CN109993084A - A kind of method of intelligent entrance guard multichannel recognition of face - Google Patents
A kind of method of intelligent entrance guard multichannel recognition of face Download PDFInfo
- Publication number
- CN109993084A CN109993084A CN201910213755.2A CN201910213755A CN109993084A CN 109993084 A CN109993084 A CN 109993084A CN 201910213755 A CN201910213755 A CN 201910213755A CN 109993084 A CN109993084 A CN 109993084A
- Authority
- CN
- China
- Prior art keywords
- face
- module
- entrance guard
- information
- connect
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000005764 inhibitory process Effects 0.000 claims abstract description 30
- 230000001815 facial effect Effects 0.000 claims abstract description 10
- 238000004891 communication Methods 0.000 claims description 40
- 238000012545 processing Methods 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 5
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 230000006870 function Effects 0.000 abstract description 8
- 238000001514 detection method Methods 0.000 description 4
- 230000001629 suppression Effects 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000012850 discrimination method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
-
- 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
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Alarm Systems (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to Internet technical field more particularly to a kind of method of intelligent entrance guard multichannel recognition of face, include the following steps: that multichannel face snap video camera accesses；Obtain the facial image of the video camera input；Recognition of face, modeling, face matching and addition personnel library；Video record in acquisition enabling front and back 15 seconds；Video information, face picture and comparison information are uploaded to server.The present invention realizes and passes in and out the identification of personnel to gate inhibition, judges whether it is resident and generate with functions such as pedestrian's records.In addition, the present invention also provides a kind of systems of intelligent entrance guard multichannel recognition of face.
Description
Technical field
The present invention relates to Internet technical field more particularly to a kind of methods of intelligent entrance guard multichannel recognition of face.
Background technique
Entrance guard management is the important component of community and building safety management, and existing guard method includes Orderless keyboard
Method, card identification method and biometric discrimination method etc..The keyboard of Orderless keyboard method is fixed on door, and user is easy defeated
Password is revealed when entering password；The safety of card identification method is also very poor, only recognizes card and does not recognize people, after user loses card, outside
Carry out personnel to be easy arbitrarily to pass in and out cell by the card picked up, threatens, and do not have personally identifiable information in card, visit to safety
Visitor's disengaging gate does not have systematic tracking, needs to ensure public security and manually checks on and record information, work is complicated and safety is low；Biology is known
The safety coefficient of other method is high, greatly improves safety coefficient.However traditional bio-identification gate inhibition is information island, is not had
Interconnect, it has not been convenient to group management, especially visitor also need rely on intercom system intercommunication enter, to managing caller less than
Position.
For this reason, it is necessary to provide a kind of method of intelligent entrance guard multichannel recognition of face to overcome drawbacks described above.
Summary of the invention
The present invention provides a kind of method of intelligent entrance guard multichannel recognition of face, the knowledge that personnel are passed in and out to gate inhibition is realized
Not, judge whether it is resident and generate with functions such as pedestrian's records.
The present invention provides a kind of system of intelligent entrance guard multichannel recognition of face, the knowledge that personnel are passed in and out to gate inhibition is realized
Not, judge whether it is resident and generate with functions such as pedestrian's records.
The technical solution used in the present invention are as follows:
A kind of method of intelligent entrance guard multichannel recognition of face, includes the following steps:
The access of multichannel face snap video camera；
Obtain the facial image of the video camera input；
Recognition of face, modeling, face matching and addition personnel library；
Video record in acquisition enabling front and back 15 seconds；
Video information, face picture and comparison information are uploaded to server.
Preferably, the step " facial image for obtaining the video camera input " specifically includes the following steps:
Dock the video camera proprietary protocol；
Obtain the picture stream of the video camera.
Preferably, the step " recognition of face, modeling, face matching and personnel library is added " specifically includes the following steps:
Face algorithm description and face picture modeling；
Generate face picture condition code；
Face matching is carried out, whether contrast judgement is object in resident library or personnel library, when contrast judgement result is no
When, personnel library is added in face information.
Preferably, the step " video record in 15 seconds before and after acquisition enabling " specifically includes following steps；
Gate inhibition's communication, opening door operation are executed according to contrast judgement result；
It extracts the video record before and after opening the door in 15 seconds and locally saves the video record of extraction.
Preferably, the step " uploading video information, face picture and comparison information to server " specifically includes:
Connect entrance guard management platform；
Video is uploaded in the front and back 15 seconds of opening the door to the entrance guard management platform；
It disconnects.
A kind of method of intelligent entrance guard multichannel recognition of face of the invention, passes through the access of multichannel Facial Image Capturing Camera, intelligence
Gate inhibition receives the face picture captured, and carries out analysis and obtains face information, whether contrast judgement is resident, when contrast judgement knot
Fruit be it is no when, by the face data input personnel library and obtain open the door front and back 15 seconds in video information and will be on video information
Server is reached, so that the present invention is gone back in the function of realizing the identification to gate inhibition disengaging personnel, judge whether it is resident
It generates with functions such as pedestrian's records, convenient for colleague personnel record and management.
The present invention provides a kind of systems of intelligent entrance guard multichannel recognition of face, comprising: multichannel face snap video camera, intelligence
Energy gate inhibition and entrance guard management platform,
The video camera includes:
First communication module is connect by proprietary protocol with gate inhibition；
Photographing module connect with the first communication module, obtains face figure according to the request command of gate inhibition transmission
Video information as information and before and after opening the door in 15 seconds；
First memory module is connect, for storing the camera shooting mould with the photographing module and the first communication module
The information of block transmission；
The intelligent entrance guard includes:
Second communication module is connect with the first communication module by proprietary protocol；
Module is obtained, is connect with the second communication module, sends request command, acquisition for issuing to the video camera
The facial image of the video camera input and the video information；
Determination module is compared, is connect with the acquisition module, for carrying out recognition of face, modeling, face matching and will locate
It manages result and personnel library is added；
Processing module is connect with the contrast judgement module and the acquisition module, is used for uploaded videos video information, people
Face picture and comparison result information；
Memory module is connect, for storing household information, Ren Yuanxin with the contrast judgement module and the processing module
Breath and video information, face picture and comparison information.
Control module is connect with the contrast judgement module, is used for access control opening signal.
Preferably, the comparison determination module includes:
First processing units are connect with the acquisition control module, for carrying out Face datection to picture；
Generation unit is connect with the first processing units, for generating face picture condition code；
Contrast judgement unit, connect with the generation unit and the memory module, for respectively with the resident in gate inhibition
Library is compared and is compared with personnel library；
Adding unit is connect, for when contrast judgement result is with the contrast judgement unit and the memory module
When no, personnel library is added in face information.
Preferably, the acquisition module includes:
Gate inhibition's communication and opening door operation unit, connect, according to the contrast judgement module with the second communication module
Judging result executes gate inhibition's communication, opening door operation；
Extraction unit, is communicated by the gate inhibition and the instruction of opening door operation unit transmission is extracted to the video camera and opened the door
Video record in front and back 15 seconds and the video record for locally saving extraction.
The system of a kind of intelligent entrance guard multichannel recognition of face of the invention, by proprietary protocol by first communication module and
The connection of two communication modules, the module that obtains receive the face information that the photographing module obtains, and the contrast judgement module will
The resident library and personnel library information comparison that the human face image information for obtaining module transmission and entrance guard management platform prestore, and will
Contrast judgement feeds back to the acquisition control module, and the processing module is according to the contrast judgement result of the contrast judgement module
Indicate that the acquisition control module sends door open command and face information is added to personnel when contrast judgement result is no
Library, the photographing module obtains the video information before and after opened the door in 15 seconds, and will acquire information and be uploaded to the memory module, from
And while realizing intelligence and opening the door, still realize the management to same pedestrian, stranger, the present invention realize to gate inhibition into
Out the identification of personnel, judge whether it is resident and generate with pedestrian record etc. functions.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the method for intelligent entrance guard multichannel recognition of face of the invention.
Fig. 2 is a kind of module frame chart of the system of intelligent entrance guard multichannel recognition of face of the present invention.
Specific embodiment
With reference to the accompanying drawing, embodiments of the present invention are specifically illustrated, attached drawing is only for reference and illustrates use, does not constitute pair
The limitation of the invention patent protection scope.
Embodiment 1:
Referring to FIG. 1, a kind of method of intelligent entrance guard multichannel recognition of face of the invention, comprising the following steps:
01, the access of multichannel face snap video camera.Specifically, by the video camera access gate inhibition system of multichannel face snap
System.
02, dock the video camera proprietary protocol.Specifically, the proprietary protocol pair of the access control system and the video camera
It connects.
03, obtain the picture stream of the video camera.Specifically, the request that the camera is transmitted according to the access control system
Instruction, which obtains corresponding face information respectively and will acquire information, feeds back to the access control system.
04, Face datection.Specifically, the access control system carries out people when receiving the picture of the video camera transmission
Face is detected and is positioned.Further, the people's face detection algorithm method particularly includes: carry out face inspection using 3 cascade modes of CNN
Survey and facial feature points detection.
1st CNN uses the full convolutional network of P-Net, for generating candidate window and frame regression vector (bounding box
regression vectors).The method of (bounding box regression) is returned using frame to correct these candidates
Window merges the candidate frame of overlapping using non-maxima suppression (NMS).
2nd CNN improves candidate window using N-Net.It will be inputted in R-Net by the candidate window of P-Net, refusal falls big portion
Divide non-real window, continues to use frame and return (bounding box regression) and non-maxima suppression (NMS) conjunction
And.
3rd CNN exports final face frame and characteristic point position using O-Net, generates 5 characteristic point positions.
05, generate face picture condition code.Specifically, the access control system according to the face frame that is obtained after step 04 and
Characteristic point position generates condition code, and this feature Calculative Process is as follows: width is according to coordinate in face block diagram picture after first height
The rgb value of the pixel of (x, y) generates eigenmatrix, further according to the value sequence in the corresponding eigenmatrix of each characteristic point position
Generate condition code.
06, face matching is carried out, whether contrast judgement is object in resident library or personnel library, when contrast judgement result is
When no, personnel library is added in face information.Specifically, at the human face image information that the access control system transmits the video camera
It is compared respectively with resident library information and personnel library information after reason, when contrast judgement to the face information is that resident library and personnel library are believed
Door open command is sent when breath, when contrast judgement result is no, personnel library is added in pictorial information by treated, to realize
Record management to same pedestrian while improving safety, is more convenient for using and managing for same administrative staff.
07, gate inhibition's communication, opening door operation are executed according to contrast judgement result.Specifically, when contrast judgement is to for non-resident
When library or personnel library object, gate inhibition's voice communication is executed, opening door operation is executed further according to sound result, when contrast judgement arrives.
08, it extracts the video record before and after opening the door in 15 seconds and locally saves the video record of extraction.Specifically, it mentions
Video record after taking away in front of the door in 15 seconds, and by the video record information preservation to the video camera.
09, connect entrance guard management platform.Specifically, the video camera connects entrance guard management platform.
10, video is uploaded in the front and back 15 seconds of opening the door to the entrance guard management platform.Specifically, before and after camera shooting generator terminal will open the door
Video information transmission in 15 seconds is to the entrance guard management platform.
11, it disconnects.Specifically, the communication connection of the entrance guard management platform and the video camera is disconnected.
Multichannel face snap video camera is arranged in a kind of method of intelligent entrance guard multichannel recognition of face of the invention, and front end is taken the photograph
Camera captures corresponding face information, the entrance guard management platform according to the request command that the entrance guard management platform is sent in real time
Recognition of face, modeling and face matching are carried out according to the face information of video camera transmission, and is same by contrast judgement result
When administrative staff, which is added into personnel library, and then the conveniently management to same administrative staff, further, opened the door
When, the camera obtains the video record before and after to open the door in 15 minutes, and will be on video information and gate inhibition's communication information whole
The server of entrance guard management platform is reached, the identification of personnel is passed in and out to gate inhibition, is judged whether it is so that the present invention realizes
Resident and generation are the same as functions such as pedestrian's records.
Embodiment 2:
Referring to FIG. 2, a kind of system of intelligent entrance guard multichannel recognition of face of the invention, comprising: multichannel face snap is taken the photograph
Camera 1 and the entrance guard management platform 2 being connect with the video camera 1.
Specifically, the video camera 1 includes: first communication module 11, photographing module 12 and the first memory module 13, described
First communication module 11 is used to connect by proprietary protocol with the entrance guard management platform 2, which is onvif agreement,
Before the request command that the photographing module 12 is used to be transmitted according to the entrance guard management platform 2 obtains human face image information and opens the door
Video information in 15 seconds afterwards, first memory module 13 connect with the photographing module 12 and the first communication module 11
The information for connecing, being transmitted for storing the photographing module 12.The entrance guard management platform 2 includes: second communication module 21, obtains
Control module 22 compares determination module 23, processing module 24 and memory module 25, the second communication module 21 and described first
The connection of communication module 11 is transmitted for realizing data, and the acquisition control module 22 connect with the second communication module 21, uses
Request command, the facial image for obtaining the video camera input and institute are sent in the instruction of sending opening gate and to the video camera
Video information is stated, the comparison determination module 23 is connect, with the acquisition module 22 for carrying out recognition of face, modeling, face
It matches and personnel library is added in processing result, the processing module 24 controls mould with the contrast judgement module 23 and the acquisition
Block 22 connects, for uploading video information, face picture and comparison information, the memory module 25 and the contrast judgement module
23 and the processing module 24 connection, for store household information, personal information and video information, face picture and compare letter
Breath.More specifically, obtaining control module 22 includes: gate inhibition's communication and opening door operation unit 221 and extraction unit 222, the door
Prohibit communication and opening door operation unit 221 is connect and according to the judgement of the contrast judgement module 23 with the second communication module 21
As a result gate inhibition's communication, opening door operation are executed, the extraction unit 222 is communicated by the gate inhibition and opening door operation unit 221 passes
The instruction sent extracts the video record before and after to open the door in 15 seconds to the video camera 1 and locally saves the video record of extraction
Picture, the contrast judgement module 23 include: that first processing units 231, generation unit 232, contrast judgement unit 233 and addition are single
Member 234, wherein the first processing units 231 connect with the extraction unit 222 for obtaining control module 22, are used for
Face algorithm description and face picture modeling, further, the first processing units 231 are receiving the biography of video camera 1
The picture sent carries out Face datection and positions, and specifically, carries out Face datection and face by using 3 cascade modes of CNN
Characteristic point detection, the 1st CNN uses the full convolutional network of P-Net, for generating candidate window and frame regression vector (bounding
box regression vectors).The method of (bounding box regression) is returned using frame to correct these
Candidate window merges the candidate frame of overlapping using non-maxima suppression (NMS).2nd CNN improves candidate window using N-Net.It will lead to
It crosses in the candidate window input R-Net of P-Net, refusal falls most of non-real window, continues to use frame and returns (bounding
Box regression) and non-maxima suppression (NMS) merging.3rd CNN exports final face frame and spy using O-Net
Sign point position, generates 5 characteristic point positions.The generation unit 232 is connect, with the first processing units 231 for generating
Face picture condition code, this feature Calculative Process are as follows: width is (x, y) according to coordinate in face block diagram picture after first height
The rgb value of pixel generates eigenmatrix, is sequentially generated spy further according to the value in the corresponding eigenmatrix of each characteristic point position
Levy code.The contrast judgement unit 233 connect with the generation unit 232 and the memory module 25, for respectively with gate inhibition
In resident library be compared and be compared with personnel library, adding unit 234 and the contrast judgement unit 233 and described deposit
Store up the connection of module 25, for when contrast judgement result is no, personnel library to be added in face information.More specifically, the place
It manages module 24 and uploads video information and face picture in real time, and same passerby is added to the memory module 25 according to testing result
In.
The working principle of the invention is: the acquisition control module 22 passes through the first communication module 21 and described second
Communication module 11 sends to the photographing module 12 and captures instruction, and the photographing module 12 captures visiting personnel information respectively, and
Picture stream information is fed back according to the request instruction that the acquisition control module 22 is transmitted, the contrast judgement module 23 is according to described
It obtains the pictorial information that control module 22 is transmitted and carries out recognition of face, modeling and face matching, and opened according to matching result generation
Door request instruction, the acquisition control module 22 further sends request instruction, before indicating that the photographing module 12 obtains enabling
Video information in 15 seconds afterwards, and will acquire result and be transferred to the processing module 24, the processing module 24 is tied according to detection
Fruit saves by the personnel library that same passerby is added in the memory module 25 and by gate inhibition's communication and video information to the storage
Module 25, so that the present invention is realized can improve safety coefficient, be also convenient for going together to the function of colleague's personal management
Personnel's is visiting.
Above disclosed is only presently preferred embodiments of the present invention, cannot limit rights protection model of the invention with this
It encloses, therefore according to equivalent variations made by scope of the present invention patent, is still within the scope of the present invention.
Claims (8)
1. a kind of method of intelligent entrance guard multichannel recognition of face, which comprises the steps of:
The access of multichannel face snap video camera；
Obtain the facial image of the video camera input；
Recognition of face, modeling, face matching and addition personnel library；
Video record in acquisition enabling front and back 15 seconds；
Video information, face picture and comparison information are uploaded to server.
2. the method for intelligent entrance guard multichannel recognition of face as described in claim 1, which is characterized in that the step " obtains institute
State the facial image of video camera input " specifically includes the following steps:
Dock the video camera proprietary protocol；
Obtain the picture stream of the video camera.
3. the method for intelligent entrance guard multichannel recognition of face as described in claim 1, which is characterized in that the step " know by face
Not, modeling, face match and are added personnel library " specifically includes the following steps:
Face algorithm description and face picture modeling；
Generate face picture condition code；
Face matching is carried out, whether contrast judgement is object in resident library or personnel library, will when contrast judgement result is no
Personnel library is added in face information.
4. the method for intelligent entrance guard multichannel recognition of face as described in claim 1, which is characterized in that the step " open by acquisition
Video record in 15 seconds after in front of the door " specifically includes following steps；
Gate inhibition's communication, opening door operation are executed according to contrast judgement result；
It extracts the video record before and after opening the door in 15 seconds and locally saves the video record of extraction.
5. the method for intelligent entrance guard multichannel recognition of face as described in claim 1, which is characterized in that the step " uploads record
As information, face picture and comparison information to server " it specifically includes:
Connect entrance guard management platform；
Video is uploaded in the front and back 15 seconds of opening the door to the entrance guard management platform；
It disconnects.
6. a kind of system of intelligent entrance guard multichannel recognition of face characterized by comprising multichannel face snap video camera and with institute
The entrance guard management platform of video camera connection is stated,
The video camera includes:
First communication module is connect by proprietary protocol with entrance guard management platform；
Photographing module connect with the first communication module, obtains people according to the request command of entrance guard management platform transmission
Video information before and after face image information and enabling in 15 seconds；
First memory module connect with the photographing module and the first communication module, passes for storing the photographing module
Defeated information；
The entrance guard management platform includes:
Second communication module is connect with the first communication module by proprietary protocol；
Control module is obtained, is connect with the second communication module, for issuing opening gate instruction and being sent out to the video camera
Send request command, the facial image for obtaining the video camera input and the video information；
Determination module is compared, is connect with the acquisition module, for carrying out recognition of face, modeling, face matching and knot being handled
Personnel library is added in fruit；
Processing module is connect, with the contrast judgement module and the acquisition control module for uploading video information, face figure
Piece and comparison information；
Memory module, connect with the contrast judgement module and the processing module, for store household information, personal information and
Video information, face picture and comparison information.
7. the system of intelligent entrance guard multichannel recognition of face as claimed in claim 6, which is characterized in that
The comparison determination module includes:
First processing units connect with the acquisition control module, model for face algorithm description and face picture；
Generation unit is connect, for generating face picture condition code with the first processing units；
Contrast judgement unit, connect with the generation unit and the memory module, for respectively with the resident library in gate inhibition into
Row is compared and is compared with personnel library；
Adding unit is connect, for when contrast judgement result is no with the contrast judgement unit and the memory module,
Personnel library is added in face information.
8. the system of intelligent entrance guard multichannel recognition of face as claimed in claim 6, which is characterized in that the acquisition control module
Include:
Gate inhibition's communication and opening door operation unit, connect, according to the judgement of the contrast judgement module with the second communication module
As a result gate inhibition's communication, opening door operation are executed；
Extraction unit, is communicated by the gate inhibition and the instruction of opening door operation unit transmission extracts front and back of opening the door to the video camera
Video record in 15 seconds and the video record for locally saving extraction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910213755.2A CN109993084A (en) | 2019-03-20 | 2019-03-20 | A kind of method of intelligent entrance guard multichannel recognition of face |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910213755.2A CN109993084A (en) | 2019-03-20 | 2019-03-20 | A kind of method of intelligent entrance guard multichannel recognition of face |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109993084A true CN109993084A (en) | 2019-07-09 |
Family
ID=67130702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910213755.2A Pending CN109993084A (en) | 2019-03-20 | 2019-03-20 | A kind of method of intelligent entrance guard multichannel recognition of face |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109993084A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113190700A (en) * | 2021-07-02 | 2021-07-30 | 成都旺小宝科技有限公司 | Face snapshot, screening and storage method and system for real estate transaction |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130279767A1 (en) * | 2012-04-24 | 2013-10-24 | Chih-Hsung Huang | Method of managing visiting guests by face recognition |
| CN106408696A (en) * | 2016-08-29 | 2017-02-15 | 珠海迈科智能科技股份有限公司 | Access control monitoring system |
| CN107067504A (en) * | 2016-12-25 | 2017-08-18 | 北京中海投资管理有限公司 | A kind of recognition of face safety-protection system and a suspect's detection and method for early warning |
| CN107665530A (en) * | 2017-09-26 | 2018-02-06 | 四川仪岛科技有限公司 | A kind of face identification unit gate control system and control method |
| US20180089499A1 (en) * | 2016-09-24 | 2018-03-29 | Nanchang O-Film Bio-Identification Technology Co., Ltd. | Face recognition method and device and apparatus |
| CN107895160A (en) * | 2017-12-21 | 2018-04-10 | 曙光信息产业(北京)有限公司 | Human face detection and tracing device and method |
| CN109243030A (en) * | 2018-09-13 | 2019-01-18 | 浙江工业大学 | A kind of control method and system of night contactless access control system |
-
2019
- 2019-03-20 CN CN201910213755.2A patent/CN109993084A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130279767A1 (en) * | 2012-04-24 | 2013-10-24 | Chih-Hsung Huang | Method of managing visiting guests by face recognition |
| CN106408696A (en) * | 2016-08-29 | 2017-02-15 | 珠海迈科智能科技股份有限公司 | Access control monitoring system |
| US20180089499A1 (en) * | 2016-09-24 | 2018-03-29 | Nanchang O-Film Bio-Identification Technology Co., Ltd. | Face recognition method and device and apparatus |
| CN107067504A (en) * | 2016-12-25 | 2017-08-18 | 北京中海投资管理有限公司 | A kind of recognition of face safety-protection system and a suspect's detection and method for early warning |
| CN107665530A (en) * | 2017-09-26 | 2018-02-06 | 四川仪岛科技有限公司 | A kind of face identification unit gate control system and control method |
| CN107895160A (en) * | 2017-12-21 | 2018-04-10 | 曙光信息产业(北京)有限公司 | Human face detection and tracing device and method |
| CN109243030A (en) * | 2018-09-13 | 2019-01-18 | 浙江工业大学 | A kind of control method and system of night contactless access control system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113190700A (en) * | 2021-07-02 | 2021-07-30 | 成都旺小宝科技有限公司 | Face snapshot, screening and storage method and system for real estate transaction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106204815B (en) | A kind of access control system based on human face detection and recognition | |
| CN109446981B (en) | Face living body detection and identity authentication method and device | |
| US20170032182A1 (en) | System for adaptive real-time facial recognition using fixed video and still cameras | |
| CN102663444B (en) | Method for preventing account number from being stolen and system thereof | |
| CN108961520A (en) | A kind of face identification method and device | |
| CN206515931U (en) | A kind of face identification system | |
| CN107590212A (en) | The Input System and method of a kind of face picture | |
| US20100329568A1 (en) | Networked Face Recognition System | |
| CN105913528A (en) | Method and device for processing access control data, method and device for access control | |
| CN106951846A (en) | A kind of face 3D models typing and recognition methods and device | |
| US11776308B2 (en) | Frictionless access control system embodying satellite cameras for facial recognition | |
| CN109243030B (en) | Control method and system of night non-contact access control system | |
| CN107688775A (en) | Binocular camera recognition of face right discriminating system and method based on elevator scene | |
| KR20160072386A (en) | Home network system using face recognition based features and method using the same | |
| KR100965428B1 (en) | The system and operating method using two different positioned intelligent cameras for automatic verification of authenticated person's entrance | |
| CN111583485A (en) | Community access control system, access control method and device, access control unit and medium | |
| CN108320359A (en) | A kind of city Internet of Things wisdom gate inhibition and safety-protection system | |
| CN111429638B (en) | Access control method based on voice recognition and face recognition | |
| Selvaraj et al. | Raspberry Pi based automatic door control system | |
| CN109377628A (en) | A kind of intelligent access control system and method | |
| Anusha et al. | Locker security system using facial recognition and One Time Password (OTP) | |
| CN111385440A (en) | Monitoring camera with face recording and inquiring functions | |
| CN109993084A (en) | A kind of method of intelligent entrance guard multichannel recognition of face | |
| CN112601054B (en) | Pickup picture acquisition method and device, storage medium and electronic equipment | |
| CN210721500U (en) | Security management and control system for lodging industry |
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: 20190709 |