CN108171113A - A kind of identity authentication method and system - Google Patents
A kind of identity authentication method and system Download PDFInfo
- Publication number
- CN108171113A CN108171113A CN201711252474.5A CN201711252474A CN108171113A CN 108171113 A CN108171113 A CN 108171113A CN 201711252474 A CN201711252474 A CN 201711252474A CN 108171113 A CN108171113 A CN 108171113A
- Authority
- CN
- China
- Prior art keywords
- image
- photo
- text
- card
- image comparison
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian 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
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- 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
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
- G06V10/464—Salient features, e.g. scale invariant feature transforms [SIFT] using a plurality of salient features, e.g. bag-of-words [BoW] representations
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Probability & Statistics with Applications (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention proposes a kind of identity authentication method and system, and described method includes following steps:Step 1 carries out scene to user and takes pictures, obtains scene photograph;The identity card of user is scanned by step 2, obtains ID Card Image;The scene photograph and ID Card Image are carried out image comparison by step 3, and the authentication failure if image comparison result is mismatches enters step four if image comparison result matches;Step 4 is compared the photo in scene photograph and big data picture data library one by one, the authentication failure if image comparison result is mismatches, the certification success if image comparison result matches.Personal identification can effectively be carried out by the present invention, criminal can effectively be taken precautions against and carry out financial swindling, network fraud, telephone fraud using the identity card that other people lose, objectively reduce the opportunity of offender, reduce personal and social loss.
Description
Technical field
The present invention relates to technical field of data processing more particularly to a kind of identity authentication methods and system.
Background technology
At present, illegal activity, public security department and financial system are carried out using false identity card in order to prevent criminal
The departments of grade establish identification system networking, have effectively contained and have carried out illegal activity using false identity card.It is but raw in reality
In work, identity card is lost or to be stolen phenomenon more universal, and criminal then carries out work of breaking laws and commit crime using other people real identity cards
It is dynamic, be by common several class means of crime:
1st, credit card fraud.Criminal's card that claims the identity of others fraudulently opens an account in bank and handles credit card, Ran Houli
Malicious overdraft is carried out with credit card.
2nd, loan swindle.Criminal claims the identity of others fraudulently to demonstrate,prove and refuse to return after bank handles loan.
3rd, contract is swindled.Criminal claims the identity of others fraudulently card, and with other people names, deal contract swindle payment for goods is signed with people
Cargo.
4th, claim the identity of others fraudulently certificate company incorporated, false capital contribution.(1) " shell company " is registered, then by first paying
Small check gains wholesale business by cheating again after obtaining the trust of client;(2) company of fake registrations first opens an account in bank and gets
Then banker's check is issued check with ghost account and is swindled to other people loans secured.
5th, telecom charges are swindled.Criminal claims the identity of others fraudulently to demonstrate,prove handles networking formality in telecommunications company, mad later to beat
Endlessly refuse to pay telecom charges;Or the card that claims the identity of others fraudulently applies to install ISDN private telephones, externally makees public telephone use, to be less than just
Normal telephone expenses standard collects telephone expenses, after escape when telecommunication bureau collects the charges.
6th, the card that claims the identity of others fraudulently carries out swindle on the net.Criminal's card data that claims the identity of others fraudulently is concurrent in network registry
Cloth message claims it to have the sales such as mobile phone, second-hand limousine, and leaves the ID card No., while by the unit on identity card
Title also serves as prestige and ensures fax to purchaser, and fooled person has converged money and confiscated arrival object space and know and be deceived.
7th, the card that claims the identity of others fraudulently is reported the loss, and draws cash in banks in advance.
8th, swindle is implemented in the card delivery of cargo that claims the identity of others fraudulently.
However, the method still do not taken precautions against effectively the identity card swindle after loss at present, can not often prevent
The generation of the events such as financial swindling recited above, network fraud, phone fraud.For example, when user removes bank's transacting business,
To prevent other people from holding non-personal identification papers' transacting business, often bank can take pictures to transactor, and pass through observation identity card
Photo is confirmed with me.However aforesaid way is of problems, such as because of some identity card pictures because shooting
Long, discrepancy may be had with appearance during my transacting business, causes some users can not transacting business;In addition, if there is violating
Guilty molecule is wanted to pretend to be identity card, it can be made to seem the extremely phase in appearance and identity card by means such as makeups
Seemingly, so as to complete the criminal offences such as financial swindling.
Invention content
To solve problem above, the purpose of the present invention is what is be achieved through the following technical solutions.
The present invention proposes a kind of identity authentication method, includes the following steps:
Step 1 carries out scene to user and takes pictures, obtains scene photograph;
The identity card of user is scanned by step 2, obtains ID Card Image;
The scene photograph and identity card picture are carried out image comparison by step 3, if image comparison result is not
Fail with then authentication, four are entered step if image comparison result matches;
Step 4 is compared the photo in scene photograph and big data picture data library, one by one if image comparison
As a result fail to mismatch then authentication, the certification success if image comparison result matches.
Preferably, the image comparison in the step 3 and/or step 4 uses fuzzy algorithmic approach.
Preferably, the fuzzy algorithmic approach is divided into following four step:
(1) Walsh transformation is carried out to scene photograph and ID Card Image respectively, respectively obtained after Walsh transformation
Image;
(2) image of the above-mentioned two after Walsh transformation is split respectively, is divided into the identical several areas of quantity
Domain;
(3) corresponding region of latter two segmented image is compared successively, and similarity judgment value is provided for each region;
(4) judge whether whole former scene photograph and ID Card Image match.
Preferably, the photo in the big data picture data library in the step 4 is to capture network by crawler algorithm
Piece and obtain.
Preferably, the crawler algorithm is divided into following five steps:
(1) using Dewey Decimal Classification, the stage is extracted in photo eigen, it is crucial with Anchor Text to rapidly find out photo text
Keyword similar in word theme;
(2) theme candidate link feature text is extracted;
(3) classified using Naive Bayes Classifier to candidate link theme edge text, obtain theme phase
Look after piece;If text belongs to specific subject, then corresponding candidate link is with weights grade value as priority of classifying, with preferential
The size order of grade is inserted into queue of creeping, and reptile preferentially accesses the big link of classification value, if text is not belonging to specific subject,
Abandon candidate link;
(4) its corresponding technorati authority and centrad are calculated with HITS algorithms to the Web link information of relevant picture, it is comprehensive
Information, reversed webpage, brother's link of backward chaining, URL link, prejudge photo to be crawled and master near Anchor Text, Anchor Text
The degree of correlation of topic;
(5) when the degree of correlation for crawling photo and theme is more than certain threshold value, photo to be crawled described in crawl is counted to big
Among picture data library.
According to another aspect of the present invention, additionally provide a kind of system of authentication, including be linked in sequence as
Lower module:
Photo module takes pictures for carrying out scene to user, obtains scene photograph;
Scan module is scanned for the identity card to user, obtains ID Card Image;
First image comparison module, for the scene photograph and identity card picture to be carried out image comparison, if image
Comparing result fails to mismatch then authentication, enters the second image comparison module if image comparison result matches;
Second image comparison module is right one by one for the photo in scene photograph and big data picture data library to be carried out
Than, the authentication failure if image comparison result is mismatches, the certification success if image comparison result matches.
Preferably, wherein described first image contrast module is including being linked in sequence such as lower unit:
Walsh transformation unit for carrying out Walsh transformation to scene photograph and ID Card Image respectively, respectively obtains
Image after Walsh transformation;
Image segmentation unit for being split respectively to image of the above-mentioned two after Walsh transformation, is divided into number
Measure identical several regions;
Similarity judging unit, it is equal for each region for comparing the corresponding region of latter two segmented image successively
Provide similarity judgment value;
Matching judgment unit, for judging whether whole former scene photograph and ID Card Image match.
Preferably, if region quantity of the similarity judgment value more than 80% accounts for the 80% of whole image cut zone quantity
More than, then former scene photograph and ID Card Image matching are assert, whereas if similarity judgment value is more than 80% region quantity
The 80% of whole image cut zone quantity is accounted for hereinafter, then assert that former scene photograph and ID Card Image mismatch.
Preferably, the second image comparison module is including being linked in sequence such as lower unit:
Photo eigen extraction unit for using Dewey Decimal Classification, extracts the stage in photo eigen, rapidly finds out photograph
Piece text and keyword similar in Anchor Text keyword subject;
Feature Text Feature Extraction unit, for extracting theme candidate link feature text;
Taxon, for being classified using Naive Bayes Classifier to candidate link theme edge text,
Obtain theme relevant picture;If text belongs to specific subject, then corresponding candidate link is to classify weights as priority
Grade value is inserted into queue of creeping with the size order of priority, and reptile preferentially accesses the big link of classification value, if text is not belonging to
Specific subject then abandons candidate link;
The degree of correlation prejudges unit, its corresponding power is calculated with HITS algorithms for the Web link information to relevant picture
Prestige degree and centrad integrate Anchor Text, Anchor Text nearby information, reversed webpage, brother's link of backward chaining, URL link, in advance
Sentence the degree of correlation of photo and theme to be crawled;
Placement unit, when wait crawl photo and theme the degree of correlation be more than certain threshold value when, photo to be crawled described in crawl
To among big data picture data library.
Preferably, the threshold value is 90%.
Personal identification can effectively be carried out by the present invention, criminal can be effectively taken precautions against and be lost using other people
Identity card carry out financial swindling, network fraud, telephone fraud, objectively reduce the opportunity of offender, reduce
Personal and social loss.
Description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this field
Technical staff will become clear.Attached drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Attached drawing 1 shows the identity authentication method flow chart according to embodiment of the present invention.
Attached drawing 2 shows the method that image comparison is carried out according to the scene photograph and identity card picture of embodiment of the present invention
Flow chart.
Attached drawing 3 shows the method flow diagram that big data picture data library is obtained using crawler algorithm.
Attached drawing 4 shows the system module figure according to the authentication of embodiment of the present invention.
Attached drawing 5 shows the structure chart of the first image comparison module according to embodiment of the present invention.
Attached drawing 6 shows the structure chart of the second image comparison module according to embodiment of the present invention.
Specific embodiment
The illustrative embodiments of the disclosure are more fully described below with reference to accompanying drawings.Although this public affairs is shown in attached drawing
The illustrative embodiments opened, it being understood, however, that may be realized in various forms the disclosure without the reality that should be illustrated here
The mode of applying is limited.It is to be able to be best understood from the disclosure, and can be by this public affairs on the contrary, providing these embodiments
The range opened completely is communicated to those skilled in the art.
Specifically, as shown in Figure 1, the present invention proposes a kind of identity authentication method, include the following steps:
Step S101 carries out scene to user and takes pictures, obtains scene photograph;
The identity card of user is scanned by step S102, obtains ID Card Image;
The scene photograph and identity card picture are carried out image comparison by step S103, if image comparison result is not
Then authentication fails for matching, and S104 is entered step if image comparison result matches;
Step S104 is compared the photo in scene photograph and big data picture data library, one by one if image pair
Fail than result to mismatch then authentication, the certification success if image comparison result matches.
The specific implementation of each step is described in detail below:
Step S101, it carries out scene to user to take pictures, obtains scene photograph.For example, when user removes bank's transacting business,
To prevent other people from holding non-personal identification papers' transacting business, often bank can use the photo of camera shooting transactor as note
Record.
The identity card of user is scanned by step S102, obtains ID Card Image.For example, after having shot user picture,
The identity card of scanner scanning user can be used, to obtain ID card information and store.
The scene photograph and identity card picture are carried out image comparison by step S103, if image comparison result is not
Then authentication fails for matching, and S104 is entered step if image comparison result matches.
In the step, present invention novelty proposes a kind of new image processing algorithm, i.e. fuzzy algorithmic approach.Such as Fig. 2
Shown, the fuzzy algorithmic approach specifically includes following steps:
S1031, Walsh transformation is carried out to scene photograph and ID Card Image respectively, respectively obtained after Walsh transformation
Image.Because the array of image is larger, if directly taking processing operation in space, very big calculation amount can be brought,
Influence the final effect of image procossing.It by using Walsh transformation, can significantly reduce the calculation amount of image procossing, be promoted
The effect of image production.
Walsh function Wal (k, t) is to propose U.S. mathematician J.L. Walsh (J.L.Walsh) nineteen twenty-threes, definition
In 0≤t of half open interval<1 one group of complete, orthogonal rectangular function.Function only takes+1 and -1 two value.Obviously, its sampling
Only+1 is worth with -1 two, corresponding to the two states in Digital Logic, particularly suitable for Digital Signal Processing.Walsh transformation
Compared with Fourier transformation, due to it only exist real number plus, subtraction without plural number multiplying so that calculate speed
Degree is fast, memory space is few, is conducive to hardware realization, to handling in real time and mass data operation has specific appeal.In image
Processing in communication system due to its orthogonality and has many advantages, such as that value and algorithm are simple, is answered convenient for the orthogonal multichannel of composition
Use system.
S1032, image of the above-mentioned two after Walsh transformation is split respectively, is divided into identical several of quantity
Region.The method of segmentation is numerous, for example, since portrait is often in the middle section of picture, then it can be to image middle section
The more a certain number of regions of Ground Split, and the edge part of picture is divided to less region quantity;In another example due to
The difference degree of portrait facial characteristics is larger, then can divide more region in the center-top of portrait picture, and at it
The less region of his partial segmentation.The quantity of two image segmentations and the size of each segmentation block are had in correspondence with each other, with profit
Similarity later judges.
S1033, the corresponding region for comparing latter two segmented image successively provide similarity for each region and judge
Value.If for example, in the corresponding region in two positions, the identical corresponding pixel points of pixel value are n%, then it is assumed that its similarity is
N%.Because the detail sections such as portrait face, profile are different for the reflectance of light, gray scale size is reflected as on photo
The difference of difference, in other words pixel value size.For example, human eye is often presented more black color, and face often present it is partially white or
It is partially yellow to wait compared with weak color.
S1034, judge whether whole former scene photograph and ID Card Image match.If for example, similarity judgment value
Region quantity more than 80% accounts for more than 80% whole image cut zone quantity, then assert former scene photograph and identity card figure
As matching, whereas if similarity judgment value more than 80% region quantity account for the 80% of whole image cut zone quantity with
Under, then assert that former scene photograph and ID Card Image mismatch.
Step S104 is compared the photo in scene photograph and big data picture data library, one by one if image pair
Fail than result to mismatch then authentication, the certification success if image comparison result matches.In the step S104
Photo in big data picture data library is to capture network picture by crawler algorithm to obtain.Described image is still adopted when comparing
With the fuzzy algorithmic approach in step S103, details are not described herein again.
In the step, present invention novelty proposes a kind of new image-capture algorithm, i.e. crawler algorithm.Such as Fig. 3
Shown, the crawler algorithm specifically includes following steps:
The web crawlers method includes the following steps:
S1041, using Dewey Decimal Classification, extract the stage in photo eigen, rapidly find out photo text and Anchor Text
Keyword similar in keyword subject;For example, the keyword can be the name of user, ID card No. etc..
S1042, extraction theme candidate link feature text;For example, the name or ID card No. of extraction user.
S1043, classified using Naive Bayes Classifier to candidate link theme edge text, obtain theme
Relevant picture;If text belongs to specific subject, then corresponding candidate link is with weights grade value as priority of classifying, with excellent
The size order of first grade is inserted into queue of creeping, and reptile preferentially accesses the big link of classification value, if text is not belonging to specific subject,
Then abandon candidate link;For example, the theme can be the name of user, ID card No. etc..
S1044, its corresponding technorati authority and centrad are calculated with HITS algorithms to the Web link information of relevant picture,
Information, reversed webpage, brother's link of backward chaining, URL link, prejudge photo to be crawled near comprehensive Anchor Text, Anchor Text
With the degree of correlation of theme.For example, the theme can be the name of user, ID card No. etc..
S1045, when the degree of correlation for crawling photo and theme is more than certain threshold value (such as 90%), waiting to climb described in crawl
It takes among photo to big data picture data library.Today's society, the application of a large amount of social networks, such as wechat, microblogging, QQ etc.
It emerges in an endless stream, in addition also have some real names or non-real-name authentication website such as Jingdone district, Taobao etc. or for example personal publishes
Monograph, paper, the meeting participated in, the very more occasion of news conference etc., often all can upload and show user photo,
ID card information etc..These personal information can all leave a trace in a network.The present invention captures net by using crawler algorithm
In network and identity card is bound or relevant photographic intelligence, thus the update big data picture data library of not timing, so as to
Various aspects even also more accurately can provide strong guarantee for personal identification sometimes.
Associated mechanisms mentioned by the present invention are related to many mechanisms, including public security, bank, industry and commerce, education, insurance, telecommunications
Etc..These mechanisms are mainly national sector or unit, for example, public security system, educational system, credit investigation system, Credit Information System, gold
Melt system, investment and financing system etc..Including public security bureau, each big bank, university, insurance company, China Mobile, China Unicom etc.
Common mechanism.
As shown in figure 4, the present invention also provides a kind of system 100 of authentication, including being linked in sequence such as lower die
Block:
Photo module 101 takes pictures for carrying out scene to user, obtains scene photograph;
Scan module 102 is scanned for the identity card to user, obtains ID Card Image;
First image comparison module 103, for the scene photograph and identity card picture to be carried out image comparison, if figure
As comparing result, for mismatch, then authentication fails, and enters the second image comparison module if image comparison result matches
104;
Second image comparison module 104, for the photo in scene photograph and big data picture data library to be carried out one by one
Comparison, the authentication failure if image comparison result is mismatches, the certification success if image comparison result matches.
As shown in figure 5, wherein described first image contrast module 103 is including being linked in sequence such as lower unit:
Walsh transformation unit 1031, for carrying out Walsh transformation to scene photograph and ID Card Image respectively, respectively
Obtain the image after Walsh transformation.It, can if directly taking processing operation in space because the array of image is larger
Very big calculation amount is brought, influences the final effect of image procossing.By using Walsh transformation, it can significantly reduce image
The calculation amount of processing promotes the effect of image production.
Image segmentation unit 1032, for being split respectively to image of the above-mentioned two after Walsh transformation, segmentation
Several regions identical for quantity.The method of segmentation is numerous, for example, since portrait is often in the middle section of picture, then may be used
With to the image middle section a certain number of regions of more Ground Split, and the edge part of picture is divided to less region
Quantity;In another example the difference degree due to portrait facial characteristics is larger, then can the center-top of portrait picture divide compared with
More regions, and divide less region in other parts.The quantity of two image segmentations and the size of each segmentation block are certain
It will in correspondence with each other, so that similarity below judges.
Similarity judging unit 1033, for comparing the corresponding region of latter two segmented image successively, for each area
Domain provides similarity judgment value.For example, if in the corresponding region in two positions, the identical corresponding pixel points of pixel value are
N%, then it is assumed that its similarity is n%.Because the detail sections such as portrait face, profile are different for the reflectance of light, shining
On piece is reflected as the difference of gray scale size, in other words the difference of pixel value size.For example, more black color is often presented in human eye,
And partially white or Huang etc. partially is often presented compared with weak color in face.
Matching judgment unit 1034, for judging whether whole former scene photograph and ID Card Image match.For example, such as
Region quantity of the fruit similarity judgment value more than 80% accounts for more than the 80% of whole image cut zone quantity, then assert former scene
Photo and ID Card Image matching, whereas if region quantity of the similarity judgment value more than 80% accounts for whole image cut section
The 80% of domain quantity is hereinafter, then assert that former scene photograph and ID Card Image mismatch.
As shown in fig. 6, wherein described second image comparison module 104 is including being linked in sequence such as lower unit:
Photo eigen extraction unit 1041 for using Dewey Decimal Classification, extracts the stage in photo eigen, quickly looks for
Go out photo text and keyword similar in Anchor Text keyword subject;
Feature Text Feature Extraction unit 1042, for extracting theme candidate link feature text;
Taxon 1043, for being divided using Naive Bayes Classifier candidate link theme edge text
Class obtains theme relevant picture;If text belongs to specific subject, then corresponding candidate link is using weights of classifying as excellent
First grade value is inserted into queue of creeping with the size order of priority, and reptile preferentially accesses the big link of classification value, if text does not belong to
In specific subject, then candidate link is abandoned;
The degree of correlation prejudges unit 1044, its correspondence is calculated with HITS algorithms for the Web link information to relevant picture
Technorati authority and centrad, comprehensive Anchor Text, Anchor Text nearby information, reversed webpage, brother's link of backward chaining, URL chains
It connects, prejudges the degree of correlation of photo and theme to be crawled.
Placement unit 1045, when wait crawl photo and theme the degree of correlation be more than certain threshold value (such as 90%) when, crawl
Among the photo to be crawled to big data picture data library.Today's society, the application of a large amount of social networks, such as wechat,
Microblogging, QQ etc. emerge in an endless stream, and in addition also have some real names or non-real-name authentication website such as Jingdone district, Taobao etc. or such as
The very more occasion of the personal monograph published, paper, the meeting participated in, news conference etc., often all can upload and show user
My photo, ID card information etc..These personal information can all leave a trace in a network.The present invention is by using reptile
Algorithm, captures in network and identity card is bound or relevant photographic intelligence, so as to the update big data picture data of not timing
Library so as to various aspects, even also more accurately can provide strong guarantee for personal identification sometimes.
Personal identification can effectively be carried out by the present invention, criminal can be effectively taken precautions against and be lost using other people
Identity card carry out financial swindling, network fraud, telephone fraud, objectively reduce the opportunity of offender, reduce
Personal and social loss.
Those skilled in the art will also be appreciated that the various illustrative components, blocks that the embodiment of the present invention is listed
(illustrative logical block), unit and step can pass through the knot of electronic hardware, computer software, or both
Conjunction is realized.To clearly show that the replaceability (interchangeability) of hardware and software, above-mentioned various explanations
Property component (illustrative components), unit and step universally describe their function.Such work(
Can be that specific application and the design requirement of whole system are depended on to realize by hardware or software.Those skilled in the art
Can be for each specific function of applying, the realization of various methods can be used described, but this realization is understood not to
Beyond the range of protection of the embodiment of the present invention.
Various illustrative logical blocks or unit described in the embodiment of the present invention can by general processor,
Digital signal processor, application-specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic devices,
Described function is realized or is operated in the design of discrete gate or transistor logic, discrete hardware components or any of the above described combination.
General processor can be microprocessor, optionally, the general processor may be any traditional processor, controller,
Microcontroller or state machine.Processor can also be realized by the combination of computing device, such as digital signal processor and micro-
Processor, multi-microprocessor, one or more microprocessors combine a digital signal processor core or any other like
Configuration realize.
The step of method or algorithm described in the embodiment of the present invention can be directly embedded into hardware, processor perform it is soft
The combination of part module or the two.Software module can be stored in RAM memory, flash memory, ROM memory, EPROM storages
Other any form of storaging mediums in device, eeprom memory, register, hard disk, moveable magnetic disc, CD-ROM or this field
In.Illustratively, storaging medium can be connect with processor, so that processor can read information from storaging medium, and
It can be to storaging medium stored and written information.Optionally, storaging medium can also be integrated into processor.Processor and storaging medium can
To be set in ASIC, ASIC can be set in user terminal.Optionally, processor and storaging medium can also be set to use
In different components in the terminal of family.
In one or more illustrative designs, the described above-mentioned function of the embodiment of the present invention can be in hardware, soft
Part, firmware or the arbitrary of this three combine to realize.If realized in software, these functions can store and computer-readable
It is transmitted on the medium of computer-readable on medium or with one or more instruction or code form.Computer readable medium includes electricity
Brain storaging medium and convenient for allow computer program to be transferred to from a place telecommunication media in other places.Storaging medium can be with
It is that any general or special computer can be with the useable medium of access.For example, such computer readable media can include but
It is not limited to RAM, ROM, EEPROM, CD-ROM or other optical disc storage, disk storage or other magnetic storage devices or other
What can be used for carrying or store with instruct or data structure and it is other can be by general or special computer or general or specially treated
The medium of the program code of device reading form.In addition, any connection can be properly termed computer readable medium, example
Such as, if software is to pass through a coaxial cable, fiber optic cables, double from a web-site, server or other remote resources
Twisted wire, Digital Subscriber Line (DSL) are defined with being also contained in for the wireless way for transmitting such as example infrared, wireless and microwave
In computer readable medium.The disk (disk) and disk (disc) includes compress disk, radium-shine disk, CD, DVD, floppy disk
And Blu-ray Disc, disk is usually with magnetic duplication data, and disk usually carries out optical reproduction data with laser.Combinations of the above
It can also be included in computer readable medium.
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited thereto,
Any one skilled in the art in the technical scope disclosed by the present invention, the change or replacement that can be readily occurred in,
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with the protection model of the claim
Subject to enclosing.
Claims (10)
1. a kind of identity authentication method, includes the following steps:
Step 1 carries out scene to user and takes pictures, obtains scene photograph;
Step 2 is scanned the identity card of user, obtains ID Card Image;
The scene photograph and ID Card Image are carried out image comparison by step 3, if image comparison result is mismatches
Authentication fails, and four are entered step if image comparison result matches;
Step 4 is compared the photo in scene photograph and big data picture data library one by one, if image comparison result
Fail to mismatch then authentication, the certification success if image comparison result matches.
2. identity authentication method as described in claim 1, it is characterised in that:Figure in the step 3 and/or step 4
As comparison is using fuzzy algorithmic approach.
3. identity authentication method as claimed in claim 2, it is characterised in that:The fuzzy algorithmic approach is divided into following four step
Suddenly:
(1) Walsh transformation is carried out to scene photograph and ID Card Image respectively, respectively obtains the image after Walsh transformation;
(2) image of the above-mentioned two after Walsh transformation is split respectively, is divided into the identical several regions of quantity;
(3) corresponding region of latter two segmented image is compared successively, and similarity judgment value is provided for each region;
(4) judge whether whole scene photograph and ID Card Image match.
4. identity authentication method as described in claim 1, it is characterised in that:Big data picture data in the step 4
Photo in library is to capture network picture by crawler algorithm to obtain.
5. identity authentication method as claimed in claim 4, it is characterised in that:The crawler algorithm is divided into following five steps
Suddenly:
(1) using Dewey Decimal Classification, the stage is extracted in photo eigen, rapidly finds out photo text and Anchor Text keyword master
Keyword similar in topic;
(2) theme candidate link feature text is extracted;
(3) classified using Naive Bayes Classifier to candidate link theme edge text, obtain theme and mutually look after
Piece;If text belongs to specific subject, then corresponding candidate link is with weights grade value as priority of classifying, with priority
Size order is inserted into queue of creeping, and reptile preferentially accesses the big link of classification value, if text is not belonging to specific subject, abandons
Candidate link;
(4) its corresponding technorati authority and centrad, comprehensive anchor text are calculated with HITS algorithms to the Web link information of relevant picture
Originally, information, reversed webpage, brother's link of backward chaining, URL link near Anchor Text, prejudge photo and theme to be crawled
The degree of correlation;
(5) when the degree of correlation for crawling photo and theme is more than certain threshold value, photo to be crawled described in crawl to big data shines
Among sheet data library.
6. a kind of system of authentication, including the following module being linked in sequence:
Photo module takes pictures for carrying out scene to user, obtains scene photograph;
Scan module is scanned for the identity card to user, obtains ID Card Image;
First image comparison module, for the scene photograph and identity card picture to be carried out image comparison, if image comparison
As a result fail to mismatch then authentication, enter the second image comparison module if image comparison result matches;
Second image comparison module, for the photo in scene photograph and big data picture data library to be compared one by one, such as
Fruit image comparison result fails to mismatch then authentication, the certification success if image comparison result matches.
7. the system of authentication as claimed in claim 6, it is characterised in that:Wherein described first image contrast module includes
Be linked in sequence such as lower unit:
Walsh transformation unit for carrying out Walsh transformation to scene photograph and ID Card Image respectively, is respectively obtained through fertile
Image after your assorted transformation;
Image segmentation unit for being split respectively to image of the above-mentioned two after Walsh transformation, is divided into quantity phase
Same several regions;
Similarity judging unit for comparing the corresponding region of latter two segmented image successively, provides each region
Similarity judgment value;
Matching judgment unit, for judging whether whole former scene photograph and ID Card Image match.
8. the system of authentication as claimed in claim 7, it is characterised in that:If similarity judgment value is more than 80% area
Domain quantity accounts for more than 80% whole image cut zone quantity, then assert former scene photograph and ID Card Image matching, conversely,
If region quantity of the similarity judgment value more than 80% account for the 80% of whole image cut zone quantity hereinafter, if assert it is former existing
Field photo and ID Card Image mismatch.
9. the system of authentication as claimed in claim 6, it is characterised in that:The second image comparison module includes sequence
Connection such as lower unit:
For using Dewey Decimal Classification, the stage is extracted in photo eigen, rapidly finds out photo text for photo eigen extraction unit
Sheet and keyword similar in Anchor Text keyword subject;
Feature Text Feature Extraction unit, for extracting theme candidate link feature text;
Taxon for being classified using Naive Bayes Classifier to candidate link theme edge text, is obtained
Theme relevant picture;If text belongs to specific subject, then corresponding candidate link with weights grade value as priority of classifying,
Creeped queue with the insertion of the size order of priority, reptile preferentially accesses the big link of classification value, if text be not belonging to it is specific
Theme then abandons candidate link;
The degree of correlation prejudges unit, its corresponding technorati authority is calculated with HITS algorithms for the Web link information to relevant picture
And centrad, nearby information, reversed webpage, brother's link of backward chaining, URL link, anticipation are treated for comprehensive Anchor Text, Anchor Text
Crawl the degree of correlation of photo and theme;
Placement unit, when the degree of correlation for crawling photo and theme is more than certain threshold value, photo to be crawled described in crawl is to greatly
Among data picture database.
10. the system of authentication as claimed in claim 9, it is characterised in that:
The threshold value is 90%.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711252474.5A CN108171113A (en) | 2017-12-01 | 2017-12-01 | A kind of identity authentication method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711252474.5A CN108171113A (en) | 2017-12-01 | 2017-12-01 | A kind of identity authentication method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108171113A true CN108171113A (en) | 2018-06-15 |
Family
ID=62525131
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711252474.5A Pending CN108171113A (en) | 2017-12-01 | 2017-12-01 | A kind of identity authentication method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108171113A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108984767A (en) * | 2018-07-20 | 2018-12-11 | 珠海宏桥高科技有限公司 | A kind of method that virtual identity is verified |
CN110020519A (en) * | 2019-01-08 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of identity checking method, device and electronic equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101136015A (en) * | 2006-09-01 | 2008-03-05 | 北大方正集团有限公司 | Method for calculating similarity between images |
CN104123485A (en) * | 2014-07-18 | 2014-10-29 | 广州三星通信技术研究有限公司 | Real-name system information binding method and device |
CN104240349A (en) * | 2014-09-12 | 2014-12-24 | 宝鸡市交通信息工程研究所 | Method for quickly confirming real name identity in important place and human image and identity comparison safety inspection system |
CN106407914A (en) * | 2016-08-31 | 2017-02-15 | 北京旷视科技有限公司 | Method for detecting human faces, device and remote teller machine system |
CN107169030A (en) * | 2017-04-14 | 2017-09-15 | 国政通科技股份有限公司 | A kind of method and system of identification check integration |
-
2017
- 2017-12-01 CN CN201711252474.5A patent/CN108171113A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101136015A (en) * | 2006-09-01 | 2008-03-05 | 北大方正集团有限公司 | Method for calculating similarity between images |
CN104123485A (en) * | 2014-07-18 | 2014-10-29 | 广州三星通信技术研究有限公司 | Real-name system information binding method and device |
CN104240349A (en) * | 2014-09-12 | 2014-12-24 | 宝鸡市交通信息工程研究所 | Method for quickly confirming real name identity in important place and human image and identity comparison safety inspection system |
CN106407914A (en) * | 2016-08-31 | 2017-02-15 | 北京旷视科技有限公司 | Method for detecting human faces, device and remote teller machine system |
CN107169030A (en) * | 2017-04-14 | 2017-09-15 | 国政通科技股份有限公司 | A kind of method and system of identification check integration |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108984767A (en) * | 2018-07-20 | 2018-12-11 | 珠海宏桥高科技有限公司 | A kind of method that virtual identity is verified |
CN110020519A (en) * | 2019-01-08 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of identity checking method, device and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Thomson et al. | Visual mis/disinformation in journalism and public communications: Current verification practices, challenges, and future opportunities | |
Lyon | Surveillance technology and surveillance society | |
Redi et al. | Digital image forensics: a booklet for beginners | |
Kirchengast | Deepfakes and image manipulation: criminalisation and control | |
Gokhale et al. | A bibliometric analysis of digital image forensics | |
US8290951B1 (en) | Unstructured data integration with a data warehouse | |
CN110322317B (en) | Transaction data processing method and device, electronic equipment and medium | |
TWI807172B (en) | Active risk control method and system based on intelligent interaction | |
Heimo et al. | Augmented reality-Towards an ethical fantasy? | |
Fiřtová | Framing Canadian immigration discourse under the conservative government (2006–2015): Breaking path dependence? | |
CN108171113A (en) | A kind of identity authentication method and system | |
Marwick | The private is political: networked privacy and social media | |
Nowroozi et al. | Impact of media forensics and deepfake in society | |
Meena et al. | Image splicing forgery detection techniques: A review | |
Lussier | Nonconsensual deepfakes: detecting and regulating this rising threat to privacy | |
Kavoliūnaitė-Ragauskienė | Right to Privacy and Data Protection Concerns Raised by the Development and Usage of Face Recognition Technologies in the European Union | |
Dauvergne | Facial recognition technology for policing and surveillance in the Global South: a call for bans | |
Fischer-Hübner et al. | The Future of Identity in the Information Society: Proceedings of the Third IFIP WG 9.2, 9.6/11.6, 11.7/FIDIS International Summer School on the Future of Identity in the Information Society, Karlstad University, Sweden, August 4-10, 2007 | |
Manish et al. | Card-Less ATM Transaction using Biometric and Face Recognition–A Review | |
CN113011254B (en) | Video data processing method, computer equipment and readable storage medium | |
Barnes et al. | Deepfakes and synthetic media | |
Mohamed et al. | Trackify: A robust system for preserving money transactions | |
Mykhalchenko et al. | Anti-fraud measures in Western Africa and commentary on research findings across the three regions analysed | |
Stemberger et al. | Watergate, Wiretapping, and Wire Transfers: The True Origin of Florida's Privacy Right | |
Mjelde | International News Media Coverage of Black Lives Matter: Evidence From Norway |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180615 |
|
RJ01 | Rejection of invention patent application after publication |