3, to the face being drawn into
Image carries out modeling processing.
A kind of recognition of face Intelligent greeting system, including video camera, visitor's terminating machine, recognition of face server, open the door carry
Show module, enabling execution module, the input terminal of the recognition of face server and visitor's terminating machine and the video camera
Output end is connected；The output end of the recognition of face server and the enabling reminding module and the enabling execution module it is defeated
Enter end to be connected.
The recognition of face server includes that the face for being captured from image or video and detach, preserve portrait is caught
Obtain tracking module；The output end of the face acquisition and tracking module with for extracting face characteristic and generated face template
Face modeling module input terminal be connected.
The output end of the face modeling module is connected to the input terminal of recognition of face contrast module, the recognition of face pair
It is internally provided with face database than module；Comparing result information is sent to the enabling and carried by the recognition of face contrast module
Show module and the enabling execution module.
Above-mentioned recognition of face Intelligent greeting system, under preferred embodiment, the face acquisition and tracking inside modules are additionally provided with use
It is true man's recognition unit of true man or photo before identifying video camera.
Above-mentioned recognition of face Intelligent greeting system, under preferred embodiment, the face acquisition and tracking inside modules are additionally provided with use
In the picture quality detection unit for detecting picture quality to be compared.
The present invention is increased and is passed through while retaining original recognition of face entrance guard management using face recognition technology
Convenience, recognition of face gate inhibition welcome's system carries out face verification using the non-fit system of dynamic and passes through, and compares traditional brush
It is more convenient that toll bar is prohibited.Due to the uniqueness of face characteristic, while solving personnel and leaving behind certificate, falsely use the problems such as other people certificates.
Welcome's system based on face recognition technology can give enterprise and visitor splendid welcome's experience, enterprise image.
Description of the drawings
Fig. 1 is the flow chart of recognition of face Intelligent greeting method in the present invention；
Fig. 2 is the structure chart of face identification intelligent welcome's system of the present invention；
Fig. 3 is the internal structure chart of recognition of face server in the present invention.
In figure, 1, video camera, 2, visitor's terminating machine, 3, recognition of face server, 4, enabling reminding module, 5, opening the door executes
Module, 6, face acquisition and tracking module, 7, true man's recognition unit, 8, picture quality detection unit.
Specific implementation mode
As shown in Figure 1, a kind of recognition of face Intelligent greeting method of the present invention, includes the following steps：
S1, visitor come foreground and carry out visitor's registration by visitor's terminating machine；
Enter in the identification range of video camera after the completion of S2, visitor's registration, video camera shoots visitor；
S3, recognition of face server extract a top-quality facial image from the video flowing of thecamera head；
S4, recognition of face server will be captured photo in head portrait and database and compared；
S5, determine whether to open the door according to the comparison result in S4；It compares consistent prompt to identify successfully, and opens the door simultaneously, than
It is inconsistent to inconsistent prompt identification, then it does not open the door.
Further include the process of portrait capture and tracking in the step S3.
Portrait captures：Portrait is detected in a frame of piece image or video flowing and detaches portrait from background
Out, it and is automatically preserved.Portrait tracking refers to utilizing portrait capture technique, is shot in camera when specified portrait
Automatically to it into line trace when being moved in range.
Candid photograph head portrait with photo in database compare and be specifically referred to by recognition of face server in the step S4：People
Face identifies two kinds of comparison patterns of pyrene reality formula and search type.Verification formula is to referring to the portrait for obtaining capture or specified portrait
With certain registered a pair in database as the verification that compares determines whether it is same people.The comparison of search type refers to, from number
It is searched whether with the presence of specified portrait according to being searched in registered all portraits in library.
When carrying out the step S3, the recognition of face server carries out true man's identification to the portrait in video, and same
Shi Jinhang quality testings.
True man identify：System can identify that the people before obtaining camera is a real people or a photos.
Prevent user with this to be played tricks with photo.Technique needs user to make the interoperation of countenance.
Picture quality detects：The quality of picture quality directly influences the effect of identification, the detection work(of picture quality
Image quality measure can be carried out to the photo that will be compared, and provide corresponding recommended value to assist in identifying.
After carrying out the step S3, modeling processing is carried out to the facial image being drawn into.
Modeling is handled：Can the portrait data of registration storage be carried out to the feature of modeling extraction face, and be given birth to
It is saved in database at face template (face characteristic file).When carrying out face search (search type), by specified portrait
It is modeled, then by itself and the proprietary template phase matching identification in database, will finally be arranged according to the similar value compared
Go out most like lists of persons.
As shown in Fig. 2, a kind of recognition of face Intelligent greeting system, including video camera 1, visitor's terminating machine 2, recognition of face clothes
Business device 3, enabling reminding module 4, enabling execution module 5, the input terminal of the recognition of face server 3 and visitor's terminating machine
2 and the video camera 1 output end be connected；The output end of the recognition of face server 3 and the enabling reminding module 4 and institute
The input terminal for stating enabling execution module 5 is connected.
As shown in figure 3, the recognition of face server 3 includes, for capturing and detaching, depositary from image or video
The face acquisition and tracking module 6 of picture；The output end of the face acquisition and tracking module 6 with for extract face characteristic and by its
The input terminal for generating the face modeling module 9 of face template is connected.
The output end of the face modeling module 9 is connected to the input terminal of recognition of face contrast module 10, and the face is known
Other contrast module 10 is internally provided with face database 11；Comparing result information is sent to institute by the recognition of face contrast module
State enabling reminding module 4 and the enabling execution module 5.
It is that the true man of true man or photo know that the face acquisition and tracking inside modules, which are additionally provided with before video camera for identification,
Other unit 7.The face acquisition and tracking inside modules are additionally provided with the picture quality for detecting picture quality to be compared and detect
Unit 8.
The regional characteristics analysis algorithm being widely adopted in face knowledge technology, it merged computer image processing technology with
Biostatistics principle extracts portrait characteristic point in one, using computer image processing technology from video, is united using biology
The principle that meter is learned carries out analysis founding mathematical models, i.e. skin detection.Using built skin detection and it is tested
The image surface of the people of person carries out signature analysis, and a similar value is provided according to the result of analysis.Can determine by this value is
No is same people.
Visitor's flow：Recognition of face Intelligent greeting system is mainly used for the statistics of turning out for work to company personnel, when employee registers
It needs through camera acquisition to employee's mug shot, then characteristic value is obtained from collected photo by face recognition algorithms
And analysis comparison is carried out with the characteristic value of the employee's human face photo pre-deposited in database, it has voice and carries after identifying successfully
Show that " hello " quotes the name of employee, then attendance success.
System can also record the job information of employee in detail, specific time, birthday of addition company etc. be included when, in spy
System can beat birthday, festivals or holidays when employee checks card attendance success or celebrate that employee enters company's year and a day in the different date
Blessing language etc..
Our company combines the market demand over the past two years, the recognition of face welcome system of new generation of independent research.This product is integrated
Live face acquisition, managing caller, blacklist early warning, white list automatic identification, people cross and the functions such as face are stayed to be integrated.It is adopted from scene
Collection human face photo is compared.Collected information and comparison result can be uploaded to the completion of big data acquisition platform in real time simultaneously
Daily welcome, visitor, attendance, gate inhibition (optional) etc..Single identification determines whether me in 0.1 second, single channel equipment 1 second recognizable 3
People.
Recognition of face gate inhibition welcome's system can be widely used for factory, enterprises and institutions, university dormitory, building, residential quarter etc.
Place can realize personnel identity identification, VIP welcome's service, staff attendance, visitor's registration, stranger in conjunction with background management system
The functions such as prompting, daily data statistics, inquiry, real automatic business processing.
Main function module：
1, face capture and following function
Face capture refers to detecting portrait in a frame of piece image or video flowing and detaching portrait from background
Out, it and is automatically preserved.Portrait tracking refers to utilizing portrait capture technique, is shot in video camera when specified portrait
Automatically to it into line trace when being moved in range.
2, recognition of face compares
Two kinds of comparison patterns of recognition of face pyrene reality formula and search type.Verification formula be to refer to will the obtained portrait of capture or
It is registered in specified portrait and database that certain is a pair of as the verification that compares determines whether it is same people.The comparison of search type
Refer to searching for and being searched whether with the presence of specified portrait from registered all portraits in database.
3, the modeling and retrieval of face
Can the portrait data of registration storage be carried out to the feature of modeling extraction face, and be generated face template (people
Face tag file) it is saved in database.When carrying out face search (search type), specified portrait is modeled, then will
Itself and the proprietary template phase matching identification in database, will finally list most like personnel according to the similar value compared
List.
4, true man's identification function
System can identify that the people before obtaining video camera is a real people or a photos.Prevent user with this
It is played tricks with photo.Technique needs user to make the interoperation of countenance.
5, picture quality detects
The quality of picture quality directly influences the effect of identification, and the detection function of picture quality can be to that will be compared
Photo carry out image quality measure, and provide corresponding recommended value to assist in identifying.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Any one skilled in the art in the technical scope of present disclosure, according to the technique and scheme of the present invention and its
Inventive concept is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (6)
1. a kind of recognition of face Intelligent greeting method, which is characterized in that include the following steps：
S1, visitor come foreground and carry out visitor's registration by visitor's terminating machine；
Enter in the identification range of video camera after the completion of S2, visitor's registration, video camera shoots visitor；
S3, recognition of face server extract a top-quality facial image from the video flowing of thecamera head；
S4, recognition of face server will be captured photo in head portrait and database and compared；
S5, determine whether to open the door according to the comparison result in S4；It compares consistent prompt to identify successfully, and opens the door simultaneously, compare not
Consistent prompt identification is inconsistent, then does not open the door.
2. recognition of face Intelligent greeting method according to claim 1, which is characterized in that when carrying out the step S3, institute
It states recognition of face server and true man's identification is carried out to the portrait in video, and be carried out at the same time quality testing.
3. recognition of face Intelligent greeting method according to claim 2, which is characterized in that right after carrying out the step S3
The facial image being drawn into carries out modeling processing.
4. a kind of recognition of face Intelligent greeting system, which is characterized in that know including video camera (1), visitor's terminating machine (2), face
Other server (3), enabling reminding module (4), enabling execution module (5), the input terminal of the recognition of face server (3) and institute
The output end for stating visitor's terminating machine (2) and the video camera (1) is connected；The output end of the recognition of face server (3) and institute
The input terminal for stating enabling reminding module (4) and the enabling execution module (5) is connected；
The recognition of face server (3) includes the face capture for capturing and detaching, preserve portrait from image or video
Tracking module (6)；The output end of the face acquisition and tracking module (6) with for extracting face characteristic and generated face
The input terminal of the face modeling module (9) of template is connected；
The output end of the face modeling module (9) is connected to the input terminal of recognition of face contrast module (10), and the face is known
Other contrast module (10) is internally provided with face database (11)；The recognition of face contrast module sends comparing result information
To the enabling reminding module (4) and the enabling execution module (5).
5. recognition of face Intelligent greeting system according to claim 4, which is characterized in that in the face acquisition and tracking module
Portion be additionally provided with before video camera for identification be true man or photo true man's recognition unit (7).
6. recognition of face Intelligent greeting system according to claim 5, which is characterized in that in the face acquisition and tracking module
Portion is additionally provided with the picture quality detection unit (8) for detecting picture quality to be compared.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810445348.XA CN108648312A (en) | 2018-05-11 | 2018-05-11 | Recognition of face Intelligent greeting method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810445348.XA CN108648312A (en) | 2018-05-11 | 2018-05-11 | Recognition of face Intelligent greeting method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108648312A true CN108648312A (en) | 2018-10-12 |
Family
ID=63754240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810445348.XA Pending CN108648312A (en) | 2018-05-11 | 2018-05-11 | Recognition of face Intelligent greeting method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108648312A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109544743A (en) * | 2018-11-20 | 2019-03-29 | 国网山东省电力公司济宁供电公司 | A kind of recognition of face access system based on intelligent machine room data center |
| CN110322602A (en) * | 2019-06-18 | 2019-10-11 | 特斯联（北京）科技有限公司 | A kind of visitor reserves passing method, system and equipment |
| CN111145413A (en) * | 2019-12-26 | 2020-05-12 | 上海电气集团数字科技有限公司 | Intelligent access control system and face recognition method thereof |
| CN112669507A (en) * | 2019-12-17 | 2021-04-16 | 上海云思智慧信息技术有限公司 | Method, system, medium, and device for selecting welcome mode |
-
2018
- 2018-05-11 CN CN201810445348.XA patent/CN108648312A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109544743A (en) * | 2018-11-20 | 2019-03-29 | 国网山东省电力公司济宁供电公司 | A kind of recognition of face access system based on intelligent machine room data center |
| CN110322602A (en) * | 2019-06-18 | 2019-10-11 | 特斯联（北京）科技有限公司 | A kind of visitor reserves passing method, system and equipment |
| CN112669507A (en) * | 2019-12-17 | 2021-04-16 | 上海云思智慧信息技术有限公司 | Method, system, medium, and device for selecting welcome mode |
| CN111145413A (en) * | 2019-12-26 | 2020-05-12 | 上海电气集团数字科技有限公司 | Intelligent access control system and face recognition method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105930709B (en) | Face recognition technology is applied to the method and device of testimony of a witness consistency check | |
| CN106203294B (en) | The testimony of a witness based on face character analysis unifies auth method | |
| CN108985134B (en) | Face living body detection and face brushing transaction method and system based on binocular camera | |
| Balcoh et al. | Algorithm for efficient attendance management: Face recognition based approach | |
| CN108648312A (en) | Recognition of face Intelligent greeting method and system | |
| CN101556717A (en) | ATM intelligent security system and monitoring method | |
| CN108846306A (en) | A kind of identity card Compare System and method based on deep learning recognition of face | |
| CN105119723A (en) | Identity authentication and authorization method based on human eye recognition | |
| CN101751562B (en) | Bank transaction image forensic acquiring method based on face recognition | |
| Kant et al. | Fake face recognition using fusion of thermal imaging and skin elasticity | |
| CN114218543A (en) | Encryption and unlocking system and method based on multi-scene expression recognition | |
| CN208156743U (en) | Recognition of face Intelligent greeting system | |
| CN202887214U (en) | Human identity recognizing device based on face recognition | |
| CN111723595A (en) | Personnel identity identification method and system | |
| JP5877678B2 (en) | Face authentication database management method, face authentication database management apparatus, and face authentication database management program | |
| Singh et al. | A review on biometrics and ear recognition techniques | |
| Li et al. | The evolution of biometrics | |
| CN208384668U (en) | A kind of access control system applied to vehicle driver examination | |
| Joshi et al. | Face Recognition Technology: A Review. | |
| Mitra et al. | ◾ Overview of Biometric Authentication | |
| Nethravathi et al. | Advanced Face Recognition Based Door Unlock System Using Arduino & MATLAB | |
| Rajput et al. | Face recognition system for door security using Raspberry Pi | |
| Sonkamble et al. | An effective machine-vision system for information security and privacy using iris biometrics | |
| Balaiah et al. | Automated Attendance System using Facial Recognition | |
| Nagpal et al. | Biometric techniques and facial expression recognition-A review |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181012 |