CN110287971A - Data verification method, device, computer equipment and storage medium - Google Patents
Data verification method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110287971A CN110287971A CN201910429736.3A CN201910429736A CN110287971A CN 110287971 A CN110287971 A CN 110287971A CN 201910429736 A CN201910429736 A CN 201910429736A CN 110287971 A CN110287971 A CN 110287971A
- Authority
- CN
- China
- Prior art keywords
- certificate
- image
- obtains
- data verification
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013524 data verification Methods 0.000 title claims abstract description 95
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 50
- 238000001514 detection method Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims description 34
- 238000012795 verification Methods 0.000 claims description 26
- 238000012550 audit Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 17
- 238000005516 engineering process Methods 0.000 claims description 13
- 238000012937 correction Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 5
- 230000001815 facial effect Effects 0.000 description 24
- 238000012216 screening Methods 0.000 description 6
- 238000003708 edge detection Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000033228 biological regulation Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 2
- 239000010931 gold Substances 0.000 description 2
- 229910052737 gold Inorganic materials 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000007373 indentation Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/752—Contour matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Abstract
The invention discloses a kind of data verification method, device, computer equipment and storage mediums.If this method includes that applying type is a kind of applying type, at least two certificate images are handled using frame detection algorithm and profile alignment algorithm, obtain the corresponding objective contour image of each certificate image；Each objective contour image is input in pre-configured face matched interfaces and carries out face matching respectively, obtains face matching result；Information identification is carried out to each certificate image using certificate recognizer, obtains the corresponding perfect instrument information of each certificate image；Perfect instrument information is screened by keyword, obtains target certificate information, consistency on messaging verifying is carried out to all target certificate informations, obtains consistency checking result；If all face matching results are successful match, and consistency checking result is to be verified, then obtains the data verification being verified as a result, improving the accuracy rate of data verification efficiency and data verification.
Description
Technical field
The present invention relates to field of image recognition more particularly to a kind of data verification method, device, computer equipment and storages
Medium.
Background technique
Currently, verifying under scene (such as personal information application verifying, bank's application loan) certificate information in specific data
To fill in be manually entered by user oneself mostly, then pass through the validity and authenticity of manual examination and verification certificate information.?
Certificate information fill in it is more or more complex in the case where, manual fill message is error-prone and fills in low efficiency, when filling in letter manually
Also it will have a direct impact on the accuracy rate by data verification in the case where breath error.In addition, manually being audited to certificate information, deposit
The case where auditing big difficulty, low efficiency.
Summary of the invention
The embodiment of the present invention provides a kind of data verification method, device, computer equipment and storage medium, artificial to solve
The problem of information that fills up a document is error-prone and low efficiency and manual examination and verification low efficiency.
A kind of data verification method, comprising:
The data verification request that client is sent is obtained, the data verification request includes applying type and the application class
Corresponding at least two original certificate of type；
The original certificate is pre-processed, certificate image is obtained；
If the applying type is a kind of applying type, using frame detection algorithm and profile alignment algorithm at least two
A certificate image is handled, and the corresponding objective contour image of each certificate image is obtained；
Each objective contour image is input in pre-configured face matched interfaces and carries out face respectively
Match, obtains the corresponding face matching result of each objective contour image；
Information identification is carried out to each certificate image using certificate recognizer, obtains each certificate image pair
The perfect instrument information answered；
The perfect instrument information is screened by keyword, obtains target certificate information, and to all mesh
It marks certificate information and carries out consistency on messaging verifying, obtain consistency checking result；
If all face matching results are successful match, and the consistency checking result is to be verified, then
It obtains the data verification result being verified and is sent to the client.
A kind of data verification device, comprising:
Checking request obtains module, for obtaining the data verification request of client transmission, the data verification request packet
Include applying type and corresponding at least two original certificate of the applying type；
Preprocessing module obtains certificate image for pre-processing to the original certificate；
Contour images searching module uses frame detection algorithm if being a kind of applying type for the applying type
At least two certificate images are handled with profile alignment algorithm, obtain the corresponding target wheel of each certificate image
Wide image；
Face matching module, for each objective contour image to be input to pre-configured face matched interfaces
It is middle to carry out face matching respectively, obtain the corresponding face matching result of each objective contour image；
First certificate image identification module, for carrying out information knowledge to each certificate image using certificate recognizer
Not, the corresponding perfect instrument information of each certificate image is obtained；
Information sifting module obtains target certificate letter for screening by keyword to the perfect instrument information
Breath, and consistency on messaging verifying is carried out to all target certificate informations, obtain consistency checking result；
First verification result obtains module, if being successful match for all face matching results, and described one
Cause property verification result is to be verified, then obtains the data verification result being verified and be sent to the client.
A kind of computer equipment, including memory, processor and storage are in the memory and can be in the processing
The computer program run on device, the processor realize above-mentioned data verification method when executing the computer program.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the meter
Calculation machine program realizes above-mentioned data verification method when being executed by processor.
Above-mentioned data verification method, device, computer equipment and storage medium, by being pre-processed to original certificate,
So that the certificate image obtained is clear and is direct picture, the accuracy rate of subsequent data authentication is improved.Pass through face recognition technology
There is facial image at least two certificate images for determining that user uploads, to determine the applying type of user for a kind of application class
Type executes the corresponding verification step of a kind of applying type.By selecting verification step corresponding with applying type to certificate image
On objective contour image and target certificate information verified, with complete the authenticity and validity of original certificate are tested
Card.Through the above steps, it is participated in without artificial, computer can be automatically performed the verifying to original certificate, improve data verification
Efficiency, and guarantee the accuracy rate that data verification is carried out to original certificate.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is an application environment schematic diagram of data verification method in one embodiment of the invention；
Fig. 2 is a flow chart of data verification method in one embodiment of the invention；
Fig. 3 is a flow chart of data verification method in one embodiment of the invention；
Fig. 4 is a specific flow chart of step S12 in Fig. 2；
Fig. 5 is a specific flow chart of step S13 in Fig. 2；
Fig. 6 is a specific flow chart of step S15 in Fig. 2；
Fig. 7 is a schematic diagram of data verification device in one embodiment of the invention；
Fig. 8 is a schematic diagram of computer equipment in one embodiment of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Data verification method provided by the present application can be applicable in the application environment such as Fig. 1, wherein it is logical to calculate client
Network is crossed to be communicated with server.Client include but is not limited to various personal computers, laptop, smart phone,
Tablet computer and portable wearable device.Server can use the service of the either multiple server compositions of independent server
Device cluster is realized.
In one embodiment, as shown in Fig. 2, providing a kind of data verification method, the service in Fig. 1 is applied in this way
It is illustrated, includes the following steps: for device
S11: the data verification request that client is sent is obtained, data verification request includes applying type and applying type pair
At least two original certificates answered.
Wherein, data verification request refers to the request that the data sent to client are verified.Data in the present embodiment
Checking request is specially the request verified user and apply passing related data when loan on the client.Specifically, user is in client
The applying type that end selection needs, and corresponding original certificate is uploaded according to this application type, it then will be original by client
Certificate is sent to corresponding server, so that server executes subsequent step.Wherein, applying type refers to loan application type, this
Applying type in embodiment includes but is not limited to that personal information verifying (such as purchase plane ticket, train ticket and high guaranteed votes, is applied
State's study and border tourism) and bank's application loan (fiduciary loan, automobile mortgage loan and home mortgage loan).Original certificate
Refer to the certificate before the deadline determined according to applying type, as travel abroad needs identity card and passport；Border tourism needs
Identity card and Hongkong and Macro's pass；Automobile mortgage loan needs identity card and driving license；Home mortgage loan needs identity card and room
Produce card etc..
S12: pre-processing original certificate, obtains certificate image.
Specifically, after obtaining original certificate, server can pre-process original certificate, to obtain certificate image.
Pretreatment in the present embodiment specifically includes two big steps, is respectively as follows: and 1) carries out fuzzy detection to original certificate, is uploaded with determining
Original certificate it is whether clear, if clearly, thening follow the steps 2)；If unintelligible, user is prompted to upload original certificate again.2)
Correction process is carried out to clearly original certificate, is not the image for having tilt angle with the original certificate for determining that server obtains,
It is direct picture.Correction process in the present embodiment includes but is not limited to the perspectiveTransform used in OpenCv
() function.Wherein, OpenCV is the cross-platform computer vision library comprising a large amount of open sources API (interface), passes through calling
Corresponding interface realizes the correction to original certificate with quick obtaining perspectiveTransform () function in OpenCV
Processing.Facilitate execution by carrying out fuzzy detection and correction process to original certificate to obtain clear and positive certificate image
Subsequent step.
S13: if applying type is a kind of applying type, using frame detection algorithm and profile alignment algorithm at least two
A certificate image is handled, and the corresponding objective contour image of each certificate image is obtained.
A kind of applying type in the present embodiment refers to that needing to upload at least two when user applies for loan includes facial image
The corresponding applying type of original certificate.Wherein, the original certificate comprising facial image includes but is not limited to identity card and driving
Card.
Specifically, server by face recognition technology judge user upload at least two certificate images in whether there is
Facial image, to determine the applying type of user.If there is facial image at least two certificate images, it is determined that user's
Applying type is a kind of applying type；If only having a facial image in certificate image or facial image being not present, it is determined that
The applying type of user is two class applying types.Wherein, two class applying types refer to the original certificate uploaded when user applies for loan
In not include facial image or only one include the corresponding applying type of facial image.
When the applying type for determining user is a kind of application, then each certificate image is carried out using frame detection algorithm
Detection, obtains the contour images that profile can be formed in each certificate image.Frame detection algorithm in the present embodiment can use
Canny edge detection algorithm in opencv vision library, Canny edge detection algorithm are a kind of common profile lookup algorithms.
Wherein, contour images refer to the image that closed contour can be formed in certificate image.
Profile since the contour images more than one of profile can be formed in certificate image, as profile can be formed on identity card
Image includes national emblem and facial image.Therefore, after obtaining the contour images in certificate image, it is also necessary to be compared and be calculated using profile
Method screens each contour images, obtains objective contour image corresponding with each certificate image.Wheel in the present embodiment
Wide alignment algorithm refers to the size and shape for setting nominal contour, the method for being compared screening to contour images.This reality
The size and shape for applying the nominal contour in example are specifically set as the shape and size of facial image on identity card or driver's license.
Each certificate image is handled by frame detection algorithm and profile alignment algorithm, it is corresponding to obtain each certificate image
Objective contour image, i.e. facial image on certificate image carry out really in order to execute subsequent step to objective contour image
Property verifying.
S14: each objective contour image is input in pre-configured face matched interfaces and carries out face respectively
Match, obtains the corresponding face matching result of each objective contour image.
Wherein, face matched interfaces refer to the interface that authenticity verification is carried out to objective contour image.It is matched by the face
Objective contour image can be sent to face verification system and carry out face authenticity verification by interface.
Specifically, after obtaining the corresponding objective contour image of each certificate image, server can be by each objective contour
Image is input in pre-configured face matched interfaces and carries out face matching respectively, and it is corresponding to obtain each objective contour image
Face matching result.Facial image similarity in objective contour image and face matched interfaces reaches preset value, then should
The corresponding face matching result of facial image is successful match；Facial image in objective contour image and face matched interfaces
Similarity does not reach preset value, then the corresponding face matching result of the facial image is that matching is unsuccessful.
Further, in order to guarantee the accuracy of face matching result, the face verification system in the present embodiment is in user
When uploading original certificate, face verification system can obtain the identity on identity card by the corresponding certificate image of identification identity card
Number is demonstrate,proved, the information that the ID card No. is stored in public security system is then obtained by ID card No., to pass through this side
Whether the facial image that formula is verified in the original certificate that user uploads is authentic and valid.
S15: information identification is carried out to each certificate image using certificate recognizer, it is corresponding to obtain each certificate image
Perfect instrument information.
Wherein, certificate recognizer refers to the algorithm that information identification is carried out to certificate image.Certificate identification in the present embodiment
Algorithm can use OCR image recognition technology.Perfect instrument information, which refers to, identifies certificate image by certificate recognizer
The obtained text information on the certificate image.Specifically, after obtaining certificate image, server uses certificate identification to calculate first
Method carries out information identification to each certificate image, obtains the corresponding text information of certificate image, is then carried by certificate image
Type of credential obtain corresponding certificate stencil, based on the certificate information mark on certificate stencil, treat classifying text and divided
Class identifies corresponding target certificate information to obtain each certificate information.Finally, the validity period to certificate is verified, with true
The original certificate that warranty family uploads be within the effect phase, it is when determining the original certificate of user before the deadline, then original from this
Perfect instrument information is obtained in the corresponding certificate image of certificate.Certificate stencil, which refers to, classifies to the text information on certificate image
Template.In order to improve the accuracy rate of certificate stencil classification, the corresponding certificate stencil of each type of credential in the present embodiment.The card
Part template includes certificate information mark, and the certificate identifier in the present embodiment refers to the mark for distinguishing the text information on certificate image
Know.By taking identity card as an example, the corresponding certificate identifier of identity card is " name ", " gender ", " nationality ", " birth ", " address " and " has
The effect phase ".
S16: screening perfect instrument information by keyword, obtains target certificate information, and demonstrate,prove all targets
Part information carries out consistency on messaging verifying, obtains consistency checking result.
It specifically, can be by keyword to perfect instrument after obtaining the corresponding perfect instrument information of each certificate image
Information is screened, and target certificate information is obtained.Wherein, target certificate information refers to the keyword by pre-setting to effective
The information that certificate information obtains after being screened.Since the information that each certificate image needs to verify is inconsistent, this implementation
The corresponding keyword setting of each certificate image is also inconsistent in example, and specific keyword setting is determine according to actual needs.Such as body
It is name, gender, address, ID card No. and validity period that part, which demonstrate,proves corresponding target certificate information,；The corresponding mesh of social security card
Mark certificate information is name, social security number and validity period.
After obtaining target certificate information, server can carry out consistency on messaging verifying to all target certificate informations, obtain
Take consistency checking result.If the target certificate information obtained is consistent, consistency checking result is to be verified；If obtaining
Target certificate information is inconsistent, then consistency checking result is that verifying does not pass through.If the certificate image of acquisition is identity card and society
It protects and blocks corresponding certificate image, then the target certificate information obtained from the corresponding certificate image of identity card is name and identity card
Number, the target certificate information obtained from the corresponding certificate image of social security card is name and social guarantee number, if the two
Name is consistent, and ID card No. is consistent with social security number, then it represents that target certificate information is consistent, corresponding consistency
Verification result is to be verified.By carrying out consistency on messaging verifying to all target certificate informations, use can be effectively verified
Whether the original certificate that family uploads is authentic and valid, to ensure the legitimate rights and interests of debtor and creditor.
S17: if all face matching results are successful match, and consistency checking result is to be verified, then obtains
The data verification result that is verified simultaneously is sent to client.
It specifically, is successful match in all face matching results, and consistency checking result is to be verified, then table
Show user upload original certificate be it is authentic and valid, server can generate the data verification being verified as a result, and should
The data verification result being verified is sent to client, so that the data verification knot that user's timely learning data verification passes through
Fruit.
Step S11- step S17, by being pre-processed to original certificate, so that the certificate image obtained is clear and is positive
Face image improves the accuracy rate of subsequent data authentication.At least two certificate figures that user uploads are determined by face recognition technology
As there is facial image, to determine the applying type of user as a kind of applying type, execute that a kind of applying type is corresponding tests
Demonstrate,prove step.By selecting verification step corresponding with applying type to the objective contour image and target certificate letter on certificate image
Breath is verified, to complete to verify the authenticity and validity of original certificate.By step S11-S17, without artificial
It participates in, computer can be automatically performed the verifying to original certificate, improve data verification efficiency, and guarantee to carry out original certificate
The accuracy rate of data verification.
In one embodiment, each certificate image carries corresponding type of credential.Due to part original certificate (such as house property
Card and driving license) it is the certificate not comprising facial image, i.e. the corresponding applying type of original certificate is not a kind of applying type, therefore
Above-mentioned steps cannot be used to carry out data verification, obtain data verification result.As shown in Fig. 2, in order to not comprising facial image
Certificate image carry out data verification, obtain verification result, the data verification method further include:
S21: if applying type is two class applying types, information is carried out to each certificate image using certificate recognizer
Identification, obtains the corresponding perfect instrument information of each certificate image.
Specifically, if server identify user upload at least two original certificates in have one do not include face figure
Picture, it is determined that the applying type of user is two class applying types.Information identification is carried out to certificate image using certificate recognizer,
Obtain the corresponding perfect instrument information of certificate image.Specific implementation procedure, to avoid repeating, is repeated no more as described in step S15.
S22: it calls certificate number identification script to identify perfect instrument information, obtains certificate number.
Certificate number identification script in the present embodiment refers to the card for identification that developer is write using regular expression
The script of part coding.Certificate number includes but is not limited to ID card No., property ownership certificate number, driver's license card number, the shelves of driving license
Case number and social security number.Specifically, after obtaining the corresponding perfect instrument information of two class applying types, server calls
Certificate number identification script, numbers the regular expression in identification script by certificate and identifies to perfect instrument information, obtain
Part of collecting evidence is numbered.
S23: being sent to certificate information query interface corresponding with the type of credential that certificate image carries for certificate number,
It obtains and numbers associated ID card No. with certificate.
Since certificate image includes more than one type of credential, in order to improve search efficiency, to each in the present embodiment
Type of credential is provided with a corresponding certificate information query interface.Wherein, type of credential refers to the corresponding type of certificate image, packet
Include but be not limited to identity card, property ownership certificate, driver's license and driving license.
Specifically, after obtaining certificate number, server is corresponding according to the corresponding type of credential selection of certificate number
Certificate information query interface, and certificate is numbered, corresponding certificate information system is sent to (such as by certificate information query interface
National identification card number code inquiry system, housing property management board web, driver's license inquiry system etc.), certificate information system passes through the card
Part number is inquired, and numbers associated ID card No. to obtain the certificate, and the ID card No. is passed through certificate information
Query interface is sent to server.
It should be noted that is, the corresponding type of credential of certificate image is identity card when certificate number is ID card No.
When, in order to verify the ID card No. whether be necessary being ID card No., server is to obtain ID card No. corresponding
Certificate number after, it is also desirable to ID card No. corresponding certificate number is sent to by corresponding certificate information query interface
National identification card number code inquiry system obtains the certificate and numbers corresponding ID card No..If certificate information query interface is fed back
Return value be an ID card No., then the ID card No. is and the certificate numbers associated ID card No.；If certificate
The return value of information query interface feedback is not an ID card No., then numbers associated identity for return value as the certificate
Demonstrate,prove number.By the way that certificate number is sent to certificate information query interface corresponding with type of credential, information can be effectively improved and obtained
The efficiency taken also ensures the authenticity and safety of certificate number.
S24: if all ID card No. are the same ID card No., the data verification result being verified is obtained simultaneously
It is sent to client.
Specifically, after obtaining different certificates and numbering associated ID card No., server can be to all bodies of acquisition
Part card number carries out consistency checking, if it is the same ID card No. that all indentations, which numbers associated ID card No.,
Data verification result is to be verified, and indicates that the original certificate that user uploads is the same person, and be authentic and valid.?
After obtaining data verification result, data verification result is sent to client by server, so that user is obtained in time by client
Primary data verification result.
Step S21- step S24, if applying type is two class applying types, using certificate recognizer to certificate image
Information identification is carried out, and certificate label identification script is called to identify the effective information of acquisition, obtains the card of certificate image
Part number.Then certificate number is sent to certificate information query interface corresponding with the type of credential that certificate image carries,
It obtains and numbers associated ID card No. with certificate, to determine the authenticity of certificate number.Finally judge all identity obtained
Demonstrate,prove whether number is the same person, to verify the authenticity of the original certificate of user's upload.
In one embodiment, data verification request further includes the intention amount of money, wherein the intention amount of money refers to that user is defeated in client
The amount of the loan entered.As shown in figure 3, after obtaining the data verification result being verified, data are tested in step S17 or S24
Card method further include:
S31: by the intention amount of money and perfect instrument information, audit engine is sent to by auditing interface.
Wherein, audit interface refers to that the intention amount of money and applying type for submitting user are sent to connecing for audit engine
Mouthful.Audit engine refers to whether the intention amount of money for selecting corresponding loan auditing rule to audit user according to applying type meets the requirements
Engine, the audit engine in the present embodiment can use drools regulation engine, faster using drools regulation engine speed,
It is more efficient.Since the present embodiment is intention amount of money apply by the auditing rule that stores in audit engine to user and effective
Certificate information is audited, and to determine whether the intention amount of money of user meets the requirements, therefore, is audited in the present embodiment and is set in engine
The auditing rule audited to different perfect instrument information is set.Wherein, auditing rule refers to the effective card uploaded to user
The rule that part information is audited.By the way that auditing rule to be stored in audit engine, the management to auditing rule is both facilitated, also
The treatment effeciency audited to the intention amount of money and perfect instrument information can be improved.
Specifically, after data verification result is to be verified, data verification can be requested the intention carried gold by server
Volume and perfect instrument information are sent to audit engine by auditing interface.Audit engine is getting the intention amount of money and perfect instrument
After information, the lendable credit amount of user met the requirements can be determined first according to perfect instrument information.Wherein, debt-credit gold
Volume refers to the amount of money that the user obtained according to audit engine to the verifying of perfect instrument information can borrow or lend money.
S32: it obtains after audit engine is assessed based on the intention amount of money and the corresponding auditing rule of perfect instrument information and obtains
The amount of money assessment result arrived, and amount of money assessment result is sent to client by data verification request.
Wherein, amount of money assessment result refers to the size for comparing credit amount and the intention amount of money, to determine whether to agree to according to meaning
The result borrowed or lent money to the amount of money.When credit amount is more than or equal to the intention amount of money, then amount of money assessment result is that assessment passes through；
When credit amount is less than the intention amount of money, then amount of money assessment result is that assessment does not pass through.
Specifically, after audit engine obtains amount of money assessment result by the audit of auditing rule, the amount of money can be assessed and is tied
Fruit returns to server by auditing result, amount of money assessment result is sent to client by data verification request, to use
Family is in client timely learning amount of money assessment result.
The intention amount of money and perfect instrument information are sent to audit engine by audit interface by step S31- step S32, with
Improve the treatment effeciency audited to the intention amount of money and perfect instrument information.Engine is audited after obtaining amount of money assessment result,
The amount of money assessment result can be sent to server, so that amount of money assessment result is sent to by server by data verification request
Client facilitates user's timely learning amount of money assessment result.
In one embodiment, as shown in figure 4, step S12, pre-processes original certificate, certificate image is obtained, specifically
Include the following steps:
S121: gray processing processing is carried out to original certificate, obtains gray level image.
Due to that may include multiple color in original certificate, in order to effectively reduce the subsequent treating capacity to data, with quick
The corresponding certificate image of original certificate is obtained, then needs to carry out gray processing processing to original certificate.Wherein, gray processing processing, which refers to, is
Convert colored original certificate image to the processing of gray level image.Gray level image is 256 between one kind has from black to white
The monochrome image of grade gray scale colour gamut or grade.
Specifically, after obtaining original certificate, server carries out gray processing to original certificate by gray processing Processing Algorithm
Processing obtains gray level image.Wherein, gray processing Processing Algorithm refers to the algorithm to the progress gray processing processing in original certificate.This
The algorithm of gray processing processing in embodiment includes but is not limited to use maximum value process, mean value method and weighted average method.
S122: process of convolution is carried out to gray level image using Laplace operator, obtains process of convolution data.
Specifically, after obtaining gray level image, the present embodiment rolls up gray level image using the Laplace operator of 3x3
Product processing, obtains process of convolution data.
S123: function is calculated using standard deviation, process of convolution data is calculated, it is corresponding to obtain process of convolution data
Standard deviation, and by handling standard deviation, obtain the corresponding variance of standard deviation.
Specifically, after obtaining process of convolution data, services use standard difference calculates function std2 () function to convolution
Processing data are calculated, and the corresponding standard deviation of process of convolution data is obtained, and by handling standard deviation, obtain standard
The corresponding variance of difference.
S124: variance is compared with Fuzzy Threshold, if variance is greater than or equal to Fuzzy Threshold, passes through the rectification function
Correction process is carried out to original certificate, obtains certificate image.
Wherein, Fuzzy Threshold refers to pre-set for judging the value whether variance meets the requirements.Specifically, it is obtaining
After variance, variance is compared with Fuzzy Threshold, if variance is greater than or equal to Fuzzy Threshold, then it represents that user uploads original
Certificate is clearly, the step of carrying out correction process to original certificate by the rectification function can be executed, to obtain acquisition certificate
Image；If variance be less than Fuzzy Threshold, then it represents that user upload original certificate be it is unsharp, need to upload again.
Step S121- step S124, by carrying out gray processing processing to original certificate, and using Laplace operator to ash
It spends image and carries out process of convolution, to calculate the corresponding standard deviation of original certificate, so that variance is obtained, the variance that then will acquire
It is compared with the Fuzzy Threshold pre-set, completes the fuzzy detection to original certificate.If server judges original certificate
It is clearly, then correction process to be carried out to clearly original certificate and improve subsequent number to obtain clear and positive certificate image
According to the accuracy rate of verifying.
In one embodiment, as shown in figure 5, step S13, using frame detection algorithm and profile alignment algorithm to each card
Part image is handled, and is obtained objective contour image corresponding with each certificate image, is specifically comprised the following steps:
S131: detecting certificate image using frame detection algorithm, obtain certificate image it is corresponding at least one have
Imitate contour images.
Frame detection algorithm used in the present embodiment refers to the Canny edge detection algorithm in opencv vision library, Canny
Edge detection algorithm is a kind of common profile lookup algorithm.
Specifically, after obtaining certificate image, certificate image is detected using frame detection algorithm, obtains certificate figure
As at least one corresponding effective contour image.Wherein, effective contour image refers to the figure that enclosed region can be formed in certificate image
Picture.
S132: traversing effective contour image using the nominal contour in profile alignment algorithm, acquisition and standard wheels
Wide matched effective contour image is as objective contour image.
Since there are many data that can form enclosed region (i.e. profile) in a certificate image, as can be with shape on identity card
What it is at enclosed region includes but is not limited to therefore facial image, national emblem image and identity card card profile are obtaining effective contour
After image, the effective contour image and nominal contour that need to will acquire using profile alignment algorithm carry out the ratio of shape and size
Compared with when the shape and size and nominal contour of effective contour image are coincide, it is determined that the corresponding image of effective contour image
For objective contour image.Wherein, profile alignment algorithm refers to the size and shape for setting nominal contour, for effective contour figure
Algorithm as being compared screening.
Specifically, after determining effective contour image, the type of credential selection and type of credential that are carried based on certificate image
Corresponding profile alignment algorithm detects effective contour image, if the result of profile alignment algorithm output is true, it is determined that
The effective contour image is the objective contour needed, continues to execute subsequent step；If the result of profile alignment algorithm output is vacation,
It then determines the objective contour that the effective contour image is not required to, subsequent processing no longer is carried out to the effective contour image.
Step S131- step S132, detects certificate image by using frame detection algorithm, obtains effective contour
Image, and effective contour image is matched using nominal contour, objective contour image is obtained, to improve subsequent data authentication
Accuracy rate.
In one embodiment, certificate image carries type of credential, as shown in fig. 6, step S15, is identified using certificate and calculated
Method carries out information identification to each certificate image, obtains the corresponding target certificate information of each certificate image, specifically includes as follows
Step:
S151: positioning the text in certificate image using text detection network model, obtains each in certificate image
The corresponding text box of character area, and text box is cut, obtain image to be classified.
Wherein, text detection network model (Connectionist Text Proposal Network, abbreviation CTPN) mould
Type is a kind of commonly for carrying out the model of pictograph positioning, and text monitoring network model can be positioned quickly and accurately
The position of text in the picture.Text box refers to the rectangle obtained when positioning by CTPN model to the text on certificate image
Frame.
Specifically, after obtaining certificate image, the text in certificate image is determined using text detection network model
Position obtains the corresponding text box of each character area in certificate image.By the upper left position coordinate of each text box and the lower right corner
Position coordinates calculate the length and width of text box by positioning coordinate as positioning coordinate.Then according to positioning coordinate, text
The length and width of this frame cuts certificate image, obtains image to be classified.
S152: Text region is carried out to image to be classified using image recognition technology, obtains text to be sorted.
Image recognition technology in the present embodiment can use OCR image recognition technology.Specifically, figure to be sorted is being obtained
As after, classifying text is treated using OCR image recognition technology and carries out Text region, obtains text to be sorted.Wherein, text to be sorted
This refers to the text that Text region acquisition is carried out to image to be classified.Classifying text, which is treated, by OCR image recognition technology carries out text
Word identification can be improved computer and treat accuracy rate and efficiency that classifying text carries out Text region.
S153: the type of credential carried based on certificate image obtains certificate stencil corresponding with type of credential.
Specifically, after obtaining text to be sorted, the type of credential carried by certificate image, acquisition is stored in advance in clothes
The certificate stencil being engaged in device, provides data source for subsequent step.
S154: treating classifying text based on the certificate identifier on certificate stencil and classify, and it is corresponding to obtain certificate image
Perfect instrument information.
Specifically, after obtaining certificate stencil, classifying text is treated based on the certificate identifier on certificate stencil and is classified,
Text to be sorted and certificate identifier are corresponded, the perfect instrument information on certificate image is obtained, guarantees perfect instrument information
Accuracy and integrality.
Step S151- step S154, is first passed through and is determined using text detection network model the text in certificate image
Position obtains the corresponding text box of each character area in certificate image, and cuts to text box, obtains image to be classified, with
Guarantee the integrality of text to be sorted.Then classifying text is treated using the certificate identifier on certificate stencil to classify, obtain
Complete and accurate perfect instrument information.If obtaining the corresponding text box of each character area without using text detection network model,
It directlys adopt image recognition technology and Text region is carried out to image to be classified, then may result in that each certificate identifier is corresponding to be had
There is the case where text omission or text misclassification in effect certificate information.Therefore, using step S151- step S154 to each certificate
Image, which carries out information identification, can effectively improve the accuracy rate and integrality of target certificate information.
Data verification method provided by the present application, by being pre-processed to original certificate, so that the certificate image obtained
Clearly and it is direct picture, improves the accuracy rate of subsequent data authentication.Determine that user uploads at least by face recognition technology
Two certificate images whether there is facial image, to determine the applying type of user, if at least two certificate images have people
Face image, it is determined that the applying type of user is a kind of applying type, executes the corresponding verification step of a kind of applying type.If extremely
Only one comprising facial image or does not include facial image in few two certificate images, it is determined that the applying type of user is
Two class applying types execute the corresponding verification step of two class applying types.By selecting verification step corresponding with applying type
Data on certificate image are verified, with complete to the authenticity of original certificate and validity into verifying, and guarantee
The reliability and accuracy of data verification.
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.
In one embodiment, a kind of data verification device is provided, which tests with data in above-described embodiment
Card method corresponds.As shown in fig. 7, the data verification device includes that checking request obtains module 11, preprocessing module 12, wheel
Wide image searching module 13, face matching module 14, the first certificate image identification module 15, information sifting module 16 and first are tested
It demonstrate,proves result and obtains module 17.Detailed description are as follows for each functional module:
Checking request obtains module 11, and for obtaining the data verification request of client transmission, data verification request includes
Applying type and corresponding at least two original certificate of applying type.
Preprocessing module 12 obtains certificate image for pre-processing to original certificate.
Contour images searching module 13, if being a kind of applying type for applying type, using frame detection algorithm and
Profile alignment algorithm handles at least two certificate images, obtains the corresponding objective contour image of each certificate image.
Face matching module 14, for each objective contour image to be input in pre-configured face matched interfaces
Face matching is carried out respectively, obtains the corresponding face matching result of each objective contour image.
First certificate image identification module 15, for carrying out information knowledge to each certificate image using certificate recognizer
Not, the corresponding perfect instrument information of each certificate image is obtained.
Information sifting module 16, for being screened by keyword to perfect instrument information, acquisition target certificate information,
And consistency on messaging verifying is carried out to all target certificate informations, obtain consistency checking result.
First verification result obtains module 17, if being successful match for all face matching results, and consistency is tested
Card result is to be verified, then obtains the data verification result being verified and be sent to client.
Further, which further includes the second certificate image identification module 21, certificate number identification module
22, certificate numbering module 23 and the second verification result obtain module 24.
Second certificate image identification module 21 is calculated if being two class applying types for applying type using certificate identification
Method carries out information identification to each certificate image, obtains the corresponding perfect instrument information of each certificate image.
Certificate number identification module 22 is obtained for calling certificate number identification script to identify perfect instrument information
Part of collecting evidence is numbered.
Certificate numbering module 23, it is corresponding with the type of credential that certificate image carries for being sent to certificate number
Certificate information query interface, obtain and number associated ID card No. with certificate.
Second verification result obtains module 24, if being the same ID card No. for all ID card No., obtains
The data verification result that is verified simultaneously is sent to client.
Further, after the first verification result obtains module 17 or the second verification result obtains module 24, the number
It further include that audit data transmission blocks and auditing result obtain module according to verifying device.
Data transmission blocks are audited, for being sent to audit by auditing interface for the intention amount of money and perfect instrument information
Engine.
Auditing result obtains module, is based on the intention amount of money and the corresponding audit of perfect instrument information for obtaining audit engine
The amount of money assessment result that rule obtains after being assessed, and amount of money assessment result is sent to client by data verification request
End.
Further, preprocessing module 12 includes gray processing processing unit, convolution processing unit, computing unit and certificate figure
As acquiring unit
Gray processing processing unit obtains gray level image for carrying out gray processing processing to original certificate.
Convolution processing unit obtains process of convolution for carrying out process of convolution to gray level image using Laplace operator
Data.
Computing unit calculates process of convolution data for calculating function using standard deviation, obtains process of convolution number
According to corresponding standard deviation, and by handling standard deviation, the corresponding variance of standard deviation is obtained.
Certificate image acquiring unit, for variance to be compared with Fuzzy Threshold, if variance is greater than or equal to fuzzy threshold
Value then carries out correction process to original certificate by the rectification function, obtains certificate image.
Further, contour images searching module 13 includes frame detection unit and effective contour screening unit.
It is corresponding to obtain certificate image for detecting using frame detection algorithm to certificate image for frame detection unit
At least one effective contour image.
Effective contour screening unit, for using the nominal contour in profile alignment algorithm to the progress time of effective contour image
It goes through, obtains with the matched effective contour image of nominal contour as objective contour image.
Further, the first certificate image identification module 15 or the second certificate image identification module 21 include text location
Unit, word recognition unit, certificate stencil acquiring unit and perfect instrument information acquisition unit.
Text location unit is obtained for being positioned using text detection network model to the text in certificate image
The corresponding text box of each character area in certificate image, and text box is cut, obtain image to be classified.
Word recognition unit obtains to be sorted for carrying out Text region to image to be classified using image recognition technology
Text.
Certificate stencil acquiring unit, the type of credential for being carried based on certificate image are obtained corresponding with type of credential
Certificate stencil.
Perfect instrument information acquisition unit is divided for treating classifying text based on the certificate identifier on certificate stencil
Class obtains the corresponding perfect instrument information of certificate image.
Specific about data verification device limits the restriction that may refer to above for data verification method, herein not
It repeats again.Modules in above-mentioned data verification device can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 8.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The data that the database of machine equipment is related in verification method for storing data.The network interface of the computer equipment be used for
External terminal passes through network connection communication.To realize a kind of data verification method when the computer program is executed by processor.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor realize the data verification of above-described embodiment when executing computer program
Method, such as the step of step S11- shown in Fig. 2 S17 perhaps step shown in step S21- step S24 or Fig. 3 to Fig. 6,
To avoid repeating, which is not described herein again.Alternatively, processor realizes this embodiment of data verification device when executing computer program
In each module/unit function, such as module shown in Fig. 7 11 to module 17 function or module 21 to module 24
Function, to avoid repeating, which is not described herein again.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes the data verification method of above-described embodiment when being executed by processor, for example, the step of step S11- shown in Fig. 2 S17 or
Step shown in person's step S21- step S24 or Fig. 3 to Fig. 6, to avoid repeating, which is not described herein again.Alternatively, calculating
The function of each module/unit in this embodiment of data verification device, such as Fig. 7 institute are realized when machine program is executed by processor
The module 11 shown to module 17 function or module 21 to the function of module 24, to avoid repeating, which is not described herein again.
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,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
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 data rate sdram (DDRSDRAM), 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 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 described device is divided into different functional unit or module, more than completing
The all or part of function of description.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained 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 for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of data verification method characterized by comprising
The data verification request that client is sent is obtained, the data verification request includes applying type and the applying type pair
At least two original certificates answered；
The original certificate is pre-processed, certificate image is obtained；
If the applying type is a kind of applying type, using frame detection algorithm and profile alignment algorithm at least two institutes
It states certificate image to be handled, obtains the corresponding objective contour image of each certificate image；
Each objective contour image is input in pre-configured face matched interfaces and carries out face matching respectively, is obtained
Take the corresponding face matching result of each objective contour image；
Information identification is carried out to each certificate image using certificate recognizer, it is corresponding to obtain each certificate image
Perfect instrument information；
The perfect instrument information is screened by keyword, obtains target certificate information, and demonstrate,prove all targets
Part information carries out consistency on messaging verifying, obtains consistency checking result；
If all face matching results are successful match, and the consistency checking result is to be verified, then obtains
The data verification result that is verified simultaneously is sent to the client.
2. data verification method as described in claim 1, which is characterized in that the certificate image carries type of credential；Institute
State data verification method further include:
If the applying type is two class applying types, information is carried out to each certificate image using certificate recognizer
Identification obtains the corresponding perfect instrument information of each certificate image；
It calls certificate number identification script to identify the perfect instrument information, obtains certificate number；
Certificate number is sent to certificate information query interface corresponding with the type of credential that the certificate image carries,
It obtains and numbers associated ID card No. with the certificate；
If all ID card No. are the same ID card No., obtain the data verification result being verified and send
To client.
3. data verification method as claimed in claim 1 or 2, which is characterized in that the data verification request further includes intention
The amount of money；After the data verification result for obtaining and being verified, the data verification method further include:
By the intention amount of money and the perfect instrument information, audit engine is sent to by auditing interface；
The audit engine is obtained to be assessed based on the intention amount of money and the corresponding auditing rule of the perfect instrument information
The amount of money assessment result obtained afterwards, and the amount of money assessment result is sent to client by data verification request.
4. data verification method as described in claim 1, which is characterized in that it is described that the original certificate is pre-processed,
Obtain certificate image, comprising:
Gray processing processing is carried out to the original certificate, obtains gray level image；
Process of convolution is carried out to the gray level image using Laplace operator, obtains process of convolution data；
Function is calculated using standard deviation to calculate the process of convolution data, obtains the corresponding mark of the process of convolution data
It is quasi- poor, and by handling the standard deviation, obtain the corresponding variance of the standard deviation；
The variance is compared with Fuzzy Threshold, if the variance is greater than or equal to the Fuzzy Threshold, passes through correction
Function carries out correction process to the original certificate, obtains certificate image.
5. data verification method as described in claim 1, which is characterized in that described to be compared using frame detection algorithm and profile
Algorithm handles at least two certificate images, obtains the corresponding objective contour image of each certificate image, packet
It includes:
The certificate image is detected using frame detection algorithm, obtain the certificate image it is corresponding at least one effectively
Contour images；
The effective contour image is traversed using the nominal contour in profile alignment algorithm, is obtained and the nominal contour
Matched effective contour image is as objective contour image.
6. data verification method as claimed in claim 1 or 2, which is characterized in that described to use certificate recognizer to each
The certificate image carries out information identification, obtains the corresponding perfect instrument information of each certificate image, comprising:
The text in the certificate image is positioned using text detection network model, obtains each text in the certificate image
The corresponding text box in block domain, and the text box is cut, obtain image to be classified；
Text region is carried out to the image to be classified using image recognition technology, obtains text to be sorted；
Based on the type of credential that the certificate image carries, certificate stencil corresponding with the type of credential is obtained；
Classified based on the certificate identifier on the certificate stencil to the text to be sorted, it is corresponding to obtain the certificate image
Perfect instrument information.
7. a kind of data verification device characterized by comprising
Checking request obtains module, and for obtaining the data verification request of client transmission, the data verification request includes Shen
It please type and corresponding at least two original certificate of the applying type；
Preprocessing module obtains certificate image for pre-processing to the original certificate；
Contour images searching module uses frame detection algorithm and wheel if being a kind of applying type for the applying type
Wide alignment algorithm handles at least two certificate images, obtains the corresponding objective contour figure of each certificate image
Picture；
Face matching module divides for each objective contour image to be input in pre-configured face matched interfaces
Not carry out face matching, obtain the corresponding face matching result of each objective contour image；
First certificate image identification module, for carrying out information identification to each certificate image using certificate recognizer,
Obtain the corresponding perfect instrument information of each certificate image；
Information sifting module, for being screened by keyword to the perfect instrument information, acquisition target certificate information, and
Consistency on messaging verifying is carried out to all target certificate informations, obtains consistency checking result；
First verification result obtains module, if being successful match for all face matching results, and the consistency
Verification result is to be verified, then obtains the data verification result being verified and be sent to the client.
8. data verification device as claimed in claim 7, which is characterized in that the data verification device further include:
Second certificate image identification module uses certificate recognizer if being two class applying types for the applying type
Information identification is carried out to the certificate image, obtains the corresponding perfect instrument information of each certificate image；
Certificate number identification module is obtained for calling certificate number identification script to identify the perfect instrument information
Certificate number；
Certificate numbering module, it is opposite with the type of credential that the certificate image carries for being sent to certificate number
The certificate information query interface answered obtains and numbers associated ID card No. with the certificate；
Second verification result obtains module, if being the same ID card No. for all ID card No., acquisition is tested
It demonstrate,proves the data verification result passed through and is sent to client.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to
Any one of 6 data verification methods.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In realization data verification method as described in any one of claim 1 to 6 when the computer program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910429736.3A CN110287971B (en) | 2019-05-22 | 2019-05-22 | Data verification method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910429736.3A CN110287971B (en) | 2019-05-22 | 2019-05-22 | Data verification method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110287971A true CN110287971A (en) | 2019-09-27 |
| CN110287971B CN110287971B (en) | 2023-11-14 |
Family
ID=68002228
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910429736.3A Active CN110287971B (en) | 2019-05-22 | 2019-05-22 | Data verification method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110287971B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110888881A (en) * | 2019-11-21 | 2020-03-17 | 望海康信(北京)科技股份公司 | Picture association method and device, computer equipment and storage medium |
| CN111046879A (en) * | 2019-10-15 | 2020-04-21 | 平安科技（深圳）有限公司 | Certificate image classification method and device, computer equipment and readable storage medium |
| CN111178238A (en) * | 2019-12-25 | 2020-05-19 | 未鲲(上海)科技服务有限公司 | Certificate testing method, device, equipment and computer readable storage medium |
| CN111428132A (en) * | 2020-03-18 | 2020-07-17 | 腾讯科技（深圳）有限公司 | Data verification method and device, computer storage medium and electronic equipment |
| CN111459936A (en) * | 2020-03-25 | 2020-07-28 | 湖南华菱涟源钢铁有限公司 | Data management method, data management device and server |
| CN111553431A (en) * | 2020-04-30 | 2020-08-18 | 上海眼控科技股份有限公司 | Picture definition detection method and device, computer equipment and storage medium |
| CN111709855A (en) * | 2020-06-17 | 2020-09-25 | 中国银行股份有限公司 | Fund escrow method, device, storage medium and equipment based on OCR |
| CN112215225A (en) * | 2020-10-22 | 2021-01-12 | 北京通付盾人工智能技术有限公司 | KYC certificate verification method based on computer vision technology |
| CN112328745A (en) * | 2020-11-05 | 2021-02-05 | 深圳壹账通智能科技有限公司 | Service application method, device, computer equipment and storage medium |
| CN112487982A (en) * | 2020-11-30 | 2021-03-12 | 乐刷科技有限公司 | Merchant information auditing method, system and storage medium |
| CN112734564A (en) * | 2021-01-11 | 2021-04-30 | 无锡锡商银行股份有限公司 | House information verification method for remote household release of house mortgage loan |
| CN113112237A (en) * | 2021-04-20 | 2021-07-13 | 上海市环境科学研究院 | Information management method and system for environmental protection verification |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090152357A1 (en) * | 2007-12-12 | 2009-06-18 | 3M Innovative Properties Company | Document verification using dynamic document identification framework |
| WO2017140218A1 (en) * | 2016-02-18 | 2017-08-24 | 阿里巴巴集团控股有限公司 | Information identification method and device |
| CN107808118A (en) * | 2017-09-28 | 2018-03-16 | 平安科技（深圳）有限公司 | Personal identification method, electronic installation and computer-readable recording medium |
| WO2018192406A1 (en) * | 2017-04-20 | 2018-10-25 | 腾讯科技（深圳）有限公司 | Identity authentication method and apparatus, and storage medium |
| CN109359691A (en) * | 2018-10-24 | 2019-02-19 | 全链通有限公司 | Auth method and system based on block chain |
| CN109446900A (en) * | 2018-09-21 | 2019-03-08 | 平安科技（深圳）有限公司 | Certificate authenticity verification method, apparatus, computer equipment and storage medium |
-
2019
- 2019-05-22 CN CN201910429736.3A patent/CN110287971B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090152357A1 (en) * | 2007-12-12 | 2009-06-18 | 3M Innovative Properties Company | Document verification using dynamic document identification framework |
| WO2017140218A1 (en) * | 2016-02-18 | 2017-08-24 | 阿里巴巴集团控股有限公司 | Information identification method and device |
| WO2018192406A1 (en) * | 2017-04-20 | 2018-10-25 | 腾讯科技（深圳）有限公司 | Identity authentication method and apparatus, and storage medium |
| CN107808118A (en) * | 2017-09-28 | 2018-03-16 | 平安科技（深圳）有限公司 | Personal identification method, electronic installation and computer-readable recording medium |
| WO2019062080A1 (en) * | 2017-09-28 | 2019-04-04 | 平安科技（深圳）有限公司 | Identity recognition method, electronic device, and computer readable storage medium |
| CN109446900A (en) * | 2018-09-21 | 2019-03-08 | 平安科技（深圳）有限公司 | Certificate authenticity verification method, apparatus, computer equipment and storage medium |
| CN109359691A (en) * | 2018-10-24 | 2019-02-19 | 全链通有限公司 | Auth method and system based on block chain |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111046879A (en) * | 2019-10-15 | 2020-04-21 | 平安科技（深圳）有限公司 | Certificate image classification method and device, computer equipment and readable storage medium |
| CN111046879B (en) * | 2019-10-15 | 2023-09-29 | 平安科技（深圳）有限公司 | Certificate image classification method, device, computer equipment and readable storage medium |
| CN110888881B (en) * | 2019-11-21 | 2023-03-10 | 望海康信(北京)科技股份公司 | Picture association method and device, computer equipment and storage medium |
| CN110888881A (en) * | 2019-11-21 | 2020-03-17 | 望海康信(北京)科技股份公司 | Picture association method and device, computer equipment and storage medium |
| CN111178238A (en) * | 2019-12-25 | 2020-05-19 | 未鲲(上海)科技服务有限公司 | Certificate testing method, device, equipment and computer readable storage medium |
| CN111428132A (en) * | 2020-03-18 | 2020-07-17 | 腾讯科技（深圳）有限公司 | Data verification method and device, computer storage medium and electronic equipment |
| CN111428132B (en) * | 2020-03-18 | 2023-09-19 | 腾讯科技（深圳）有限公司 | Data verification method and device, computer storage medium and electronic equipment |
| CN111459936A (en) * | 2020-03-25 | 2020-07-28 | 湖南华菱涟源钢铁有限公司 | Data management method, data management device and server |
| CN111459936B (en) * | 2020-03-25 | 2023-09-29 | 湖南华菱涟源钢铁有限公司 | Data management method, data management device and server |
| CN111553431A (en) * | 2020-04-30 | 2020-08-18 | 上海眼控科技股份有限公司 | Picture definition detection method and device, computer equipment and storage medium |
| CN111709855A (en) * | 2020-06-17 | 2020-09-25 | 中国银行股份有限公司 | Fund escrow method, device, storage medium and equipment based on OCR |
| CN112215225A (en) * | 2020-10-22 | 2021-01-12 | 北京通付盾人工智能技术有限公司 | KYC certificate verification method based on computer vision technology |
| CN112215225B (en) * | 2020-10-22 | 2024-03-15 | 北京通付盾人工智能技术有限公司 | KYC certificate verification method based on computer vision technology |
| CN112328745A (en) * | 2020-11-05 | 2021-02-05 | 深圳壹账通智能科技有限公司 | Service application method, device, computer equipment and storage medium |
| CN112487982A (en) * | 2020-11-30 | 2021-03-12 | 乐刷科技有限公司 | Merchant information auditing method, system and storage medium |
| CN112734564A (en) * | 2021-01-11 | 2021-04-30 | 无锡锡商银行股份有限公司 | House information verification method for remote household release of house mortgage loan |
| CN113112237A (en) * | 2021-04-20 | 2021-07-13 | 上海市环境科学研究院 | Information management method and system for environmental protection verification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110287971B (en) | 2023-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110287971A (en) | Data verification method, device, computer equipment and storage medium | |
| RU2733115C1 (en) | Method and apparatus for verifying certificates and identities | |
| US10332118B2 (en) | Efficient prevention of fraud | |
| CN109472918A (en) | Invoice validation method, financing checking method, device, equipment and medium | |
| EP3678049A1 (en) | Document verification and identity verification method and device | |
| US9483629B2 (en) | Document authentication based on expected wear | |
| KR102406432B1 (en) | Identity authentication methods and devices, electronic devices and storage media | |
| US20140270404A1 (en) | Efficient prevention of fraud | |
| US20140270409A1 (en) | Efficient prevention of fraud | |
| CN113128271A (en) | Counterfeit detection of face images | |
| US20210312263A1 (en) | Techniques For Matching Disparate Input Data | |
| CN107609364A (en) | User identification confirmation method and apparatus | |
| CN111709413A (en) | Certificate verification method and device based on image recognition, computer equipment and medium | |
| CN114187449A (en) | Vehicle information processing method, device, computer equipment and storage medium | |
| Al Qudah et al. | Using Artificial Intelligence Applications For E-Government Services As Iris Recognition | |
| CN115035533B (en) | Data authentication processing method and device, computer equipment and storage medium | |
| WO2023192808A1 (en) | Authentication of age, gender, and other biometric data from live images of users | |
| US11783030B2 (en) | Defense mechanism against component-wise hill climbing using synthetic face generators | |
| CN116071835B (en) | Face recognition attack post screening method and device and electronic equipment | |
| CN117576826B (en) | Financial self-service terminal and credit giving processing method based on same | |
| Chen et al. | A New ID Verification and Image Recognition Framework for Risk Management | |
| Goud et al. | Fraudulence Detection of Medical Images using Pixel Level Algorithm | |
| CN115147209A (en) | Credit investigation authorization bookmark deployment method, system, equipment and storage medium | |
| Kumar et al. | Digital Signature Verification using Support Vector Machine | |
| WO2024052054A1 (en) | Method for determining the quality of a captured image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |