Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, so as to provide a thorough understanding of the present application embodiment.However, it will be clear to one skilled in the art that there is no these specific
The application also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, so as not to obscure the description of the present application with unnecessary details.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " instruction is described special
Sign, entirety, step, operation, the presence of element and/or component, but be not precluded one or more of the other feature, entirety, step,
Operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this present specification merely for the sake of description specific embodiment
And be not intended to limit the application.As present specification and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in present specification and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
As used in this specification and in the appended claims, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determination " or " in response to detecting ".Similarly, phrase " if it is determined that " or
" if detecting [described condition or event] " can be interpreted to mean according to context " once it is determined that " or " in response to true
It is fixed " or " once detecting [described condition or event] " or " in response to detecting [described condition or event] ".
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
Fig. 1 is the implementation process schematic diagram for the face identification method that one embodiment of the invention provides, for ease of description, only
Show part related to the embodiment of the present invention.The executing subject of the embodiment of the present invention can be terminal device.Such as Fig. 1 institute
Show, this method may comprise steps of:
Step S101: the first user information set of several first users to be identified, the first user information set packet are obtained
The User Identity, the first photo and the second photo of the several first users to be identified are included, wherein the first photo is to be taken on site
The several first users to be identified human face photo, the second photo be taken on site the several first users to be identified identity card
Photo.
In embodiments of the present invention, User Identity can be the identification card number of the first user to be identified, be also possible to
Other identity that can uniquely distinguish the first user to be identified.First photo and the second photo can be field personnel's bat
The photo taken the photograph is also possible to the photo that the first user to be identified is shot by self-service device.First photo be taken on site can
See the clear pictures of the face of the first user to be identified clearly;Second photo be taken on site see the first user to be identified clearly
The clear pictures of photo on identity card.
First user information set can also include name, phone number, organization, application class of service, etc. information.
Step S102: the credit record of the several first users to be identified is obtained according to User Identity, and according to credit
Record determines the credit value of several first users to be identified.
In embodiments of the present invention, terminal device can be looked into according to the User Identity of each first user to be identified
Peripheral canalization is ask, the credit record of each first user to be identified is obtained.Peripheral canalization can be the large system of peace, letter
The system of examining one or more of buys the system of proposing.Credit record may include this transaction generic, the gold of this transaction
Volume, this information such as overdue non-repayment amount of trading.
Credit value be used to measure the first user to be identified credit rating height, can be determined according to credit record first to
Identify the credit value of user.
Step S103: from the several first users to be identified, filtering out corresponding credit value is more than default prestige threshold value
Several second users to be identified.
In embodiments of the present invention, the first user to be identified that credit value is more than default prestige threshold value is known as second wait know
Other user, the second user to be identified are the preferable users of credit rating.
In financial industry, the lending and borrowing business of the user application poor for some credit ratings will not generally be given and pass through, institute
Recognition of face is carried out again carrying out authentication, user's rejected in advance that can be poor by these credit ratings is reduced may not need
The workload of recognition of face later, improves efficiency.
Default prestige threshold value can be configured according to actual needs.Illustratively, without the user of bad credit record
Credit value be 1, the poorer user's credit value of credit rating is lower, and default prestige threshold value can be set to 0.6, from several first to
It identifies in user, filters out the several second users to be identified that corresponding credit value is more than 0.6.
Step S104: obtaining the third photo of each second user to be identified, and wherein third photo is each second wait know
Photo on the identity card of other user saved in public security system.
In embodiments of the present invention, terminal device obtains each second use to be identified by identity information interface ID5 batch
The third photo at family, if the third photo of this some the second user to be identified obtains failure, by the task of acquisition failure
Failed tasks pond is added, when obtaining third photo by identity information interface ID5 batch next time, by appointing in failed tasks pond
Business is added in this batch acquisition task, until the obtaining failure of the task reacquires to obtain third photo.
Step S105: the first photo, the second photo, third photo of each second user to be identified are compared, obtained
To the face recognition result of each second user to be identified.
In embodiments of the present invention, it by comparing three photos of each second user to be identified, obtains each
The face recognition result of user to be identified.
Batch of the embodiment of the present invention obtains the user information of user to be identified, screening in advance obtain credit record it is good to
Identify user, the poor user to be identified of removal credit record, the workload of the recognition of face after reducing improves recognition of face
Efficiency, and will be protected in the human face photo of the live shooting of user to be identified, the identity card picture of live shooting and public security system
The photo on identity card deposited compares, can both determine user to be identified identity card picture whether in public security system
Photo is consistent, can also determine whether the human face photo of live shooting is consistent with the photo in identity card picture or public security system,
The accuracy of recognition of face can be improved.
Fig. 2 is the implementation process schematic diagram for the face identification method that further embodiment of this invention provides.As shown in Fig. 2,
On the basis of above-described embodiment, step S105 be may comprise steps of:
Step S201: the second photo of each second user to be identified and third photo are compared, and obtain each
The first comparison score value of two users to be identified.
In embodiments of the present invention, the second photo and third photo are compared first, judges the identity being taken on site
Whether the photo on identity card saved in license piece and public security system is consistent, obtains the first comparison score value.
Before the second photo of each second user to be identified and third photo are compared, can also include: by
The second photo and third photo of each second user to be identified pre-processes, and pretreatment includes the photograph for extracting face part
Piece, and illumination compensation, gray scale balance are carried out to the photo for the face part that extraction obtains, reduce noise, raising clarity processing.
Step S202: the first comparison score value of each second user to be identified is compared with default comparison threshold value.
In embodiments of the present invention, default comparison threshold value can be configured according to actual needs.Illustratively, if comparison
Score value full marks are 100 points, then presetting comparison threshold value can be set to 90 points.
If the first comparison score value of the second user to be identified is greater than or equal to default comparison threshold value, second use to be identified
Second photo and third photo at family compare successfully;If the first comparison score value of the second user to be identified is less than default contrast threshold
Value, then the second photo and third photo of second user to be identified compares failure.If the second of second user to be identified shines
Piece and third photo compare failure, then illustrate that the identity card picture of the live shooting of second user to be identified and public security system are protected
The photo on identity card deposited is inconsistent, and there are problems for the identity card which provides, thus determine this second
The face recognition result of user to be identified is recognition failures, no longer needs to carry out next by the first of second user to be identified
Photo and the second photo compare, or, the first photo of second user to be identified and third photo are compared, in this way
The efficiency of recognition of face can be improved.
Step S203: the first comparison score value is greater than or equal to the use to be identified of target second of default comparison threshold value if it exists
Family then compares the first photo of the user to be identified of target second and the second photo, or, by the user to be identified of target second
The first photo and third photo compare, obtain the user to be identified of target second second comparison score value.
In embodiments of the present invention, the first comparison score value is greater than or equal to the second user to be identified of default comparison threshold value
The referred to as user to be identified of target second.The user to be identified of target second if it exists illustrates the scene of the user to be identified of target second
The photo on identity card saved in the identity card picture and public security system of shooting compares success, then by the use to be identified of target second
The human face photo of the live shooting at family and the identity card picture of live shooting compare, or, by the user to be identified of target second
Live shooting human face photo and public security system in photo on the identity card that saves compare, obtain target second wait know
The second comparison score value of other user.
It is compared by the first photo of the user to be identified of target second and the second photo, or, by target second wait know
Before the first photo and third photo of other user compares, the first photo is pre-processed first, pretreatment includes mentioning
Take the photo of face part, and to the photo for the face part that extraction obtains carry out illumination compensation, gray scale balance, reduce noise,
Improve clarity processing.
Step S204: if the second comparison score value of the user to be identified of target second is greater than or equal to default comparison threshold value,
The face recognition result of the user to be identified of target second is to identify successfully, otherwise the recognition of face knot of the user to be identified of target second
Fruit is recognition failures.
The embodiment of the present invention first compares the second photo of the second user to be identified and third photo, it can be determined that
Whether the identity card that the second user to be identified provides is correctly, if the identity card that the second user to be identified provides is incorrect
, then it no longer needs to carry out following photo comparison;If the second photo of the second user to be identified and third photo comparison success,
The first photo of second user to be identified and the second photo are compared, or, by the first photo of the second user to be identified and
Third photo compares, and the accuracy of recognition of face can be improved.
As further embodiment of this invention, on the basis of the above embodiments, step S105 can with the following steps are included:
If the face recognition result of the user to be identified of target second is recognition failures, by the first photo, the second photo, the
Three photos, the first comparison score value and the second comparison score value are sent to display terminal, so that display terminal reminds auditor by the
One photo, the second photo and third photo compare, and obtain final comparing result.
The final comparing result that display terminal is sent is received, and using final comparing result as the user to be identified of target second
Final face recognition result.
In embodiments of the present invention, if the face recognition result of the user to be identified of target second is recognition failures, increase
The link of manual examination and verification, auditor compare the first photo, the second photo and third photo, and refer to first pair of score
Value and the second comparison score value, obtain manual examination and verification as a result, the artificial auditing result is known as final comparing result, and this is final
Final face recognition result of the comparing result as the user to be identified of target second.The embodiment of the present invention is by increasing artificial examine
The link of core can be further improved the accuracy of recognition of face.
Fig. 3 is the implementation process schematic diagram for the face identification method that yet another embodiment of the invention provides.As shown in figure 3,
On the basis of above-described embodiment, in above-mentioned steps S102, the credit value of the several first users to be identified is determined according to credit record
Process, may comprise steps of:
Step S301: determine whether each first user to be identified has bad credit record according to credit record.
In embodiments of the present invention, can be judged according to the overdue non-repayment amount of this transaction in every credit record each
Whether the first user to be identified has bad credit record.If this in credit record is traded, overdue non-repayment amount is not zero,
Then this credit record is bad credit record.If in every credit record of the first user to be identified, this transaction is overdue not
Repayment amount is zero, then bad credit record is not present in first user to be identified, and otherwise, which exists
Bad credit record.
Step S302: if it exists with bad credit record the user to be identified of target first, it is determined that target first to
Identify classification belonging to the bad credit record of user, and the classification according to belonging to bad credit record obtains each classification and corresponds to
Weight coefficient and each classification bad credit record the amount of money.
In embodiments of the present invention, that the first user to be identified with bad credit record is known as target first is to be identified
User.Classification belonging to bad credit record can be the classifications such as housing loan, vehicle loan, also can according to need and be divided into other classes
Not.Each classification has the corresponding weight coefficient pre-set, can the acquisition of the classification according to belonging to bad credit record
The corresponding weight coefficient of each classification.This in bad credit record trades overdue non-repayment amount as the bad credit record
The amount of money is added the amount of money of the bad credit record in the corresponding bad credit record of each classification to obtain the bad of each classification
The amount of money of credit record.
Step S303: it is obtained according to the amount of money of the corresponding weight coefficient of each classification and the bad credit record of each classification
The total amount of the bad credit record of the user to be identified of target first.
In embodiments of the present invention, the amount of money of the corresponding weight coefficient of a certain classification and the bad credit record of the category
Product is the total amount of the bad credit record of the category, and the bad credit of each classification of the user to be identified of target first is remembered
The total amount of record is added to obtain the total amount of the bad credit record of the user to be identified of target first.
Step S304: the total amount traded in the credit record of the user to be identified of target first is obtained.
In embodiments of the present invention, by the amount of money of this transaction in every credit record of the user to be identified of target first
Addition obtains the total amount traded in the credit record of the user to be identified of target first.
Step S305: according to the total amount traded in the total amount of bad credit record and credit record, target is determined
The credit value of one user to be identified.
In embodiments of the present invention, during the total amount that the total amount traded in credit record subtracts bad credit record obtains
Between be worth, the ratio for the total amount traded in median and credit record is the credit value of the user to be identified of target first.
As further embodiment of this invention, the first user information set of several first users to be identified is obtained, comprising:
Directly acquire the first user information set of the several first users to be identified;Or, obtaining each first use to be identified
The contract mark for the contract that family is signed searches the contract mark pair for the contract that each first user to be identified signs from database
The user information answered obtains the first user information set.
In embodiments of the present invention, terminal device can directly acquire the first user information of the several first users to be identified
Set, can also the contract mark of contract signed of each first user to be identified, then search from database each first to
It identifies that the contract for the contract that user signs identifies corresponding user information, obtains the first user information set.Wherein, contract identifies
It can be first user's processes financial business to be identified, such as when lending and borrowing business, the contract number of the contract of signing.
The embodiment of the present invention can also monitor each face identification mission in real time, such as record each recognition of face
At the beginning of task, the end time, record the information such as success rate, failure rate of face identification mission.
The embodiment of the present invention can simplify the docking mode of recognition of face task Yu other tasks to the maximum extent, new when having
When recognition of face task, it is ensured that quickly access.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Fig. 4 be one embodiment of the invention provide face identification system schematic block diagram, for ease of description, only show with
The relevant part of the embodiment of the present invention.
In embodiments of the present invention, face identification system 4 includes:
User profile acquisition module 41, for obtaining the first user information set of the several first users to be identified, first
User information set includes the User Identity, the first photo and the second photo of the several first users to be identified, wherein first
Photo is the human face photo for the several first users to be identified being taken on site, and the second photo be live shooting several first wait know
The identity card picture of other user;
Credit record obtains module 42, and the credit for obtaining the several first users to be identified according to User Identity is remembered
It records, and determines the credit value of the several first users to be identified according to credit record;
Screening module 43 is more than default prestige for from the several first users to be identified, filtering out corresponding credit value
Several second users to be identified of threshold value;
Third photo obtains module 44, for obtaining the third photo of each second user to be identified, wherein third photo
For the photo on the identity card of each second user to be identified saved in public security system;
Contrast module 45, for carrying out pair the first photo, the second photo, third photo of each second user to be identified
Than obtaining the face recognition result of each second user to be identified.
Optionally, contrast module 45 includes:
First comparison unit is obtained for comparing the second photo of each second user to be identified and third photo
First to each second user to be identified compares score value;
Comparing unit, for comparing the first comparison score value of each second user to be identified with default comparison threshold value
Compared with;
Second comparison unit, for the if it exists first comparison score value be greater than or equal to the target second of default comparison threshold value to
It identifies user, then compares the first photo of the user to be identified of target second and the second photo, or, by target second wait know
The first photo and third photo of other user compares, and obtains the second comparison score value of the user to be identified of target second;
Recognition result confirmation unit is preset if the second comparison score value for the user to be identified of target second is greater than or equal to
Comparison threshold value, then the face recognition result of the user to be identified of target second is to identify successfully, otherwise the user to be identified of target second
Face recognition result be recognition failures.
Optionally, contrast module 45 further include:
Transmission unit shines if the face recognition result for the user to be identified of target second is recognition failures by first
Piece, the second photo, third photo, the first comparison score value and the second comparison score value are sent to display terminal, so that display terminal mentions
The auditor that wakes up compares the first photo, the second photo and third photo, and obtains final comparing result;
Receiving unit, for receiving the final comparing result of display terminal transmission, and using final comparing result as target
The final face recognition result of second user to be identified.
Optionally, credit record obtains module 42 further include:
First determination unit, for determining whether each first user to be identified there is bad credit to remember according to credit record
Record;
Second determination unit, for if it exists with the user to be identified of target first of bad credit record, it is determined that mesh
Classification belonging to the bad credit record of the first user to be identified is marked, and the classification according to belonging to bad credit record obtains each
The amount of money of the corresponding weight coefficient of classification and the bad credit record of each classification;
Computing unit, for the amount of money according to the corresponding weight coefficient of each classification and the bad credit record of each classification
Obtain the total amount of the bad credit record of the user to be identified of target first;
First acquisition unit, the total amount traded in the credit record for obtaining the user to be identified of target first;
Third determination unit, the total amount for trading in the total amount and credit record according to bad credit record, really
Set the goal the credit value of the first user to be identified.
Optionally, User profile acquisition module 41 further include:
Second acquisition unit, for directly acquiring the first user information set of the several first users to be identified;Or,
Third acquiring unit, for obtaining the contract mark for the contract that each first user to be identified signs, from database
The middle contract for searching the contract that each first user to be identified signs identifies corresponding user information, obtains the first user information collection
It closes.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of the face identification system is divided into different functional unit or module, with
Complete all or part of function described above.Each functional unit in embodiment, module can integrate single in a processing
In member, it is also possible to each unit and physically exists alone, can also be integrated in one unit with two or more units, on
It states integrated unit both and can take the form of hardware realization, can also realize in the form of software functional units.In addition, each
Functional unit, module specific name be also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.On
The specific work process for stating unit in device, module, can refer to corresponding processes in the foregoing method embodiment, no longer superfluous herein
It states.
Fig. 5 is the schematic block diagram for the terminal device that one embodiment of the invention provides.As shown in figure 5, the terminal of the embodiment
Equipment 5 includes: one or more processors 50, memory 51 and is stored in the memory 51 and can be in the processor
The computer program 52 run on 50.The processor 50 realizes above-mentioned each recognition of face when executing the computer program 52
Step in embodiment of the method, such as step S101 to S105 shown in FIG. 1.Alternatively, the processor 50 executes the calculating
The function of each module/unit in above-mentioned face identification system embodiment, such as module 41 to 45 shown in Fig. 4 are realized when machine program 52
Function.
Illustratively, the computer program 52 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 51, and are executed by the processor 50, to complete the application.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 52 in the terminal device 5 is described.For example, the computer program 52 can be divided
It is cut into User profile acquisition module, credit record obtains module, screening module, third photo obtain module and contrast module.
User profile acquisition module, for obtaining the first user information set of the several first users to be identified, first is used
Family information aggregate includes the User Identity, the first photo and the second photo of the several first users to be identified, wherein first shines
Piece is the human face photo for the several first users to be identified being taken on site, and the second photo be the several first to be identified of live shooting
The identity card picture of user;
Credit record obtains module, and the credit for obtaining the several first users to be identified according to User Identity is remembered
It records, and determines the credit value of the several first users to be identified according to credit record;
Screening module is more than default prestige threshold for from the several first users to be identified, filtering out corresponding credit value
Several second users to be identified of value;
Third photo obtains module, and for obtaining the third photo of each second user to be identified, wherein third photo is
Photo on the identity card of each second user to be identified saved in public security system;
Contrast module, for carrying out pair the first photo, the second photo, third photo of each second user to be identified
Than obtaining the face recognition result of each second user to be identified.
Other modules or unit can refer to the description in embodiment shown in Fig. 4, and details are not described herein.
The terminal device can be desktop PC, notebook, palm PC and cloud server etc. and calculate equipment.
The terminal device 5 includes but are not limited to processor 50, memory 51.It will be understood by those skilled in the art that Fig. 5 is only
One example of terminal device, does not constitute the restriction to terminal device 5, may include components more more or fewer than diagram,
Perhaps combine certain components or different components, for example, the terminal device 5 can also include input equipment, output equipment,
Network access equipment, bus etc..
The processor 50 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 51 can be the internal storage unit of the terminal device, such as the hard disk or interior of terminal device
It deposits.What the memory 51 was also possible to be equipped on the External memory equipment of the terminal device, such as the terminal device inserts
Connect formula hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash memory
Block (Flash Card) etc..Further, the memory 51 can also both include the internal storage unit of terminal device or wrap
Include External memory equipment.The memory 51 is for storing needed for the computer program 52 and the terminal device other
Program and data.The memory 51 can be also used for temporarily storing the data that has exported or will export.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
Scope of the present application.
In embodiment provided herein, it should be understood that disclosed face identification system and method, Ke Yitong
Other modes are crossed to realize.For example, face identification system embodiment described above is only schematical, for example, described
The division of module or unit, only a kind of logical function partition, there may be another division manner in actual implementation, such as more
A unit or assembly can be combined or can be integrated into another system, or some features can be ignored or not executed.It is another
Point, shown or discussed mutual coupling or direct-coupling or communication connection can be through some interfaces, device or
The INDIRECT COUPLING or communication connection of unit can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the application realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium
It may include: any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic that can carry the computer program code
Dish, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to the requirement made laws in jurisdiction with patent practice
Subtract, such as in certain jurisdictions, according to legislation and patent practice, computer-readable medium do not include be electric carrier signal and
Telecommunication signal.
Embodiment described above is only to illustrate the technical solution of the application, rather than its limitations;Although referring to aforementioned reality
Example is applied the application is described in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features;And these are modified
Or replacement, the spirit and scope of each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution should all
Comprising within the scope of protection of this application.