CN109583326A - Method, apparatus and computer equipment based on recognition of face verifying outsourcing employee - Google Patents
Method, apparatus and computer equipment based on recognition of face verifying outsourcing employee Download PDFInfo
- Publication number
- CN109583326A CN109583326A CN201811340836.0A CN201811340836A CN109583326A CN 109583326 A CN109583326 A CN 109583326A CN 201811340836 A CN201811340836 A CN 201811340836A CN 109583326 A CN109583326 A CN 109583326A
- Authority
- CN
- China
- Prior art keywords
- facial information
- matching
- value
- employee
- matching value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- 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
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
This application involves field of artificial intelligence, disclose a kind of method, apparatus and computer equipment based on recognition of face verifying outsourcing employee, wherein method include: obtain be arranged in employee check card place camera acquisition enter workplace personnel the first facial information, and obtain current environment illumination intensity value;First facial information is matched with each of Outsourced database the second facial information respectively, using highest matching value as the first matching value, and searches the second matching value corresponding with the illumination intensity value as matching threshold;If the first matching value is lower than the matching threshold, mark first facial information abnormal.The acquisition of the application employee place of checking card enters the first facial information of the personnel of workplace, and judge whether the personnel of admission are outsourcing service providers according to the intensity of illumination at the place of checking card, workplace is entered after effectively avoiding other people that outsourcing service provider is replaced to check card and causes the risk of company's information leakage.
Description
Technical field
This application involves field of artificial intelligence is arrived, especially relate to a kind of based on recognition of face verifying outsourcing employee
Method, apparatus and computer equipment.
Background technique
Most of company only carries out simple personnel identity verification to outsourcing employee in registration process, enters trade-after no longer to outsourcing
Worker carries out periodic reinvestigation.But reality is, since that there are mobility is strong by outsourcing service provider, company affiliation sense is weaker, portion
There is the features such as speculative and management difficulty is larger in point personnel, there are still later period personnel occur by work card to other people help into
Enter workplace carry out generation check card, or even allow other people help substitute into field work situations such as, the classified papers of company can be generated in this way
The risk leaked out.Therefore, it is necessary to audit when entering workplace to outsourcing service provider, avoid borrowing because of other people outer
The card of packet personnel enters information leakage event caused by workplace.
So providing the problem of new method based on recognition of face verifying outsourcing employee of one kind is urgent need to resolve.
Summary of the invention
The main purpose of the application is to provide a kind of method, dress that outsourcing employee is fast and accurately verified based on recognition of face
It sets and computer equipment.
In order to achieve the above-mentioned object of the invention, the application proposes a kind of method based on recognition of face verifying outsourcing employee, packet
Include: obtain be arranged in employee check card place camera acquisition enter workplace personnel the first facial information, and obtain
The illumination intensity value of current environment;
First facial information is matched with each of Outsourced database the second facial information respectively, is obtained
Multiple matching values, using highest matching value as the first matching value, and in the respective column of preset intensity of illumination and matching value
The second matching value corresponding with the illumination intensity value is searched in table as matching threshold;
Judge whether first matching value is lower than the matching threshold;
If so, label first facial information is abnormal.Further, it is described by first facial information respectively and outside
The second facial information of each of bag data library is matched, and multiple matching values are obtained, using highest matching value as first
Before the step of matching value, comprising:
Receive the positive face photo and side face photo of each outsourcing service provider;
Extract respectively each described positive face take and side face picture in facial information, obtain each described positive face
Corresponding second facial information of photo and corresponding second facial information of the side face photo;
It will all second facial information store into preset Outsourced database.
Further, it is described by first facial information respectively with the second face of each of the Outsourced database
Information is matched, and multiple matching values are obtained, and includes: using highest matching value as the step of the first matching value
First facial information is input to preset Sexual discriminating model, judges the sex types of the personnel;
The second facial information identical with the sex types of the personnel is searched in the Outsourced database;
First facial information is identical with the sex types of the personnel in the Outsourced database respectively
Second facial information is matched, and multiple matching values are obtained, using highest matching value as the first matching value.
Further, it is described by first facial information respectively with the second facial information of each of Outsourced database
It is matched, obtains multiple matching values, using highest matching value as before the step of the first matching value, comprising:
Multiple sample facial informations and the corresponding gender of sample facial information are input in neural network model, are carried out
Training;
The parameter for exporting the neural network model obtains the Sexual discriminating model.
Further, it is described by first facial information respectively with the property with the personnel in the Outsourced database
Identical second facial information of other type is matched, and multiple matching values is obtained, using highest matching value as the first matching value
The step of, comprising:
First facial information is identical with the sex types of the personnel in the Outsourced database respectively
Second facial information matches respectively, obtains multiple matching values;
By value highest in the multiple matching value multiplied by the corresponding default sex coefficient of the sex types, obtain described
First matching value.
Further, after the step of label the first facial information exception, comprising:
By first facial information load on the display screen that employee checks card place.
Further, it is described acquisition be arranged in employee check card place camera acquisition carry out workplace personnel first
Before the step of facial information, comprising:
Obtain employee check card place range sensor detection range sensor in front of object distance value;
Judge whether the distance value is less than preset distance threshold;
If so, generating the instruction of the first facial information of acquisition.
The application also provides a kind of device based on recognition of face verifying outsourcing employee, comprising:
Obtain module, for obtains be arranged in employee check card place camera acquisition into workplace personnel first
Facial information, and obtain the illumination intensity value of current environment;
Matching module, for by first facial information respectively with the second facial information of each of Outsourced database
Matched, obtain multiple matching values, using highest matching value as the first matching value, and preset intensity of illumination with
The second matching value corresponding with the illumination intensity value is searched in corresponding lists with value as matching threshold;
First judgment module, for judging whether first matching value is lower than the matching threshold;
Mark module marks first facial information different if being lower than the matching threshold for first matching value
Often.
The application also provides a kind of computer equipment, including memory and processor, and the memory is stored with computer
The step of program, the processor realizes any of the above-described the method when executing the computer program.
The application also provides a kind of computer readable storage medium, is stored thereon with computer program, the computer journey
The step of method described in any of the above embodiments is realized when sequence is executed by processor.
The method, apparatus and computer equipment based on recognition of face verifying outsourcing employee of the application, checks card place in employee
Acquisition enters the first facial information of the personnel of workplace, and judges that according to the intensity of illumination at the place of checking card, the personnel of admission are
No is the outsourcing service provider with typing information, effectively avoid other people replace outsourcing service provider check card enter workplace and
Cause the risk of company's information leakage.Before carrying out recognition of face, first judgement enters the gender of the personnel of workplace, in data
It will only be matched with consistent second facial information of above-mentioned gender when being matched in library, and reduce matched number, accelerate matching
Speed.When it fails to match, by the load of the first facial information on the display screen for checking card place, police is played to for the personnel to check card
It is shown as using, reduce for the case where checking card.
Detailed description of the invention
Fig. 1 is the flow diagram of the method that outsourcing employee is verified based on recognition of face of one embodiment of the application;
Fig. 2 is the structural schematic block diagram of the device that outsourcing employee is verified based on recognition of face of one embodiment of the application;
Fig. 3 is the structural schematic block diagram of the device that outsourcing employee is verified based on recognition of face of one embodiment of the application;
Fig. 4 is the structural schematic block diagram of the device that outsourcing employee is verified based on recognition of face of one embodiment of the application;
Fig. 5 is the specific of the coupling subelement of the device that outsourcing employee is verified based on recognition of face of one embodiment of the application
Structural schematic block diagram;
Fig. 6 is the structural schematic block diagram of the device that outsourcing employee is verified based on recognition of face of one embodiment of the application;
Fig. 7 is the structural schematic block diagram of the device that outsourcing employee is verified based on recognition of face of one embodiment of the application;
Fig. 8 is the structural schematic block diagram of the computer equipment of one embodiment of the application.
The embodiments will be further described with reference to the accompanying drawings for realization, functional characteristics and the advantage of the application purpose.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Referring to Fig.1, the embodiment of the present application provides a kind of method based on recognition of face verifying outsourcing employee, comprising steps of
S1, acquisition be arranged in employee check card place camera acquisition enter workplace personnel the first facial information,
And obtain the illumination intensity value of current environment;
S2, first facial information is matched with each of Outsourced database the second facial information respectively,
Multiple matching values are obtained, using highest matching value as the first matching value, and in pair of preset intensity of illumination and matching value
It answers and searches the second matching value corresponding with the illumination intensity value in list as matching threshold;
S3, judge whether first matching value is lower than the matching threshold;
S4, if so, label first facial information is abnormal.
In the present embodiment, the employee place of checking card refers to that people enters the gate inhibition position of the process of workplace.The place of checking card is provided with
Camera, acquisition enter the first facial information of the personnel of workplace.After camera shoots photo, server obtains photo,
Acquire the first facial information for entering the personnel of workplace in photo.There are one optical sensors on the side of camera, use
In the intensity of illumination of detection current environment.Server gets the intensity of illumination of optical sensor detection, and it is strong to calculate generation illumination
Angle value.Illumination intensity value is used to embody the bright dark degree of light at the place that checks card.
Outsourced database is the database for being stored with outsourcing service provider's information, just includes each outsourcing in outsourcing service provider's information
The facial information of personnel, i.e. the second facial information.First facial information and the second facial information are matched, that is, calculate two
The similarity of facial information.Specifically, acquiring the characteristic point in two the first facial informations and the second facial information respectively, so
It is matched afterwards according to characteristic point, calculates the similarity of two characteristic points, obtain matching value.Face is obtained specifically, can be
The boundary characteristic of information, is then matched.Characteristic point refers to that the point of acute variation occurs for gray value of image or in image
The biggish point of curvature (intersection point at i.e. two edges), the gray-value variation of the image by calculating the first facial information on edge
Place greater than certain value is set as characteristic point.Image characteristic point has very heavy in the image matching algorithm based on characteristic point
The effect wanted.Image characteristic point is able to reflect image substantive characteristics, can be identified for that target object in image.Pass through of characteristic point
With the matching primitives that can complete image.By the fisrt feature point of the first facial information and the second feature of the second facial information
Point extracts respectively, is then compared fisrt feature point with second feature point, utilizes the method progress of characteristic matching
Match, obtain the quantity of interior point, interior point refers to the characteristic point for having one-to-one relationship in two images, and two images are more similar, interior
Point is more, and the matching value of corresponding generation is higher.It is often matched once with second facial information, obtains a matching value,
After matching, multiple matching values are obtained, choose the peak in multiple matching values, as the first matching value.In addition, light is got over
Good, the photo shot is apparent, and the first facial information of corresponding acquisition is more accurate.Outsourcing service provider in Outsourced database
The second facial information be gem-pure pictorial information, therefore, light is better, the first facial information of collection of server with
The environment for acquiring the second facial information is closer.Corresponding, the matching degree of the first facial information and the second facial information is higher.
Therefore, there is corresponding relationship between illumination intensity value and matching threshold.Staff according to debugging calculate illumination intensity value with
The corresponding relationship of matching threshold forms mapping table, and in the server by mapping table storage.Server calls should
Mapping table gets corresponding first matching threshold according to illumination intensity value, then judge above-mentioned first matching value with it is right
The size for the matching threshold answered.If above-mentioned first matching value is lower than matching threshold, and then determines first facial information exception,
First facial information is marked abnormal.In one embodiment, intensity of illumination and the mapping table of matching value are as follows:
Intensity of illumination | Matching value |
50-60 | 0.65 |
61-70 | 0.70 |
71-80 | 0.80 |
81-90 | 0.90 |
91-100 | 0.95 |
Wherein, above-mentioned illumination intensity value is the mapping table obtained using the optical sensor test of a certain brand, is used
The value of optical sensor detection is from 1-100, and numerical value is higher, indicates that intensity of illumination is better, i.e., light is better.With other illumination
Sensor detection may detect same intensity intensity of illumination and obtain different illumination intensity values, thus mapping table with it is upper
Table is different.The mapping table obtained with the test of other optical sensors is also within the scope of protection of this application.
In another embodiment, when illumination intensity value is less than default intensity of illumination threshold value, server issues warning
Signal reminds staff's current light intensity value too low, and the facial information of acquisition may be inaccurate, and staff is needed to improve
Employee checks card the light at place.In upper table, intensity of illumination threshold value is 50, and illumination intensity value is lower than 50, then server issues warning
Signal reminds staff's current light intensity value too low, or controls the lamp opening at the place that checks card or brightness is turned up.
In one embodiment, it is above-mentioned by first facial information respectively with the second face of each of Outsourced database
Portion's information is matched, and multiple matching values are obtained, using highest matching value as before the step of the first matching value, comprising:
S201, the positive face photo and side face photo for receiving each outsourcing service provider;
S202, extract respectively each described positive face take and side face picture in facial information, obtain each institute
State corresponding second facial information of positive face photo and corresponding second facial information of the side face photo;
S203, it will all second facial information store into preset Outsourced database.
In the present embodiment, when the second facial information of outsourcing service provider is stored in Outsourced database by staff, according to
The different angle of outsourcing service provider shoots multiple photos, includes at least a positive face photo and a side face photo, wherein side face
Photo includes positive side face photo and 45 degree of side face photos.Then multiple photos of each outsourcing service provider are uploaded onto the server
In, after server receives each photo that employee uploads, recognition of face is carried out, the facial information in each photo is extracted,
The frontal one information and side facial information of each outsourcing service provider is obtained, is the second facial information, then by whole
Second facial information is stored in preset Outsourced database.Outsourced database is arranged in the server, is convenient for server calls.
When entering workplace because of personnel, it may be possible to enter workplace from multiple directions, corresponding camera acquisition enters work
The first facial information of the personnel of occasion it could also be possible that acquire from different directions.Be conducive to more accurately identify into work
Whether the personnel for making occasion are outsourcing service providers.In one embodiment, Outsourced database is divided into two subdata bases,
In, the second facial information of a sub- database purchase male outsourcing service provider, another subdata base stores women outsourcing service provider
The second facial information, server automatically stores each second facial information to corresponding son according to preset Sexual discriminating model
In database.
In one embodiment, it is described by first facial information respectively with each of the Outsourced database
Two facial informations match respectively, obtain multiple matching values, will match the step of highest matching value is as first matching value
Include:
S21, first facial information is input to preset Sexual discriminating model, judges the gender class of the personnel
Type;
S22, the second facial information identical with the sex types of the personnel is searched in the Outsourced database;
S23, by first facial information respectively with the sex types phase with the personnel in the Outsourced database
The second same facial information is matched, and multiple matching values is obtained, using highest matching value as the first matching value.
The second facial information of each outsourcing service provider is contained in the present embodiment, in Outsourced database, but also to each second
Facial information can all have the essential informations such as the personal information, including gender, name, age, department for marking corresponding outsourcing service provider.
After server has got the first facial information, after the first facial information to be input to the Sexual discriminating model after training, calculate
The corresponding gender of first facial information out.Then according to the corresponding sex types of the first facial information, by Outsourced database with
Identical second facial information of the corresponding sex types of first facial information is found out, specifically, according to the second facial information institute
The gender information of the outsourcing service provider of category finds out.Then in matching, only the second facial information identical with sex types is carried out
Matching, in this way when being matched the first facial information with the second facial information in database, reduces matched number, mentions
Height calculates the speed of the first matching value.
In one embodiment, it is above-mentioned by first facial information respectively with the second face of each of Outsourced database
Portion's information is matched, and matching value is obtained, using highest matching value as before the step of the first matching value, comprising:
S204, multiple sample facial informations and the corresponding gender of sample facial information are input to neural network model
In, it is trained;
The parameter of S205, the output neural network model, obtain the Sexual discriminating model.
It,, will be multiple preparatory using neural network as basic model when being trained to Sexual discriminating model in the present embodiment
The sample facial information of acquisition is input in neural network, and the result to the gender of sample facial information as output.Specifically
, first the sample facial information of whole males can be input in neural network, output result is entirely male.Then will
The sample facial information of whole women is input in neural network, and the result of output is entirely women.So training.Nerve net
The sample facial information of sample facial information and women of the network model based on male, respectively obtains the parameter and women of male
Parameter, the corresponding Sexual discriminating model obtained based on neural network model.
In one embodiment, it is above-mentioned by first facial information respectively in the Outsourced database with the people
Identical second facial information of sex types of member is matched, and multiple matching values is obtained, using highest matching value as first
The step S23 of matching value, comprising:
S231, by first facial information respectively with the sex types phase with the personnel in the Outsourced database
The second same facial information matches respectively, obtains multiple matching values;
S232, it is worth highest in the multiple matching value multiplied by the corresponding default sex coefficient of the sex types, obtains
To first matching value.
In the present embodiment, after having got the sex types of personnel, according to the corresponding relationship of sex types and sex coefficient,
The corresponding sex coefficient of the personnel is got, in one embodiment, sex types include male and female, and male is corresponding
Sex coefficient is 0.95, and the corresponding sex coefficient of women is 0.90.Then server is by the first facial information and Outsourced database
In each second facial information match respectively, obtain multiple matching values, multiple obtained values of matching be compared, are calculated most
High matching value;Then by highest matching value multiplied by sex coefficient, if it is male then by highest value multiplied by 0.95, if
It is women then by highest value multiplied by 0.90, retains two decimals after decimal point, obtain the first final matching value.According to gender class
Corresponding sex coefficient is arranged in type, is more conducive to obtaining stable and accurate first matching value.Because working in workplace, workplace is to institute
The appearance instrument of someone has certain requirement, and the requirement to women is some more, for example requires women at least with light makeup, such female
Property outsourcing service provider enter workplace when, compare male with the photo gap for the second facial information being pre-stored in Outsourced database
For property outsourcing service provider, gap is larger.Therefore, setting sex types corresponding sex coefficients calculates the first matching value,
Whether the personnel that more accurately and effectively identification enters workplace are outsourcing service providers in Outsourced database.
In one embodiment, after the step S6 of above-mentioned label the first facial information exception, comprising:
S5, first facial information is loaded on the display screen that employee checks card place.
In the present embodiment, when determining that the first facial information is abnormal, illustrate that the corresponding employee of the first facial information is not outsourcing
Employee, it is more likely that be that outsourcing employee allows other people help to check card, it is therefore necessary to be disciplined as a warning or be warned.It is abnormal by being marked
First facial information is shown on the display screen at the place that checks card, and carries out publicity, is played a warning role, is avoided to for the behavior that people checks card
Occurs the case where checking card for people again.
In one embodiment, above-mentioned acquisition be arranged in employee check card place camera acquisition carry out workplace personnel
The first facial information step S1 before, comprising:
S101, obtain employee check card place range sensor detection range sensor in front of object distance value;
S102, judge whether the distance value is less than preset distance threshold;
S103, if so, generate acquisition the first facial information instruction.
In the present embodiment, the employee place of checking card is additionally provided with range sensor, the distance of the object for detecting front.The person of working as
Work goes to employee and checks card place, and range sensor detects the distance value with the employee in front, and the distance value is less than apart from threshold at this time
Value determines that there is employee at the employee place of checking card;When the employee place of checking card does not have employee, range sensor detect with preceding object away from
From distance threshold is greater than, determine that the no employee's distance threshold in the employee place of checking card is staff and checks card the specific position at place according to employee
Set the distance threshold of scene setting.After range sensor detects the distance value with objects in front, it is sent to server, server
Distance value is got, the distance threshold uploaded with backstage personnel is compared, see whether distance value is less than distance threshold, if away from
From value be less than distance threshold, then determine that there is employee at the employee place of checking card, need to judge the employee whether be the workplace outsourcing
Therefore employee generates the instruction of the first facial information of acquisition, convenient for the first facial information of subsequent acquisition to carry out judging the employee
Whether be the workplace outsourcing employee.
In conclusion the method based on recognition of face verifying outsourcing employee of the application, acquires at the employee place of checking card and enters
The first facial information of the personnel of workplace, and judge whether the personnel of admission have according to the intensity of illumination at the place of checking card
The outsourcing service provider of typing information effectively avoids other people that outsourcing service provider is replaced check card entering workplace and causing company
The risk of information leakage.Before carrying out recognition of face, first judgement enters the gender of the personnel of workplace, carries out in the database
It will only be matched with consistent second facial information of above-mentioned gender when matching, and reduce matched number, accelerate matched speed.When
When it fails to match, by the load of the first facial information on the display screen for checking card place, plays a warning role, subtract to for the personnel to check card
It is small to replace the case where checking card.
Referring to Fig. 2, a kind of device based on recognition of face verifying outsourcing employee is also provided in the embodiment of the present application, comprising:
Obtain module 1, for obtains be arranged in employee check card place camera acquisition into workplace personnel the
One facial information, and obtain the illumination intensity value of current environment;
Matching module 2, for believing first facial information with each of Outsourced database the second face respectively
Breath matched, obtain multiple matching values, using highest matching value as the first matching value, and preset intensity of illumination with
The second matching value corresponding with the illumination intensity value is searched in the corresponding lists of matching value as matching threshold;
First judgment module 3, for judging whether first matching value is lower than the matching threshold;
Mark module 4 marks first facial information different if being lower than the matching threshold for first matching value
Often.
In the present embodiment, the employee place of checking card refers to that people enters the gate inhibition position of the process of workplace.The place of checking card is provided with
Camera, acquisition enter the first facial information of the personnel of workplace.After camera shoots photo, obtains module 1 and obtain and shine
Piece acquires the first facial information for entering the personnel of workplace in photo.The side of camera there are one optical sensor,
For detecting the intensity of illumination of current environment.The intensity of illumination that module 1 gets optical sensor detection is obtained, calculates and generates light
According to intensity value.Illumination intensity value is used to embody the bright dark degree of light at the place that checks card.
Outsourced database is the database for being stored with outsourcing service provider's information, just includes each outsourcing in outsourcing service provider's information
The facial information of personnel, i.e. the second facial information.Matching module 2 matches the first facial information and the second facial information,
Calculate the similarity of two facial informations.Specifically, acquiring in two the first facial informations and the second facial information respectively
Characteristic point, then matched according to characteristic point, calculate the similarity of two characteristic points, obtain matching value.Specifically, can be with
It is the boundary characteristic for obtaining facial information, is then matched.Characteristic point refers to that the point of acute variation occurs for gray value of image
Or on the image border biggish point of curvature (intersection point at i.e. two edges), by the image for calculating the first facial information
The place that gray-value variation is greater than certain value is set as characteristic point.Image characteristic point is in the image matching algorithm based on characteristic point
There is highly important effect.Image characteristic point is able to reflect image substantive characteristics, can be identified for that target object in image.Pass through
The matching of characteristic point can complete the matching primitives of image.By the fisrt feature point of the first facial information and the second facial information
Second feature point extract respectively, fisrt feature point is compared with second feature point then, utilizes characteristic matching
Method is matched, and the quantity of interior point is obtained, and interior point refers to the characteristic point for having one-to-one relationship in two images, two images
More similar, interior point is more, and the matching value of corresponding generation is higher.It is often matched once with second facial information, obtains one
Matching value after matching, obtains multiple matching values, chooses the peak in multiple matching values, as the first matching value.Separately
Outside, light is better, and the photo shot is apparent, and the first facial information of corresponding acquisition is more accurate.In Outsourced database
The second facial information of outsourcing service provider be gem-pure pictorial information, therefore, light is better, the first of collection of server
The environment of facial information and the second facial information of acquisition is closer.It is corresponding, of the first facial information and the second facial information
It is higher with spending.Therefore, there is corresponding relationship between illumination intensity value and matching threshold.Staff calculates light according to debugging
According to the corresponding relationship of intensity value and matching threshold, mapping table is formed, and in the server by mapping table storage.?
The mapping table is called with module 2, corresponding first matching threshold is got according to illumination intensity value, then first judges mould
Block 3 judges the size of above-mentioned first matching value and corresponding matching threshold.If above-mentioned first matching value is lower than matching threshold, into
And determining first facial information exception, mark module 4 marks first facial information abnormal.In one embodiment,
Intensity of illumination and the mapping table of matching value are as follows:
Intensity of illumination | Matching value |
50-60 | 0.65 |
61-70 | 0.70 |
71-80 | 0.80 |
81-90 | 0.90 |
91-100 | 0.95 |
Wherein, above-mentioned illumination intensity value is the mapping table obtained using the optical sensor test of a certain brand, is used
The value of optical sensor detection is from 1-100, and numerical value is higher, indicates that intensity of illumination is better, i.e., light is better.With other illumination
Sensor detection may detect same intensity intensity of illumination and obtain different illumination intensity values, thus mapping table with it is upper
Table is different.The mapping table obtained with the test of other optical sensors is also within the scope of protection of this application.
In another embodiment, when illumination intensity value is less than default intensity of illumination threshold value, server issues warning
Signal reminds staff's current light intensity value too low, and the facial information of acquisition may be inaccurate, and staff is needed to improve
Employee checks card the light at place.In upper table, intensity of illumination threshold value is 50, and illumination intensity value is lower than 50, then server issues warning
Signal reminds staff's current light intensity value too low, or controls the lamp opening at the place that checks card or brightness is turned up.
Referring to Fig. 3, in one embodiment, the above-mentioned device based on recognition of face verifying outsourcing employee further include:
Receiving module 201, for receiving the positive face photo and side face photo of each outsourcing service provider;
Extraction module 202, for extract respectively each described positive face take and side face picture in facial information, obtain
To corresponding second facial information of positive face photo described in each and corresponding second facial information of the side face photo
Memory module 203, for will all second facial information store into preset Outsourced database.
In the present embodiment, when the second facial information of outsourcing service provider is stored in Outsourced database by staff, according to
The different angle of outsourcing service provider shoots multiple photos, includes at least a positive face photo and a side face photo, wherein side face
Photo includes positive side face photo and 45 degree of side face photos.Then multiple photos of each outsourcing service provider are uploaded onto the server
In, after receiving module 201 receives each photo that employee uploads, recognition of face is carried out, extraction module 202 extracts each photograph
Facial information in piece obtains the frontal one information and side facial information of each outsourcing service provider, is the second face letter
Breath, then the second whole facial informations is stored in preset Outsourced database by memory module 203.Outsourced database setting
In the server, it is convenient for server calls.When entering workplace because of personnel, it may be possible to enter workplace from multiple directions,
The first facial information of the personnel into workplace of corresponding camera acquisition it could also be possible that acquire from different directions.
Be conducive to more accurately identify whether the personnel into workplace are outsourcing service providers.In one embodiment, by outsourcing
Database is divided into two subdata bases, wherein the second facial information of a sub- database purchase male outsourcing service provider, another
Subdata base stores the second facial information of women outsourcing service provider, and server is according to preset Sexual discriminating model automatically by each the
Two facial informations are stored into corresponding subdata base.
Referring to Fig. 4, in one embodiment, above-mentioned matching module 2 includes:
Input unit 21 is judged described for first facial information to be input to preset Sexual discriminating model
The sex types of personnel;
Searching unit 22, for searching the second face identical with the sex types of the personnel in the Outsourced database
Portion's information;
Matching unit 23, for by first facial information respectively in the Outsourced database with the personnel's
Identical second facial information of sex types is matched, and multiple matching values are obtained, using highest matching value as the first matching
Value.
The second facial information of each outsourcing service provider is contained in the present embodiment, in Outsourced database, but also to each second
Facial information can all have the essential informations such as the personal information, including gender, name, age, department for marking corresponding outsourcing service provider.
After server has got the first facial information, the first facial information is input to the Sexual discriminating mould after training by input unit 21
After type, the corresponding gender of the first facial information is calculated.Then searching unit 22 is according to the corresponding gender class of the first facial information
Type finds out identical second facial information of sex types corresponding with the first facial information in Outsourced database, specifically,
It is found out according to the gender information of outsourcing service provider belonging to the second facial information.Then matching unit 23 matching when only and property
Identical second facial information of other type is matched, in this way by the second facial information in the first facial information and database
When being matched, reduce matched number, improves the speed for calculating the first matching value.
In one embodiment, the above-mentioned device based on recognition of face verifying outsourcing employee further include:
Training module 204, for multiple sample facial informations and the corresponding gender of sample facial information to be input to mind
Through being trained in network model;
Module 205 is obtained, for exporting the parameter of the neural network model, obtains the Sexual discriminating model.
In the present embodiment, training module 204 is when being trained Sexual discriminating model, with neural network for basic mould
Multiple sample facial informations gathered in advance are input in neural network by type, and to the gender of sample facial information as defeated
Result out.Specifically, first the sample facial information of whole males can be input in neural network, output result is whole
It is male.Then the sample facial information of whole women is input in neural network, the result of output is entirely women.Such as
This training.The sample facial information of sample facial information and women of the neural network model based on male, obtains module 205 and divides
The parameter of male and the parameter of women, the corresponding Sexual discriminating model obtained based on neural network model are not obtained.
Referring to Fig. 5, in one embodiment, above-mentioned matching unit 23 includes:
Coupling subelement 231, for by first facial information respectively in the Outsourced database with the people
Identical second facial information of sex types of member matches respectively, obtains multiple matching values;
Computation subunit 232, for value highest in the multiple matching value is corresponding pre- multiplied by the sex types
If sex coefficient, first matching value is obtained.
In the present embodiment, after having got the sex types of personnel, according to the corresponding relationship of sex types and sex coefficient,
The corresponding sex coefficient of the personnel is got, in one embodiment, sex types include male and female, and male is corresponding
Sex coefficient is 0.95, and the corresponding sex coefficient of women is 0.90.Then coupling subelement 231 is by the first facial information and outsourcing
Each second facial information in database matches respectively, obtains multiple matching values, and multiple obtained values that match are compared, are counted
Calculate highest matching value;Then computation subunit 232 by highest matching value multiplied by sex coefficient, then will most if it is male
High value if it is women then by highest value multiplied by 0.90, retains two decimals after decimal point multiplied by 0.95, obtains final the
One matching value.Corresponding sex coefficient is set according to sex types, is more conducive to obtaining stable and accurate first matching value.Cause
It works in workplace, there is certain requirement in workplace to proprietary appearance instrument, and the requirement to women is some more, for example requires female
Property it is at least with light makeup, such women outsourcing service provider enter workplace when, with the second face being pre-stored in Outsourced database
The photo gap of information is compared for male outsourcing service provider, and gap is larger.Therefore, the corresponding gender system of setting sex types
For number to calculate the first matching value, whether the personnel that more accurately and effectively identification enters workplace are outer in Outsourced database
Packet personnel.
Referring to Fig. 6, in one embodiment, the above-mentioned device based on recognition of face verifying outsourcing employee further include:
Loading module 5, for first facial information load to be checked card the display screen at place in employee.
In the present embodiment, when determining that the first facial information is abnormal, illustrate that the corresponding employee of the first facial information is not outsourcing
Employee, it is more likely that be that outsourcing employee allows other people help to check card, it is therefore necessary to be disciplined as a warning or be warned.Loading module 5 will be marked
Remember that the first abnormal facial information is shown on the display screen at the place that checks card, carried out publicity, has played police to for the behavior that people checks card
It is shown as using, avoids occurring the case where checking card for people again.
Referring to Fig. 7, in one embodiment, the above-mentioned device based on recognition of face verifying outsourcing employee further include:
Spacing module 101, for obtain employee check card place range sensor detection range sensor in front of object
Distance value;
Second judgment module 102, for judging whether the distance value is less than preset distance threshold;
Generation module 103 generates the first facial information of acquisition if being less than preset distance threshold for the distance value
Instruction.
In the present embodiment, in the present embodiment, the employee place of checking card is additionally provided with range sensor, for detecting the object in front
Distance.It checks card place when employee goes to employee, range sensor detects the distance value with the employee in front, at this time the distance value
Less than distance threshold, determine that there is employee at the employee place of checking card;When the employee place of checking card does not have employee, range sensor is detected with before
The distance of square obstacle is greater than distance threshold, determines that the no employee's distance threshold in the employee place of checking card is that staff checks card according to employee
The distance threshold of the specific location scene setting at place.After range sensor detects the distance value with objects in front, be sent to away from
From module 101, spacing module 101 gets distance value, the second judgment module 102 by the distance value and backstage personnel upload away from
It is compared from threshold value, sees whether distance value is less than distance threshold, if distance value is less than distance threshold, determine that employee checks card
There is employee at place, need to judge the employee whether be the workplace outsourcing employee, therefore, generation module 103 generates acquisition the
The instruction of one facial information, convenient for the first facial information of subsequent acquisition judge whether the employee is the outer of the workplace
Wrap employee.
In conclusion the device based on recognition of face verifying outsourcing employee of the application, acquires at the employee place of checking card and enters
The first facial information of the personnel of workplace, and judge whether the personnel of admission have according to the intensity of illumination at the place of checking card
The outsourcing service provider of typing information effectively avoids other people that outsourcing service provider is replaced check card entering workplace and causing company
The risk of information leakage.Before carrying out recognition of face, first judgement enters the gender of the personnel of workplace, carries out in the database
It will only be matched with consistent second facial information of above-mentioned gender when matching, and reduce matched number, accelerate matched speed.When
When it fails to match, by the load of the first facial information on the display screen for checking card place, plays a warning role, subtract to for the personnel to check card
It is small to replace the case where checking card.
Referring to Fig. 8, a kind of computer equipment is also provided in the embodiment of the present application, which can be server,
Its internal structure can be as shown in Figure 8.The computer equipment includes processor, the memory, network connected by system bus
Interface and database.Wherein, the processor of the Computer Design is for providing calculating and control ability.The computer equipment is deposited
Reservoir includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program
And database.The internal memory provides environment for the operation of operating system and computer program in non-volatile memory medium.It should
The database of computer equipment is for storing the data such as the second facial information, the first matching threshold.The network of the computer equipment
Interface is used to communicate with external terminal by network connection.To realize that one kind is based on when the computer program is executed by processor
The method of recognition of face verifying outsourcing employee.
Above-mentioned processor executes the step of above-mentioned method based on recognition of face verifying outsourcing employee: obtaining and is arranged in employee
Check card place camera acquisition enter workplace personnel the first facial information, and obtain current environment intensity of illumination
Value;First facial information is matched with each of Outsourced database the second facial information respectively, is obtained multiple
Matching value, using highest matching value as the first matching value, and in preset intensity of illumination and the corresponding lists of matching value
The second matching value corresponding with the illumination intensity value is searched as matching threshold;Judge whether first matching value is lower than institute
State matching threshold;If so, label first facial information is abnormal.
In one embodiment, above-mentioned processor execute by first facial information respectively with it is every in Outsourced database
One the second facial information is matched, and multiple matching values are obtained, using highest matching value as the step of the first matching value it
Before, comprising: receive the positive face photo and side face photo of each outsourcing service provider;Extract respectively each described positive face shine with
And the facial information in side face photo, it obtains each positive corresponding second facial information of face photo and the side face is shone
Corresponding second facial information of piece;It will all second facial information store into preset Outsourced database.
In one embodiment, above-mentioned processor is executed first facial information respectively and in the Outsourced database
Each second facial information matched, multiple matching values are obtained, using highest matching value as the step of the first matching value
Suddenly include: that first facial information is input to preset Sexual discriminating model, judge the sex types of the personnel;?
The second facial information identical with the sex types of the personnel is searched in the Outsourced database;By first facial information
It matches, obtains more with the second facial information identical with the sex types of the personnel in the Outsourced database respectively
A matching value, using highest matching value as the first matching value.
In one embodiment, above-mentioned processor execute by first facial information respectively with it is every in Outsourced database
One the second facial information is matched, and multiple matching values are obtained, using highest matching value as the step of the first matching value it
Before, comprising: multiple sample facial informations and the corresponding gender of sample facial information are input in neural network model, are carried out
Training;The parameter for exporting the neural network model obtains the Sexual discriminating model.
In one embodiment, above-mentioned processor is executed first facial information respectively and in the Outsourced database
The second facial information identical with the sex types of the personnel match, multiple matching values are obtained, by highest matching
The step of value is as the first matching value, comprising: by first facial information respectively in the Outsourced database with it is described
Identical second facial information of the sex types of personnel matches respectively, obtains multiple matching values;By in the multiple matching value most
High value obtains first matching value multiplied by the corresponding default sex coefficient of the sex types.
In one embodiment, after the step of above-mentioned processor execution label the first facial information exception, comprising:
By first facial information load on the display screen that employee checks card place.
In one embodiment, the camera acquisition that the employee place of checking card is arranged in above-mentioned processor execution acquisition works
Before the step of the first facial information of the personnel of occasion, comprising: obtain employee check card place range sensor detection distance
The distance value of object in front of sensor;Judge whether the distance value is less than preset distance threshold;If so, generating acquisition the
The instruction of one facial information.
In conclusion the computer equipment of the application, at the employee place of checking card, acquisition enters the first of the personnel of workplace
Facial information, and judge whether the personnel of admission are the outsourcing service providers with typing information according to the intensity of illumination at the place of checking card,
Effectively avoid other people that outsourcing service provider is replaced check card and to enter workplace and cause the risk of company's information leakage.Into
Before row recognition of face, first judgement enters the gender of the personnel of workplace, only will be with above-mentioned property when being matched in the database
Not consistent second facial information matching, reduces matched number, accelerates matched speed.When it fails to match, by first
Facial information loads on the display screen for checking card place, plays a warning role to for the personnel to check card, reduces for the case where checking card.
It will be understood by those skilled in the art that structure shown in Fig. 8, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme.
One embodiment of the application also provides a kind of computer readable storage medium, is stored thereon with computer program, calculates
Machine program realizes a kind of method based on recognition of face verifying outsourcing employee when being executed by processor, specifically: it obtains setting and exists
Employee check card place camera acquisition enter workplace personnel the first facial information, and obtain current environment illumination
Intensity value;First facial information is matched with each of Outsourced database the second facial information respectively, is obtained
Multiple matching values, using highest matching value as the first matching value, and in the respective column of preset intensity of illumination and matching value
The second matching value corresponding with the illumination intensity value is searched in table as matching threshold;Judge whether first matching value is low
In the matching threshold;If so, label first facial information is abnormal.
In one embodiment, above-mentioned processor execute by first facial information respectively with it is every in Outsourced database
One the second facial information is matched, and multiple matching values are obtained, using highest matching value as the step of the first matching value it
Before, comprising: receive the positive face photo and side face photo of each outsourcing service provider;Extract respectively each described positive face shine with
And the facial information in side face photo, it obtains each positive corresponding second facial information of face photo and the side face is shone
Corresponding second facial information of piece;It will all second facial information store into preset Outsourced database.
In one embodiment, above-mentioned processor is executed first facial information respectively and in the Outsourced database
Each second facial information matched, multiple matching values are obtained, using highest matching value as the step of the first matching value
Suddenly include: that first facial information is input to preset Sexual discriminating model, judge the sex types of the personnel;?
The second facial information identical with the sex types of the personnel is searched in the Outsourced database;By first facial information
It matches, obtains more with the second facial information identical with the sex types of the personnel in the Outsourced database respectively
A matching value, using highest matching value as the first matching value.
In one embodiment, above-mentioned processor execute by first facial information respectively with it is every in Outsourced database
One the second facial information is matched, and multiple matching values are obtained, using highest matching value as the step of the first matching value it
Before, comprising: multiple sample facial informations and the corresponding gender of sample facial information are input in neural network model, are carried out
Training;The parameter for exporting the neural network model obtains the Sexual discriminating model.
In one embodiment, above-mentioned processor is executed first facial information respectively and in the Outsourced database
The second facial information identical with the sex types of the personnel match, multiple matching values are obtained, by highest matching
The step of value is as the first matching value, comprising: by first facial information respectively in the Outsourced database with it is described
Identical second facial information of the sex types of personnel matches respectively, obtains multiple matching values;By in the multiple matching value most
High value obtains first matching value multiplied by the corresponding default sex coefficient of the sex types.
In one embodiment, after the step of above-mentioned processor execution label the first facial information exception, comprising:
By first facial information load on the display screen that employee checks card place.
In one embodiment, the camera acquisition that the employee place of checking card is arranged in above-mentioned processor execution acquisition works
Before the step of the first facial information of the personnel of occasion, comprising: obtain employee check card place range sensor detection distance
The distance value of object in front of sensor;Judge whether the distance value is less than preset distance threshold;If so, generating acquisition the
The instruction of one facial information.
In conclusion the computer readable storage medium of the application, at the employee place of checking card, acquisition enters the people of workplace
The first facial information of member, and judge according to the intensity of illumination at the place of checking card whether the personnel of admission are have typing information outer
Packet personnel effectively avoid other people that outsourcing service provider is replaced check card and to enter workplace and cause the wind of company's information leakage
Danger.Before carrying out recognition of face, first judgement enters the gender of the personnel of workplace, only will be with when being matched in the database
The above-mentioned consistent second facial information matching of gender, reduces matched number, accelerates matched speed.When it fails to match,
It by the load of the first facial information on the display screen for checking card place, is played a warning role to for the personnel to check card, reduces to check card
Situation.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
Any reference used in provided herein and embodiment to memory, storage, database or other media,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double speed are according to rate SDRAM (SSRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, device, article or the method that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, device, article or method institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, device of element, article or method.
The foregoing is merely preferred embodiment of the present application, are not intended to limit the scope of the patents of the application, all utilizations
Equivalent structure or equivalent flow shift made by present specification and accompanying drawing content is applied directly or indirectly in other correlations
Technical field, similarly include in the scope of patent protection of the application.
Claims (10)
1. a kind of method based on recognition of face verifying outsourcing employee characterized by comprising
Obtain be arranged in employee check card place camera acquisition enter workplace personnel the first facial information, and obtain
The illumination intensity value of current environment;
First facial information is matched with each of Outsourced database the second facial information respectively, is obtained multiple
Matching value, using highest matching value as the first matching value, and in preset intensity of illumination and the corresponding lists of matching value
The second matching value corresponding with the illumination intensity value is searched as matching threshold;
Judge whether first matching value is lower than the matching threshold;
If so, label first facial information is abnormal.
2. the method as described in claim 1 based on recognition of face verifying outsourcing employee, which is characterized in that described by described the
One facial information is matched with each of Outsourced database the second facial information respectively, obtains multiple matching values, will most
Before the step of high matching value is as the first matching value, comprising:
Receive the positive face photo and side face photo of each outsourcing service provider;
Extract respectively each described positive face take and side face picture in facial information, obtain each described positive face photo
Corresponding second facial information and corresponding second facial information of the side face photo;
It will all second facial information store into preset Outsourced database.
3. the method as described in claim 1 based on recognition of face verifying outsourcing employee, which is characterized in that described by described the
One facial information is matched with each of the Outsourced database the second facial information respectively, obtains multiple matching values,
Include: using highest matching value as the step of the first matching value
First facial information is input to preset Sexual discriminating model, judges the sex types of the personnel;
The second facial information identical with the sex types of the personnel is searched in the Outsourced database;
By first facial information respectively with identical with the sex types of the personnel second in the Outsourced database
Facial information is matched, and multiple matching values are obtained, using highest matching value as the first matching value.
4. the method as claimed in claim 3 based on recognition of face verifying outsourcing employee, which is characterized in that described by described the
One facial information is matched with each of Outsourced database the second facial information respectively, obtains multiple matching values, will most
Before the step of high matching value is as the first matching value, comprising:
Multiple sample facial informations and the corresponding gender of sample facial information are input in neural network model, are instructed
Practice;
The parameter for exporting the neural network model obtains the Sexual discriminating model.
5. the method as claimed in claim 3 based on recognition of face verifying outsourcing employee, which is characterized in that described by described the
One facial information is carried out with the second facial information identical with the sex types of the personnel in the Outsourced database respectively
Matching, obtains multiple matching values, using highest matching value as the step of the first matching value, comprising:
By first facial information respectively with identical with the sex types of the personnel second in the Outsourced database
Facial information matches respectively, obtains multiple matching values;
By value highest in the multiple matching value multiplied by the corresponding default sex coefficient of the sex types, described first is obtained
Matching value.
6. the method as described in claim 1 based on recognition of face verifying outsourcing employee, which is characterized in that described in the label
After the step of first facial information exception, comprising:
By first facial information load on the display screen that employee checks card place.
7. the method as described in claim 1 based on recognition of face verifying outsourcing employee, which is characterized in that the acquisition setting
Before the step of employee checks card the first facial information of the personnel of the camera acquisition progress workplace at place, comprising:
Obtain employee check card place range sensor detection range sensor in front of object distance value;
Judge whether the distance value is less than preset distance threshold;
If so, generating the instruction of the first facial information of acquisition.
8. a kind of device based on recognition of face verifying outsourcing employee characterized by comprising
Obtain module, for obtains be arranged in employee check card place camera acquisition into workplace personnel the first face
Information, and obtain the illumination intensity value of current environment;
Matching module, for carrying out first facial information with each of Outsourced database the second facial information respectively
Matching, obtains multiple matching values, using highest matching value as the first matching value, and in preset intensity of illumination and matching value
Corresponding lists in search corresponding with the illumination intensity value the second matching value as matching threshold;
First judgment module, for judging whether first matching value is lower than the matching threshold;
Mark module marks first facial information abnormal if being lower than the matching threshold for first matching value.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811340836.0A CN109583326A (en) | 2018-11-12 | 2018-11-12 | Method, apparatus and computer equipment based on recognition of face verifying outsourcing employee |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811340836.0A CN109583326A (en) | 2018-11-12 | 2018-11-12 | Method, apparatus and computer equipment based on recognition of face verifying outsourcing employee |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109583326A true CN109583326A (en) | 2019-04-05 |
Family
ID=65922067
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811340836.0A Pending CN109583326A (en) | 2018-11-12 | 2018-11-12 | Method, apparatus and computer equipment based on recognition of face verifying outsourcing employee |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109583326A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110705354A (en) * | 2019-08-29 | 2020-01-17 | 万翼科技有限公司 | Early warning method and related device |
CN112785785A (en) * | 2019-11-11 | 2021-05-11 | 阿里巴巴集团控股有限公司 | Attendance management system, method, related device and equipment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103136533A (en) * | 2011-11-28 | 2013-06-05 | 汉王科技股份有限公司 | Face recognition method and device based on dynamic threshold value |
CN103902961A (en) * | 2012-12-28 | 2014-07-02 | 汉王科技股份有限公司 | Face recognition method and device |
CN106022317A (en) * | 2016-06-27 | 2016-10-12 | 北京小米移动软件有限公司 | Face identification method and apparatus |
-
2018
- 2018-11-12 CN CN201811340836.0A patent/CN109583326A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103136533A (en) * | 2011-11-28 | 2013-06-05 | 汉王科技股份有限公司 | Face recognition method and device based on dynamic threshold value |
CN103902961A (en) * | 2012-12-28 | 2014-07-02 | 汉王科技股份有限公司 | Face recognition method and device |
CN106022317A (en) * | 2016-06-27 | 2016-10-12 | 北京小米移动软件有限公司 | Face identification method and apparatus |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110705354A (en) * | 2019-08-29 | 2020-01-17 | 万翼科技有限公司 | Early warning method and related device |
CN112785785A (en) * | 2019-11-11 | 2021-05-11 | 阿里巴巴集团控股有限公司 | Attendance management system, method, related device and equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CA2782071C (en) | Liveness detection | |
JP4241763B2 (en) | Person recognition apparatus and method | |
CN110334570B (en) | Face recognition automatic library building method, device, equipment and storage medium | |
KR101546137B1 (en) | Person recognizing device and method | |
CN112418009B (en) | Image quality detection method, terminal equipment and storage medium | |
CN106991395A (en) | Information processing method, device and electronic equipment | |
US11989975B2 (en) | Iris authentication device, iris authentication method, and recording medium | |
JP7151875B2 (en) | Image processing device, image processing method, and program | |
US20190026543A1 (en) | Person identification device | |
CN110660078B (en) | Object tracking method, device, computer equipment and storage medium | |
CN111144372A (en) | Vehicle detection method, device, computer equipment and storage medium | |
CN112784740B (en) | Gait data acquisition and labeling method and application | |
CN109583326A (en) | Method, apparatus and computer equipment based on recognition of face verifying outsourcing employee | |
KR20070105074A (en) | Method of managing image in a mobile communication terminal | |
JP2017525060A (en) | ID information for identifying animals | |
KR20180085505A (en) | System for learning based real time guidance through face recognition and the method thereof | |
JP7364187B2 (en) | Accounting audit support device, accounting audit support method, and accounting audit support program | |
CN112836041B (en) | Personnel relationship analysis method, device, equipment and storage medium | |
TW202125323A (en) | Processing method of learning face recognition by artificial intelligence module | |
CN112926616A (en) | Image matching method and device, electronic equipment and computer-readable storage medium | |
CN111783786A (en) | Picture identification method and system, electronic equipment and storage medium | |
TW201804368A (en) | Face recognition method | |
Di Martino et al. | Face matching with an a contrario false detection control | |
JP6975882B2 (en) | Collation device and collation result display method | |
US20210117653A1 (en) | Imaging device and smart identification method |
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 |