CN109064613A - Face identification method and device - Google Patents
Face identification method and device Download PDFInfo
- Publication number
- CN109064613A CN109064613A CN201811091911.4A CN201811091911A CN109064613A CN 109064613 A CN109064613 A CN 109064613A CN 201811091911 A CN201811091911 A CN 201811091911A CN 109064613 A CN109064613 A CN 109064613A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- personnel
- images
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
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
- G07C9/30—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
Abstract
The embodiment of the present application provides a kind of face identification method, face-image by that will likely arrive at the pedestrian of gate mouth in advance is compared with personnel's face-image in access demographic data library, the personnel's face-image that may arrive at the pedestrian of gate mouth is drawn a circle to approve out as white list word bank, before last gate mouth, personnel's face-image in the first smaller white list word bank of ergodic data amount, is greatly saved the time to be verified in gate mouth etc..
Description
Technical field
This application involves electronic information technical fields, in particular to a kind of face identification method and device.
Background technique
It improves with the continuous development of science and technology, also starts introducing information technology in traditional routine work activity and formed
It combines.
When in the prior art, for carrying out recognition of face by gate inhibition, it usually needs the face letter prestored in Ergodic Theory
Breath, takes a long time, brings great inconvenience to daily production activity.
Summary of the invention
The application's is designed to provide a kind of face identification method and device, effectively to improve drawbacks described above.
Embodiments herein is accomplished in that
In a first aspect, the embodiment of the present application provides a kind of face identification method, a kind of face identification method, the method
It include: that m personnel's face-images in n pedestrian's face-images and preset access demographic data library are subjected to one-to-one face
Portion compares, and obtains m*n similarity value；Wherein, the m personnel's face-images are belonging respectively in access demographic data library
Whole m name access personnel respectively own, and n, m are the integer greater than 1；In the m personnel's face-images, select and institute
The similarity value for stating any row human face's image in n pedestrian's face-images meets a preferential comparison charts of the first preset threshold
Picture；Wherein, a is the integer not less than 0；According to a preferential comparison images, obtaining includes the white of a preferential comparison images
List word bank；When receive first kind camera to station gate mouth the first pedestrian shoot and obtain clearance application personnel face
When portion's image, each Zhang Youxian in the white list word bank is successively compared into image and clearance application personnel's face shines one
One carries out facial comparison, until determining there is the similarity shone with clearance application personnel's face in the white list word bank
Value is greater than a preferential comparison image of the second preset threshold；If it is determined that a preferential compare in image are led in the presence of with described
Close the preferential comparison image that the similarity value that application personnel face shines is greater than the second preset threshold, the lock of the open gate mouth
Machine.
Further, m personnel's faces by n pedestrian's face-images and preset access demographic data library
Image carries out one-to-one face and compares, and obtains m*n similarity value, before further include: receives the second class scanner to channel
In multiple pedestrians shooting and the n that obtains pedestrian's face-images；Wherein, first pedestrian reaches empty warp before the gate mouth
Cross the channel.
Further, the n pedestrians that reception the second class scanner obtains the shooting of pedestrians multiple in channel
Face-image, before further include: obtain the corresponding personnel's face-image uploaded of a user；By the personnel face figure
It is compared as the standard certificate photo in public security system corresponding with the user carries out face；When personnel's face-image
When the similarity value of the standard certificate photo in public security system corresponding with the user meets third predetermined threshold value, by described one
It opens personnel's face-image to be added in the access demographic data library that there is standard to have m-1 personnel's face-images, acquisition has m personnel
The access demographic data library of face-image.
Further, described according to a preferential comparison images, obtain the white names comprising a preferential comparison images
List library, later further include: receive the m that the first kind camera is sent1Open pedestrian's face-image；Wherein, m1For greater than 1
Integer；From the m1It opens in pedestrian's face-image, selects and the n opens any row human face's image in pedestrian's face-images
Similarity value meets a of the first preset threshold1Zhang Youxian compares image；Wherein, a1For the integer not less than 0；According to a
It is preferential to compare image and a1Zhang Youxian compares image, updates the white list word bank.
Further, described according to a preferential comparison images and a1Zhang Youxian compares image, described in update
White list word bank, comprising: judge a+a1Whether be more than the white list word bank capacity threshold；If a+a1More than the white list
The capacity threshold of word bank, in a preferential comparison images and a1Zhang Youxian compare image in, select it is newest reception and
Quantity is equal to a of the capacity threshold2Zhang Youxian compares image；Wherein, a2For not less than a and a1, and it is not more than a+a1It is whole
Number；According to a2Zhang Youxian compares image, and obtaining includes a2The white list word bank of Zhang Youxian comparison image.
Second aspect, the embodiment of the present application provide a kind of face identification device, comprising: the first comparison module, the first choosing
Select module, the first acquisition module, the second comparison module and open module；First comparison module, for n pedestrians are facial
Image carries out one-to-one face with the m in preset access demographic data library personnel's face-images and compares, and obtains m*n phase
Like angle value；Wherein, the m personnel's face-images are belonging respectively to m name access personnel whole in access demographic data library
Respectively all, n, m are the integer greater than 1；The first choice module, for selecting in the m personnel's face-images
Meet a preferential ratios of the first preset threshold with the similarity value of any row human face's image in the n pedestrian's face-images
To image；Wherein, a is the integer not less than 0；Described first obtains module, for obtaining according to a preferential comparison images
It obtains comprising a preferential white list word banks for comparing image；Second comparison module receives first kind camera pair for working as
Stand gate mouth the first pedestrian shooting and obtain clearance application personnel's face-image when, successively will be in the white list word bank
Each Zhang Youxian compare image and clearance application personnel's face and compare according to carrying out face one by one, it is described white up to determining
There is one of similarity value greater than the second preset threshold shone with clearance application personnel's face in list word bank preferentially to compare
Image；The open module is used for if it is determined that a preferential compare in image exist and the clearance application personnel face
According to similarity value be greater than the one of the second preset threshold and preferentially compare image, the gate of the open gate mouth.
Further, the face identification device, further includes: the first receiving module；First receiving module, is used for
Receive n pedestrian's face-images that the second class scanner obtains the shooting of pedestrians multiple in channel；Wherein, the first row
Void passes through the channel before people reaches the gate mouth.
Further, the face identification device, further includes: second obtains module, the second comparison module and mould is added
Block；Described second obtains module, for obtaining the corresponding personnel's face-image uploaded of a user；Described second compares mould
Block, for personnel's face-image standard certificate photo in public security system corresponding with the user to be carried out face
It compares；The addition module, for working as personnel's face-image mark in public security system corresponding with the user
When the similarity value of quasi- certificate photo meets third predetermined threshold value, personnel's face-image is added, and there is standard to have m-1
In the access demographic data library of personnel's face-image, the access demographic data library with m personnel's face-images is obtained.
Further, the face identification device, further includes: the second receiving module, the second selecting module and update mould
Block；Second receiving module, the m sent for receiving the first kind camera1Open pedestrian's face-image；Wherein, m1It is big
In 1 integer；Second selecting module is used for from the m1It opens in pedestrian's face-image, selects and the n opens pedestrian faces
The similarity value of any row human face image meets a of the first preset threshold in portion's image1Zhang Youxian compares image；Wherein, a1For
Integer not less than 0；The update module, for according to a preferential comparison images and a1Zhang Youxian compares image,
Update the white list word bank.
Further, the face recognition module, the update module include: judging unit, selecting unit and acquisition
Unit；The judging unit, for judging a+a1Whether be more than the white list word bank capacity threshold；The selecting unit,
If for a+a1More than the capacity threshold of the white list word bank, in a preferential comparison images and a1Zhang Youxian is compared
In image, select it is newest reception and quantity be equal to the capacity threshold a2Zhang Youxian compares image；Wherein, a2For not less than a
And a1, and it is not more than a+a1Integer；The obtaining unit, for according to a2Zhang Youxian compares image, and obtaining includes a2?
The preferential white list word bank for comparing image.
The beneficial effect of the embodiment of the present application is:
The embodiment of the present application provides a kind of face identification method, a kind of face identification method, which comprises by n
Pedestrian's face-image is opened to compare with the m in the preset access demographic data library one-to-one faces of personnel's face-images progress,
Obtain m*n similarity value；In the m personnel's face-images, select and any row in the n pedestrian's face-images
The similarity value of human face's image meets a preferential comparison images of the first preset threshold；According to a preferential comparison charts
Picture is obtained comprising a preferential white list word banks for comparing image；When receive first kind camera to station the first of gate mouth
Pedestrian shooting and obtain clearance application personnel's face-image when, successively by the white list word bank each Zhang Youxian compare
Image and clearance application personnel's face are compared according to carrying out face one by one, until determine to exist in the white list word bank with
The similarity value that clearance application personnel's face shines is greater than a preferential comparison image of the second preset threshold；If it is determined that described
A is preferential to compare that there is the similarity value that shines with clearance application personnel's face in images one excellent greater than the second preset threshold
First compare image, the gate of the open gate mouth.
Personnel's face in face-image and access demographic data library by the way that the pedestrian of gate mouth will likely be arrived in advance
Image compares, and draws a circle to approve out the personnel's face-image that may arrive at the pedestrian of gate mouth as white list word bank, in last gate
Before mouthful, personnel's face-image in the first smaller white list word bank of ergodic data amount is greatly saved to be tested in gate mouth etc.
The time of card.
To enable the above objects, features, and advantages of the application to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows a kind of structural block diagram of face identification system of the application first embodiment offer；
Fig. 2 shows a kind of structural frames of the embedded device of face identification system of the application first embodiment offer
Figure；
Fig. 3 shows a kind of flow chart of face identification method of the application second embodiment offer；
Fig. 4 shows a kind of structural block diagram of face identification device of the application 3rd embodiment offer；
Fig. 5 shows the structural block diagram of update module in a kind of face identification device of the application second embodiment offer.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Ground description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.Usually exist
The component of the embodiment of the present application described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed the application's to the detailed description of the embodiments herein provided in the accompanying drawings below
Range, but it is merely representative of the selected embodiment of the application.Based on embodiments herein, those skilled in the art are not being done
Every other embodiment obtained under the premise of creative work out, shall fall in the protection scope of this application.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.Term " first ", " the
Two " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
First embodiment
As shown in Figure 1, the embodiment of the invention provides a kind of face identification systems 20, comprising: the server for 10, it is red
Outer sensor 11, camera 12 and gate 13.Embedded equipment 10 and 13 communication link of infrared sensor 11, camera 12 and gate
It connects.
The server for 10 can be PC (personal computer, PC), tablet computer, smart phone,
Personal digital assistant (personal digital assistant, PDA), network server, database server etc..
The gate 13 is the gate that common electronic control is unlocked.
As shown in Fig. 2, be the server for 10 block diagram.The server includes: recognition of face dress for 10
Set 100, memory 101, storage control 102, processor 103, Peripheral Interface 104, input-output unit 105, display unit
106。
The memory 101, processor 103, Peripheral Interface 104, input-output unit 105, is shown storage control 102
Show that unit 106, each element are directly or indirectly electrically connected between each other, to realize the transmission or interaction of data.For example, these
Element can be realized by one or more communication bus or signal wire be electrically connected between each other.The face identification device includes
At least one can be stored in the memory or be solidificated in the server 10 in the form of software or firmware (firmware)
Operating system (operating system, OS) in software function module.The processor 103 is for executing memory
The executable module stored in 101, such as software function module or computer program that the face identification device includes.
Wherein, memory 101 may be, but not limited to, random access memory (Random Access Memory,
RAM), read-only memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only
Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM),
Electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory, EEPROM) etc..
Wherein, memory 101 is for storing program, and the processor 103 executes described program after receiving and executing instruction, subsequent
Method performed by the server 10 that the process that any embodiment of the embodiment of the present invention discloses defines can be applied to handle
In device 103, or realized by processor 103.
Processor 103 can be a kind of IC chip, the processing capacity with signal.Above-mentioned processor can be
General processor, including central processing unit (Central Processing Unit, abbreviation CPU), network processing unit (Network
Processor, abbreviation NP) etc.；It can also be digital signal processor (DSP), specific integrated circuit (ASIC), ready-made programmable
Gate array (FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware components, can be with
Realize or execute disclosed each method, step and the logic diagram in the embodiment of the present invention.General processor 103 can be micro-
Processor or the processor are also possible to any conventional processor etc..
Various input-output units 105 are couple processor 103 and memory 101 by the Peripheral Interface 104.One
In a little embodiments, Peripheral Interface, processor and storage control can be realized in one single chip.In some other example
In, they can be realized by independent chip respectively.
Input-output unit 105 is used to be supplied to the interaction that user input data realizes user and data collection station.Institute
Stating input-output unit may be, but not limited to, mouse and keyboard etc..
Display unit 106 provides an interactive interface, such as user interface between the mobile terminal and user,
Or it is referred to for display image data to user.In the present embodiment, the display unit can be liquid crystal display or touch-control
Display.It can be the capacitance type touch control screen or electric resistance touch-control of support single-point and multi-point touch operation if touch control display
Screen etc..It is one or more on the touch control display to support that single-point and multi-point touch operation refer to that touch control display can be sensed
The touch control operation generated simultaneously at position, and the touch control operation that this is sensed transfers to processor to be calculated and handled.
Second embodiment
Referring to Fig. 3, the face identification method is applied to a clothes the embodiment of the invention provides a kind of face identification method
Business device.
The face identification method includes: step S100, step S200, step S300, step S400 and step S500.
Step S100: by m personnel's face-images in n pedestrian's face-images and preset access demographic data library into
The one-to-one face of row compares, and obtains m*n similarity value；Wherein, the m personnel's face-images are belonging respectively to the access
Whole m name access personnel respectively own in demographic data library, and n, m are the integer greater than 1.
Step S200: it in the m personnel's face-images, selects and any row in the n pedestrian's face-images
The similarity value of human face's image meets a preferential comparison images of the first preset threshold；Wherein, a is the integer not less than 0.
Step S300: according to a preferential comparison images, the white list word banks comprising a preferential comparison images are obtained.
Step S400: when receive first kind camera to station gate mouth the first pedestrian shoot and obtain clearance Shen
When the person's of asking someone face-image, each Zhang Youxian in the white list word bank is successively compared into image and the clearance application personnel
Face shines until determining to exist in the white list word bank with clearance application personnel's face according to facial comparison is carried out one by one
Similarity value be greater than the second preset threshold one preferentially compare image.
Step S500: if it is determined that a it is preferential compare to exist in images shone with clearance application personnel's face
Similarity value is greater than a preferential comparison image of the second preset threshold, the gate of the open gate mouth.
The face identification method is before the step S100, further includes: step S14.
Step S11: n pedestrian's face figures that the second class scanner obtains the shooting of pedestrians multiple in channel are received
Picture；Wherein, void passes through the channel before first pedestrian reaches the gate mouth.
Wherein, it is notable that second preset threshold is greater than first preset threshold.Institute Hu n pedestrian faces
Portion's Image Acquisition is in the channel that pedestrian walks, then the n pedestrian's face-images are bound to, image quality is taken the photograph not as good as the first kind
As clearance application personnel's face-image that head obtains station in the first pedestrian shooting of gate mouth, an opposite institute is set at this time
State lower first preset threshold of the second preset threshold, so as to draw a circle to approve out as far as possible may be belong to last station gate mouth into
The personnel's face-image for the first pedestrian that row face compares.
The face identification method is before the step S14, further includes: step S11, step S12 and step S13.
Step S11: the corresponding personnel's face-image uploaded of a user is obtained.
Wherein, in step s 11, personnel's face-image of acquisition is very big to recognition of face influential effect, in a certain range
Interior, personnel's face-image is more clear, and pixel is higher, and the accuracy that face compares is higher；But what personnel's face-image occupied
Memory space will be higher, and transmission speed can also decline；Meeting requirement of the face face comparison function to personnel's face-image
Under, compromise processing, the quality of selection preferably personnel's face-image are done, appropriateness reduces photo size and pixel；
Step S12: by personnel's face-image standard certificate in public security system corresponding with the user
Row face is shone into compare.
Step S13: when personnel's face-image standard certificate in public security system corresponding with the user
According to similarity value meet third predetermined threshold value when, personnel's face-image is added, and there is standard to have the personnel faces m-1
In the access demographic data library of portion's image, the access demographic data library with m personnel's face-images is obtained.
The face identification method is after the step S300, further includes: step S40, step S50 and step S60.
Step S40: the m that the first kind camera is sent is received1Open pedestrian's face-image；Wherein, m1It is whole greater than 1
Number.
Step S50: from the m1It opens in pedestrian's face-image, selects and the n opens any row in pedestrian's face-images
The similarity value of human face's image meets a of the first preset threshold1Zhang Youxian compares image；Wherein, a1For the integer not less than 0.
Step S60: according to a preferential comparison images and a1Zhang Youxian compares image, updates the white list
Word bank.
Wherein, in step S60, including step S61, step S62 and step S63.
Step S61: judge a+a1Whether be more than the white list word bank capacity threshold.
Step S62: if a+a1More than the capacity threshold of the white list word bank, in a preferential comparison images and institute
State a1Zhang Youxian compare image in, select it is newest reception and quantity be equal to the capacity threshold a2Zhang Youxian compares image；Its
In, a2For not less than a and a1, and it is not more than a+a1Integer.
Step S63: according to a2Zhang Youxian compares image, and obtaining includes a2The white list of Zhang Youxian comparison image
Word bank.
A large amount of pedestrians have the residence time of certain time length, have under normal circumstances 3 seconds to 1 minute when channel is current, utilize
It does the comparison of dynamic human face face this period, that is, does what the m in access demographic data library personnel's face-images all traversed
Pretreatment；Server, which receives, is located at pedestrian's face-image that the first kind camera of passage proximate is captured, and does traversal face and search
Rope makes out similar personnel's face-image in m personnel's face-image centre circles；These personnel's Facial image synthesis dynamics are white
List, that is, white list word bank, the white list word bank are dynamic, and according to the inventory limitation and human face photo in white list word bank library
Holding time remove automatically；It illustrates, when walk is mobile posture, the similarity value of this face comparison
It is required that it is lower, to search out all similar human face photos as far as possible.It is embodied in embodiment provided herein
Be: the first preset threshold is less than the second preset threshold.This pretreatment mode can be effectively utilized user and walk on a passage
Time, the target zone of user is reduced, thus the covert face storage capacity for expanding terminal recognition of face.
It is worth noting that, being calculated and stored in multiple personnel's face-images progress face characteristic value in memory,
Face is carried out by the comparison of the characteristic value to face compares the accuracy rate that can effectively guarantee face comparison.In the application
In provided embodiment, the quantity for carrying out personnel's face-image that face compares with the personnel of current gate mouth is more, compares
Error chance it is bigger, embodiment provided herein can be by near field and dynamic face recognition technology, will be finally in lock
The quantity for the personnel's face-image for needing to compare when machine mouth is controlled in a lesser threshold values, and threshold values is smaller, compares chance of errors
It is smaller.
3rd embodiment
Referring to Fig. 4, the embodiment of the present application provides a kind of face identification device 100, comprising: the first comparison module 110,
First choice module 120, first obtains module 130, the second comparison module 140 and open module 150；
First comparison module 110, for n to be opened to the m in pedestrian's face-images and preset access demographic data library
It opens personnel's face-image and carries out one-to-one face comparison, obtain m*n similarity value；Wherein, the m personnel's face-images
It is belonging respectively to m name access personnel whole in access demographic data library respectively to own, n, m are the integer greater than 1；
The first choice module 120, in the m personnel's face-images, selecting and the n pedestrian faces
The similarity value of any row human face image meets a preferential comparison images of the first preset threshold in portion's image；Wherein, a is
Integer not less than 0；
Described first obtains module 130, for obtaining comprising a preferential comparison charts according to a preferential comparison images
The white list word bank of picture；
Second comparison module 140, for working as the first pedestrian bat for receiving first kind camera to standing in gate mouth
Take the photograph and obtain clearance application personnel's face-image when, successively by the white list word bank each Zhang Youxian compare image with
Clearance application personnel's face shines carries out facial comparison one by one, leads to until determining to exist in the white list word bank with described
Close the preferential comparison image that the similarity value that application personnel face shines is greater than the second preset threshold；
The open module 150 is used for if it is determined that a preferential compare in image exist and the clearance applicant
One of the similarity value that member's face shines greater than the second preset threshold preferentially compares image, the gate of the open gate mouth.
Wherein, the face identification device, further includes: the first receiving module 160；
First receiving module 160 obtains the shooting of pedestrians multiple in channel for receiving the second class scanner
N pedestrian's face-images；Wherein, void passes through the channel before first pedestrian reaches the gate mouth.
Wherein, the face identification device, further includes: second obtains module 170, the second comparison module 180 and be added
Module 190；
Described second obtains module 170, for obtaining the corresponding personnel's face-image uploaded of a user；
Second comparison module 180, for personnel's face-image is corresponding with the user in public security
Standard certificate photo in system carries out facial comparison；
The addition module 190, it is corresponding with the user in public security system for working as personnel's face-image
In the similarity value of standard certificate photo when meeting third predetermined threshold value, personnel's face-image is added to be had with standard
In the access demographic data library of m-1 personnel's face-images, the access demographic data with m personnel's face-images is obtained
Library.
In addition, the face identification device, further includes: the second receiving module 200, second selects 210 pieces of mould and updates
Module 220；
Second receiving module 200, the m sent for receiving the first kind camera1Open pedestrian's face-image；Its
In, m1For the integer greater than 1；
Second selecting module 210 is used for from the m1It opens in pedestrian's face-image, selects and the n opens pedestrians
The similarity value of any row human face image meets a of the first preset threshold in face-image1Zhang Youxian compares image；Wherein, a1
For the integer not less than 0；
The update module 220, for according to a preferential comparison images and a1Zhang Youxian compares image, more
The new white list word bank.
Referring to Fig. 5, wherein, the update module 220 includes: judging unit 221, selecting unit 222 and obtaining unit
223；
The judging unit 221, for judging a+a1Whether be more than the white list word bank capacity threshold；
The selecting unit 222, if being used for a+a1It is preferential at a more than the capacity threshold of the white list word bank
Compare image and a1Zhang Youxian compare image in, select it is newest reception and quantity be equal to the capacity threshold a2Zhang You
First compare image；Wherein, a2For not less than a and a1, and it is not more than a+a1Integer；
The obtaining unit 223, for according to a2Zhang Youxian compares image, and obtaining includes a2Zhang Youxian compares image
The white list word bank.
It should be noted that due to it is apparent to those skilled in the art that, for the convenience and letter of description
Clean, system, the specific work process of device and unit of foregoing description can be with reference to corresponding in preceding method embodiment
Journey, details are not described herein.
It should be understood by those skilled in the art that, the embodiment of the present application can provide as the production of method, system or computer program
Product.Therefore, in terms of the embodiment of the present application can be used complete hardware embodiment, complete software embodiment or combine software and hardware
Embodiment form.Moreover, it wherein includes computer available programs generation that the embodiment of the present application, which can be used in one or more,
The meter implemented in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of code
The form of calculation machine program product.
In conclusion the embodiment of the present application provides a kind of face identification method, a kind of face identification method, the method
It include: that m personnel's face-images in n pedestrian's face-images and preset access demographic data library are subjected to one-to-one face
Portion compares, and obtains m*n similarity value；In the m personnel's face-images, select and the n pedestrian's face-images
The similarity value of middle any row human face image meets a preferential comparison images of the first preset threshold；It is preferential according to a
Image is compared, is obtained comprising a preferential white list word banks for comparing image；When receive first kind camera to station in gate mouth
The first pedestrian shooting and obtain clearance application personnel's face-image when, successively by each Zhang You in the white list word bank
It first compares image and is compared with clearance application personnel's face according to progress face one by one, until determining in the white list word bank
Be greater than the second preset threshold in the presence of the similarity value shone with clearance application personnel's face one preferentially compares image；If it is determined that
The a preferential similarity values for existing in image and shining with clearance application personnel's face that compare are greater than the second preset threshold out
One preferential compare image, the gate of the open gate mouth.
Personnel's face in face-image and access demographic data library by the way that the pedestrian of gate mouth will likely be arrived in advance
Image compares, and draws a circle to approve out the personnel's face-image that may arrive at the pedestrian of gate mouth as white list word bank, in last gate
Before mouthful, personnel's face-image in the first smaller white list word bank of ergodic data amount is greatly saved to be tested in gate mouth etc.
The time of card.
By infrared identification, restarts camera collection image when determining that someone occurs and the appearance of personnel is known
When other, it is convenient and efficient and have good safety.
The above is only preferred embodiment of the present application, are not intended to limit this application, for those skilled in the art
For member, various changes and changes are possible in this application.Within the spirit and principles of this application, it is made it is any modification,
Equivalent replacement, improvement etc., should be included within the scope of protection of this application.It should also be noted that similar label and letter are under
Similar terms are indicated in the attached drawing in face, therefore, once being defined in a certain Xiang Yi attached drawing, are not then needed in subsequent attached drawing
It is further defined and explained.
More than, the only specific embodiment of the application, but the protection scope of the application is not limited thereto, and it is any to be familiar with
Those skilled in the art within the technical scope of the present application, can easily think of the change or the replacement, and should all cover
Within the protection scope of the application.Therefore, the protection scope of the application should be subject to the protection scope in claims.
Claims (10)
1. a kind of face identification method, which is characterized in that the described method includes:
M personnel's face-images in n pedestrian's face-images and preset access demographic data library are subjected to one-to-one face
Portion compares, and obtains m*n similarity value；Wherein, the m personnel's face-images are belonging respectively in access demographic data library
Whole m name access personnel respectively own, and n, m are the integer greater than 1；
In the m personnel's face-images, the phase with any row human face's image in the n pedestrian's face-images is selected
Meet a preferential comparison images of the first preset threshold like angle value；Wherein, a is the integer not less than 0；
According to a preferential comparison images, the white list word banks comprising a preferential comparison images are obtained；
When receive first kind camera to station gate mouth the first pedestrian shoot and obtain clearance application personnel's face figure
When picture, successively by each Zhang Youxian in the white list word bank compare image and clearance application personnel's face according to one by one into
Row face compares, until determining big in the presence of the similarity value shone with clearance application personnel's face in the white list word bank
One in the second preset threshold preferentially compares image；
If it is determined that there is the similarity value that shines with clearance application personnel's face in images greater than the in preferential compare of a
The one of two preset thresholds is preferential to compare image, the gate of the open gate mouth.
2. face identification method according to claim 1, which is characterized in that described by n pedestrian's face-images and pre-
If access demographic data library in m personnel's face-images carry out one-to-one face and compare, obtain m*n similarity value,
Before further include:
Receive n pedestrian's face-images that the second class scanner obtains the shooting of pedestrians multiple in channel；Wherein, described
Void passes through the channel before a group traveling together reaches the gate mouth.
3. face identification method according to claim 2, which is characterized in that reception the second class scanner is to channel
In multiple pedestrians shooting and the n that obtains pedestrian's face-images, before further include:
Obtain the corresponding personnel's face-image uploaded of a user；
One personnel's face-image standard certificate photo in public security system corresponding with the user is subjected to facial ratio
It is right；
When the similarity value of personnel's face-image standard certificate photo in public security system corresponding with the user
When meeting third predetermined threshold value, personnel's face-image is added to the access that there is standard there are m-1 personnel's face-images
In demographic data library, the access demographic data library with m personnel's face-images is obtained.
4. face identification method according to claim 3, which is characterized in that described according to a preferential comparison charts
Picture is obtained comprising a preferential white list word banks for comparing image, later further include:
Receive the m that the first kind camera is sent1Open pedestrian's face-image；Wherein, m1For the integer greater than 1；
From the m1It opens in pedestrian's face-image, selects the phase with any row human face's image in the n pedestrian's face-images
Meet a of the first preset threshold like angle value1Zhang Youxian compares image；Wherein, a1For the integer not less than 0；
According to a preferential comparison images and a1Zhang Youxian compares image, updates the white list word bank.
5. face identification method according to claim 4, which is characterized in that described according to a preferential comparison charts
Picture and a1Zhang Youxian compares image, updates the white list word bank, comprising:
Judge a+a1Whether be more than the white list word bank capacity threshold；
If a+a1More than the capacity threshold of the white list word bank, in a preferential comparison images and a1Zhang Youxian is compared
In image, select it is newest reception and quantity be equal to the capacity threshold a2Zhang Youxian compares image；Wherein, a2For not less than a
And a1, and it is not more than a+a1Integer；
According to a2Zhang Youxian compares image, and obtaining includes a2The white list word bank of Zhang Youxian comparison image.
6. a kind of face identification device characterized by comprising the first comparison module, first choice module, first obtain mould
Block, the second comparison module and open module；
First comparison module, for the m in n pedestrian's face-images and preset access demographic data library to be opened personnel faces
Portion's image carries out one-to-one face and compares, and obtains m*n similarity value；Wherein, the m personnel's face-images are belonging respectively to
Whole m name access personnel respectively own in access demographic data library, and n, m are the integer greater than 1；
The first choice module, in the m personnel's face-images, selecting and the n pedestrian's face-images
The similarity value of middle any row human face image meets a preferential comparison images of the first preset threshold；Wherein, a is not less than 0
Integer；
Described first obtains module, for preferentially comparing images according to a, obtains and preferentially compares the white of image comprising a
List word bank；
Second comparison module obtains station in the first pedestrian shooting of gate mouth for that ought receive first kind camera
Clearance application personnel's face-image when, each Zhang Youxian in the white list word bank is successively compared into image and the clearance
Application personnel's face according to facial comparison is carried out one by one, until determining exist and the clearance applicant in the white list word bank
One of the similarity value that member's face shines greater than the second preset threshold preferentially compares image；
The open module is used for if it is determined that a preferential compare in image exist and the clearance application personnel face
According to similarity value be greater than the one of the second preset threshold and preferentially compare image, the gate of the open gate mouth.
7. face identification device according to claim 6, which is characterized in that further include: the first receiving module；
First receiving module, for receiving the n rows that the second class scanner obtains the shooting of pedestrians multiple in channel
Human face's image；Wherein, void passes through the channel before first pedestrian reaches the gate mouth.
8. face identification device according to claim 7, which is characterized in that further include: second obtains module, the second comparison
Module and addition module；
Described second obtains module, for obtaining the corresponding personnel's face-image uploaded of a user；
Second comparison module, for personnel's face-image is corresponding with the user in public security system
Standard certificate photo carries out facial comparison；
The addition module, for working as personnel's face-image standard in public security system corresponding with the user
When the similarity value of certificate photo meets third predetermined threshold value, personnel's face-image is added, and there is standard to have m-1 people
In the access demographic data library of member's face-image, the access demographic data library with m personnel's face-images is obtained.
9. face identification device according to claim 8, which is characterized in that further include: the second receiving module, the second selection
Module and update module；
Second receiving module, the m sent for receiving the first kind camera1Open pedestrian's face-image；Wherein, m1For
Integer greater than 1；
Second selecting module is used for from the m1It opens in pedestrian's face-image, selects and the n opens pedestrian's face-images
The similarity value of middle any row human face image meets a of the first preset threshold1Zhang Youxian compares image；Wherein, a1For not less than
0 integer；
The update module, for according to a preferential comparison images and a1Zhang Youxian compares image, updates described white
List word bank.
10. face identification device according to claim 9, which is characterized in that the update module include: judging unit,
Selecting unit and obtaining unit；
The judging unit, for judging a+a1Whether be more than the white list word bank capacity threshold；
The selecting unit, if being used for a+a1More than the capacity threshold of the white list word bank, in a preferential comparison images
With a1Zhang Youxian compare image in, select it is newest reception and quantity be equal to the capacity threshold a2Zhang Youxian comparison chart
Picture；Wherein, a2For not less than a and a1, and it is not more than a+a1Integer；
The obtaining unit, for according to a2Zhang Youxian compares image, and obtaining includes a2Zhang Youxian compares the described white of image
List word bank.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811091911.4A CN109064613B (en) | 2018-09-18 | 2018-09-18 | Face recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811091911.4A CN109064613B (en) | 2018-09-18 | 2018-09-18 | Face recognition method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109064613A true CN109064613A (en) | 2018-12-21 |
| CN109064613B CN109064613B (en) | 2021-04-06 |
Family
ID=64763179
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811091911.4A Active CN109064613B (en) | 2018-09-18 | 2018-09-18 | Face recognition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109064613B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919091A (en) * | 2019-03-06 | 2019-06-21 | 广州佳都数据服务有限公司 | Face safety inspection method, device and electronic equipment based on dynamic white list |
| CN110991390A (en) * | 2019-12-16 | 2020-04-10 | 腾讯云计算（北京）有限责任公司 | Identity information retrieval method and device, service system and electronic equipment |
| CN112200944A (en) * | 2020-09-30 | 2021-01-08 | 广州市果豆科技有限责任公司 | Barrier gate control method and system combining face recognition |
| CN112381956A (en) * | 2019-10-31 | 2021-02-19 | 北京城建设计发展集团股份有限公司 | AI intelligent face recognition ticket selling and checking system and method based on cloud computing |
| WO2023173664A1 (en) * | 2022-03-18 | 2023-09-21 | 上海商汤智能科技有限公司 | Face recognition method and apparatus, electronic device, storage medium, computer program, and program product |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130215275A1 (en) * | 2011-05-18 | 2013-08-22 | Nextgenid, Inc. | Enrollment kiosk including biometric enrollment and verification, face recognition and fingerprint matching systems |
| CN104715271A (en) * | 2015-03-23 | 2015-06-17 | 北京中盾安全技术开发公司 | Witness verifying machine |
| CN105096420A (en) * | 2015-07-31 | 2015-11-25 | 北京旷视科技有限公司 | Access control system and data processing method for same |
| CN105260757A (en) * | 2015-10-22 | 2016-01-20 | 上海澄真信息科技有限公司 | Ticket checking system combining palm vein authentication and mobile positioning and method |
| CN105389880A (en) * | 2015-12-25 | 2016-03-09 | 成都比善科技开发有限公司 | Control method for multifunctional intelligent access control system |
| CN105550638A (en) * | 2015-12-07 | 2016-05-04 | 深圳市安网通信有限公司 | Intelligent self-service identity card customs control system and intelligent self-service identity card customs control method |
| CN106599813A (en) * | 2016-12-05 | 2017-04-26 | 中兴智能视觉大数据技术（湖北）有限公司 | Railway security check and security protection management system based on face recognition |
| CN107305624A (en) * | 2016-04-20 | 2017-10-31 | 厦门中控智慧信息技术有限公司 | A kind of person recognition method and device based on multi-mode biometric information |
| CN206805652U (en) * | 2017-05-15 | 2017-12-26 | 北京旷视科技有限公司 | Recognition of face gate |
| CN107609508A (en) * | 2017-09-08 | 2018-01-19 | 深圳市金立通信设备有限公司 | A kind of face identification method, terminal and computer-readable recording medium |
| CN107945347A (en) * | 2017-12-08 | 2018-04-20 | 苏州高新文体集团有限公司 | A kind of personal identification method |
| CN108389284A (en) * | 2018-01-18 | 2018-08-10 | 南京熊猫电子股份有限公司 | Gate identity fast verification system and method based on mobile phone IMSI identification technologies |
-
2018
- 2018-09-18 CN CN201811091911.4A patent/CN109064613B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130215275A1 (en) * | 2011-05-18 | 2013-08-22 | Nextgenid, Inc. | Enrollment kiosk including biometric enrollment and verification, face recognition and fingerprint matching systems |
| CN104715271A (en) * | 2015-03-23 | 2015-06-17 | 北京中盾安全技术开发公司 | Witness verifying machine |
| CN105096420A (en) * | 2015-07-31 | 2015-11-25 | 北京旷视科技有限公司 | Access control system and data processing method for same |
| CN105260757A (en) * | 2015-10-22 | 2016-01-20 | 上海澄真信息科技有限公司 | Ticket checking system combining palm vein authentication and mobile positioning and method |
| CN105550638A (en) * | 2015-12-07 | 2016-05-04 | 深圳市安网通信有限公司 | Intelligent self-service identity card customs control system and intelligent self-service identity card customs control method |
| CN105389880A (en) * | 2015-12-25 | 2016-03-09 | 成都比善科技开发有限公司 | Control method for multifunctional intelligent access control system |
| CN107305624A (en) * | 2016-04-20 | 2017-10-31 | 厦门中控智慧信息技术有限公司 | A kind of person recognition method and device based on multi-mode biometric information |
| CN106599813A (en) * | 2016-12-05 | 2017-04-26 | 中兴智能视觉大数据技术（湖北）有限公司 | Railway security check and security protection management system based on face recognition |
| CN206805652U (en) * | 2017-05-15 | 2017-12-26 | 北京旷视科技有限公司 | Recognition of face gate |
| CN107609508A (en) * | 2017-09-08 | 2018-01-19 | 深圳市金立通信设备有限公司 | A kind of face identification method, terminal and computer-readable recording medium |
| CN107945347A (en) * | 2017-12-08 | 2018-04-20 | 苏州高新文体集团有限公司 | A kind of personal identification method |
| CN108389284A (en) * | 2018-01-18 | 2018-08-10 | 南京熊猫电子股份有限公司 | Gate identity fast verification system and method based on mobile phone IMSI identification technologies |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919091A (en) * | 2019-03-06 | 2019-06-21 | 广州佳都数据服务有限公司 | Face safety inspection method, device and electronic equipment based on dynamic white list |
| CN112381956A (en) * | 2019-10-31 | 2021-02-19 | 北京城建设计发展集团股份有限公司 | AI intelligent face recognition ticket selling and checking system and method based on cloud computing |
| CN110991390A (en) * | 2019-12-16 | 2020-04-10 | 腾讯云计算（北京）有限责任公司 | Identity information retrieval method and device, service system and electronic equipment |
| CN110991390B (en) * | 2019-12-16 | 2023-04-07 | 腾讯云计算（北京）有限责任公司 | Identity information retrieval method and device, service system and electronic equipment |
| CN112200944A (en) * | 2020-09-30 | 2021-01-08 | 广州市果豆科技有限责任公司 | Barrier gate control method and system combining face recognition |
| WO2023173664A1 (en) * | 2022-03-18 | 2023-09-21 | 上海商汤智能科技有限公司 | Face recognition method and apparatus, electronic device, storage medium, computer program, and program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109064613B (en) | 2021-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109064613A (en) | Face identification method and device | |
| CN108875522A (en) | Face cluster methods, devices and systems and storage medium | |
| US10846552B1 (en) | Universal object recognition | |
| CN108197250B (en) | Picture retrieval method, electronic equipment and storage medium | |
| CN109766872A (en) | Image-recognizing method and device | |
| CN106856015B (en) | A kind of Work attendance method and device | |
| CN109829381A (en) | A kind of dog only identifies management method, device, system and storage medium | |
| CN106022032A (en) | Individual identification device, and identification threshold setting method | |
| CN109508694A (en) | A kind of face identification method and identification device | |
| CN109903474A (en) | A kind of intelligence based on recognition of face opens cabinet method and device | |
| CN109117760A (en) | Image processing method, device, electronic equipment and computer-readable medium | |
| KR101835333B1 (en) | Method for providing face recognition service in order to find out aging point | |
| CN110472504A (en) | A kind of method and apparatus of recognition of face | |
| EP2659434A1 (en) | Method for face registration | |
| CN108875484A (en) | Face unlocking method, device and system and storage medium for mobile terminal | |
| CN111401160A (en) | Hotel authentication management method, system and platform and hotel PMS system | |
| CN105989174A (en) | Extraction device and extraction method of area of interest | |
| CN108875582A (en) | Auth method, device, equipment, storage medium and program | |
| CN110175990A (en) | Quality of human face image determination method, device and computer equipment | |
| CN111626163A (en) | Human face living body detection method and device and computer equipment | |
| Alam et al. | A smart login system using face detection and recognition by ORB algorithm | |
| CN108681720A (en) | A kind of testimony of a witness veritification management system and method | |
| US20240028698A1 (en) | System and method for perfecting and accelerating biometric identification via evolutionary biometrics via continual registration | |
| CN108416298A (en) | A kind of scene judgment method and terminal | |
| CN108416595A (en) | Information processing method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |