CN110046644A - A kind of method and device of certificate false proof calculates equipment and storage medium - Google Patents
A kind of method and device of certificate false proof calculates equipment and storage medium Download PDFInfo
- Publication number
- CN110046644A CN110046644A CN201910142956.8A CN201910142956A CN110046644A CN 110046644 A CN110046644 A CN 110046644A CN 201910142956 A CN201910142956 A CN 201910142956A CN 110046644 A CN110046644 A CN 110046644A
- Authority
- CN
- China
- Prior art keywords
- reproduction
- certificate
- image
- distance image
- distance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- 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
-
- 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
Abstract
The application provides a kind of method and device of certificate false proof, calculates equipment and storage medium, wherein, the method of the certificate false proof includes: two width for obtaining certificate or certificate images more than two width, the certificate image includes the first distance image obtained from first distance and the second distance image obtained from second distance, wherein, first distance and second distance difference；To in the certificate image two width or several, carry out registration verification；If verification passes through, using one or more reproduction models, the first reproduction probability of first distance image and the second reproduction probability of second distance image are calculated；According to the first reproduction probability and the second reproduction probability, judge whether certificate is reduced the time that certificate image identification expends, improved recognition efficiency by reproduction without manually identifying to the true and false of image.
Description
Technical field
This application involves technical field of image processing, in particular to a kind of method and device of certificate false proof calculates equipment
And storage medium.
Background technique
For financial scenario, identity is falsely used using forged certificate for identification or the behavior of fraud is most important.It is black
The behavior for producing user's forged certificate can be divided into two classes: physics certificate is forged and electronic certificate is forged.The forgery of physics certificate refers to
Be directly to modify certificate information on the physical entity of certificate, including (such as being made with the means of physics modification subscriber identity information
Name, birthday by information are distorted with smearing, the mode of physics patch) or one false certificate of direct manufacture.Electronic certificate is forged
It refers to by taking pictures, after scanning means electronization usurping physics certificate in the obtained enterprising row information of electronic edition certificate image
The behavior (repair figure tool as used and distort) changed.
It is forged compared to physics certificate, electronic certificate is forged easily to obtain with forgery target and (be taken pictures against certificate, no
With taking physics certificate), at low cost, fraud tool of faking (Photoshop etc. change plan software) easily obtains and effect is true to nature
The features such as, it easily causes batch and attacks, need guard key for business electronic for internet finance etc..But electronics is demonstrate,proved
Part forgery also has a weakness, is exactly after the completion of forgery, it is necessary to (such as by certain physics mode by (forgery) electronic certificate
Computer or mobile phone screen show, printer printing etc.) show after, reuse an other terminal and pass through secondary reproduction
Mode will be in its typing target application (such as certain Web bank remotely open an account application).
Therefore, how to carry out indirect prevention and control electronic certificate by the identification to screen reproduction to forge, be the technology for needing to solve
Problem.
Summary of the invention
In view of this, this specification one or more embodiment provides a kind of method and device of certificate false proof, calculates
Equipment and storage medium, to solve technological deficiency existing in the prior art.
This specification one or more embodiment discloses a kind of method of certificate false proof, which comprises
Two width or certificate images more than two width for obtaining certificate, the certificate image include the obtained from first distance
One range image and the second distance image obtained from second distance, wherein first distance and second distance difference；
To in the certificate image two width or several, carry out registration verification；
If verification passes through, using one or more reproduction models, the first reproduction probability and the of first distance image is calculated
Second reproduction probability of two range images；
According to the first reproduction probability and the second reproduction probability, judge certificate whether by reproduction.
Optionally, in the certificate image two width or several, carry out registration verification, comprising:
The first registration for obtaining the first distance image and the second distance image, to first registration into
Row verification.
Optionally, the certificate image of two width or two width of certificate or more is obtained, comprising:
Obtain certificate first distance image, intermediate distance image and second distance image, wherein first distance, in
Between distance and second distance be sequentially increased.
Optionally, in the certificate image two width or several, carry out registration verification, comprising:
The first distance image, intermediate distance image and second distance image of certificate are subjected to registration verification.
Optionally, the first distance image of certificate, intermediate distance image and second distance image are subjected to registration school
It tests, comprising:
The first distance image of certificate and the second registration of intermediate distance image are obtained, second registration is carried out
Verification；
The intermediate distance image of certificate and the third registration of second distance image are obtained, the third registration is carried out
Verification；
In the case where the second registration is greater than first threshold and third registration is greater than second threshold, verification passes through；
In the case where the second registration is less than or equal to first threshold or third registration is less than or equal to second threshold, verification
Do not pass through.
Optionally, the first distance image of certificate and the second registration of intermediate distance image are obtained, comprising:
The first distance Image Adjusting is aligned with the intermediate distance image space positions based on preset algorithm
First distance converts image；
Obtain the second registration of first distance the conversion image and second distance image.
Optionally, the intermediate distance image of certificate and the third registration of second distance image are obtained, comprising:
The intermediate distance Image Adjusting is aligned with the second distance image space positions based on preset algorithm
Intermediate distance converts image；
Obtain the third registration of intermediate distance the conversion image and second distance image.
Optionally, using one or more reproduction models, the first reproduction probability and the second reproduction probability are calculated, comprising:
The first distance image that verification is passed through inputs the first reproduction model, obtains the first reproduction probability；
The second distance image that verification is passed through inputs the second reproduction model, obtains the second reproduction probability.
Optionally, according to the first reproduction probability and the second reproduction probability, judge certificate whether by reproduction, comprising:
In the case where the first reproduction probability is less than or equal to third threshold value and the second reproduction probability is less than or equal to four threshold values,
Determine certificate not by reproduction；
In the case where the first reproduction probability is greater than third threshold value or the second reproduction probability is greater than four threshold values, certificate is determined
By reproduction.
Optionally, in the case where determining certificate by reproduction, reproduction prompt information is exported.
Optionally, the first reproduction model is trained by the following method:
It will be marked with the first distance image zooming-out feature vector of reproduction type, described eigenvector includes first distance figure
Spectrum signature, textural characteristics and/or the color characteristic of picture；
It is adopted using the feature vector of first distance image as training sample using the label of reproduction type as training label
It is trained to obtain the first reproduction model with two disaggregated models, wherein the reproduction type includes reproduction and non-reproduction.
Optionally, the second reproduction model is trained by the following method:
It will be marked with the second distance image zooming-out feature vector of reproduction type, described eigenvector includes second distance figure
The spectrum signature and/or contour feature of picture；
It is adopted using the feature vector of second distance image as training sample using the label of reproduction type as training label
It is trained to obtain the second reproduction model with two disaggregated models, wherein the reproduction type includes reproduction and non-reproduction.
This specification one or more embodiment discloses a kind of device of certificate false proof, and described device includes:
Module is obtained, two width for obtaining certificate is configured as or certificate images more than two width, the certificate image includes
The first distance image obtained from first distance and the second distance image obtained from second distance, wherein first distance and the
Two distances are different；
Registration correction verification module, be configured as in the certificate image two width or several, carry out registration verification；
Reproduction probability evaluation entity passes through if being configured as verification, using one or more reproduction models, calculate first away from
Second reproduction probability of the first reproduction probability and second distance image from image；
Reproduction judgment module is configured as judging whether certificate is turned over according to the first reproduction probability and the second reproduction probability
It claps.
Optionally, the registration correction verification module is specifically configured to: obtaining the first distance image and described second
First registration of range image verifies first registration.
Optionally, the acquisition module is specifically configured to:
Obtain first distance image, intermediate distance image and the second distance image of certificate, wherein first distance, mark
Quasi- distance and second distance are sequentially increased.
Optionally, the registration correction verification module is specifically configured to: by the first distance image of certificate, intermediate distance figure
Picture and second distance image carry out registration verification.
Optionally, the registration correction verification module is specifically configured to: obtaining the first distance image and medium spacing of certificate
The second registration from image verifies second registration；
The intermediate distance image of certificate and the third registration of second distance image are obtained, the third registration is carried out
Verification；
In the case where the second registration is greater than first threshold and third registration is greater than second threshold, verification passes through；
In the case where the second registration is less than or equal to first threshold or third registration is less than or equal to second threshold, verification
Do not pass through.
Optionally, the registration correction verification module is specifically configured to: being based on preset algorithm for the first distance image
It is adjusted to the first distance being aligned with intermediate distance image space positions conversion image；
Obtain the second registration of first distance the conversion image and second distance image.
Optionally, the registration correction verification module is specifically configured to: being based on preset algorithm for the intermediate distance image
It is adjusted to the intermediate distance being aligned with second distance image space positions conversion image；
Obtain the third registration of intermediate distance the conversion image and second distance image.
Optionally, the reproduction probability evaluation entity is specifically configured to: the first distance image that verification is passed through inputs
First reproduction model obtains the first reproduction probability；
The second distance image that verification is passed through inputs the second reproduction model, obtains the second reproduction probability.
Optionally, the reproduction judgment module is specifically configured to: the first reproduction probability be less than or equal to third threshold value and
In the case that second reproduction probability is less than or equal to the 4th threshold value, determine certificate not by reproduction；
In the case where the first reproduction probability is greater than third threshold value or the second reproduction probability is greater than four threshold values, certificate is determined
By reproduction.
This specification one or more embodiment discloses a kind of calculating equipment, including memory, processor and is stored in
On memory and the computer instruction that can run on a processor, the processor realize card as described above when executing described instruction
The step of part anti-fake method.
This specification one or more embodiment discloses a kind of computer readable storage medium, is stored with computer and refers to
The step of order, which realizes the method for certificate false proof as described above when being executed by processor.
The method and device for the certificate false proof that this specification one or more embodiment provides, by two width for obtaining certificate
Or two certificate images more than width, then in the certificate image two width or several carry out registration verifications, if verification is logical
Cross, using one or more reproduction models, calculate first distance image the first reproduction probability and second distance image second
Reproduction probability, and according to the first reproduction probability and the second probabilistic determination certificate whether by reproduction, to utilize several figures of certificate
As combining with reproduction model, the prevention and control to certificate image are realized.The certificate false proof of this specification one or more embodiment
Method does not need manually to identify the true and false of image, reduces the time that certificate image identification expends, improve identification effect
Rate.
In addition, comparing the common anti-conversion system of single picture, the method for the application certificate false proof is by obtaining certificate
First distance image, intermediate distance image and second distance image, thus obtain certificate more abundant foreground information and
Background information improves the accuracy identified to screen reproduction, is of great significance to Internet application prevention and control forged certificate.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of the calculating equipment of this specification one or more embodiment；
Fig. 2 is the method flow schematic diagram of the certificate false proof of this specification one or more embodiment；
Fig. 3 is the method flow schematic diagram of the certificate false proof of this specification one or more embodiment；
Fig. 4 is the method flow schematic diagram of the certificate false proof of this specification one or more embodiment；
Fig. 5 is the structural schematic diagram of the device of the certificate false proof of this specification one or more embodiment.
Specific embodiment
Many details are explained in the following description in order to fully understand the application.But the application can be with
Much it is different from other way described herein to implement, those skilled in the art can be without prejudice to the application intension the case where
Under do similar popularization, therefore the application is not limited by following public specific implementation.
The term used in this specification one or more embodiment be only merely for for the purpose of describing particular embodiments,
It is not intended to be limiting this specification one or more embodiment.In this specification one or more embodiment and appended claims
The "an" of singular used in book, " described " and "the" are also intended to including most forms, unless context is clearly
Indicate other meanings.It is also understood that term "and/or" used in this specification one or more embodiment refers to and includes
One or more associated any or all of project listed may combine.
It will be appreciated that though may be retouched using term first, second etc. in this specification one or more embodiment
Various information are stated, but these information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other
It opens.For example, first can also be referred to as second, class in the case where not departing from this specification one or more scope of embodiments
As, second can also be referred to as first.Depending on context, word as used in this " if " can be construed to
" ... when " or " when ... " or " in response to determination ".
Firstly, the vocabulary of terms being related to one or more embodiments of the invention explains.
OCR: optical character identification refers to positioning and identifies the technology of text information in picture.
Core body: the authenticity of user identity is veritified
Certificate false proof: the measure that forged certificate is identified.
Characteristics of image: characteristics of image includes: color characteristic, textural characteristics, shape feature and spatial relation characteristics.Wherein,
Color characteristic is a kind of global characteristics, describes the surface nature of scenery corresponding to image or image-region；Textural characteristics
It is a kind of global characteristics, it also illustrates the surface nature of scenery corresponding to image or image-region；Shape feature has two class tables
Show that method, one kind are contour features, another kind of is provincial characteristics, the contour feature of image mainly for object outer boundary, and
The provincial characteristics of image is then related to entire shape area；Spatial relation characteristics refer to the multiple targets split in image
Between mutual spatial position or relative direction relationship, these relationships can also be divided into connection/syntople, overlapping/overlapping is closed
System and include/containment relationship etc..
In this specification one or more embodiment, provides a kind of method and device of certificate false proof, calculates equipment
And storage medium, it is described in detail one by one in the following embodiments.
Fig. 1 is to show the structural block diagram of the calculating equipment 100 according to one embodiment of this specification.The calculating equipment 100
Component include but is not limited to memory 110 and processor 120.Processor 120 is connected with memory 110 by bus 130,
Database 150 is for saving data.
Calculating equipment 100 further includes access device 140, access device 140 enable calculate equipment 100 via one or
Multiple networks 160 communicate.The example of these networks includes public switched telephone network (PSTN), local area network (LAN), wide area network
(WAN), the combination of the communication network of personal area network (PAN) or such as internet.Access device 140 may include wired or wireless
One or more of any kind of network interface (for example, network interface card (NIC)), such as IEEE802.11 wireless local area
Net (WLAN) wireless interface, worldwide interoperability for microwave accesses (Wi-MAX) interface, Ethernet interface, universal serial bus (USB) connect
Mouth, cellular network interface, blue tooth interface, near-field communication (NFC) interface, etc..
In one embodiment of this specification, other unshowned portions in the above-mentioned component and Fig. 1 of equipment 100 are calculated
Part can also be connected to each other, such as pass through bus.It should be appreciated that calculating device structure block diagram shown in FIG. 1 merely for the sake of
Exemplary purpose, rather than the limitation to this specification range.Those skilled in the art can according to need, and increases or replaces it
His component.
Calculating equipment 100 can be any kind of static or mobile computing device, including mobile computer or mobile meter
Calculate equipment (for example, tablet computer, personal digital assistant, laptop computer, notebook computer, net book etc.), movement
Phone (for example, smart phone), wearable calculating equipment (for example, smartwatch, intelligent glasses etc.) or other kinds of shifting
Dynamic equipment, or the static calculating equipment of such as desktop computer or PC.Calculating equipment 100 can also be mobile or state type
Server.
Wherein, processor 120 can execute the step in method shown in Fig. 2.Fig. 2 is to show according to this specification one in fact
Apply the schematic flow chart of the method for the certificate false proof of example, including step 202 is to step 208.
202, two width or certificate images more than two width for obtaining certificate, the certificate image include obtaining from first distance
First distance image and the second distance image that is obtained from second distance, wherein first distance and second distance are different.
Wherein, the present embodiment can be the two images of acquisition certificate, including first distance image and second distance image；
Or images more than two width of acquisition certificate, including first distance image, intermediate distance image and second distance image,
Wherein, first distance, intermediate distance and second distance are sequentially increased.By obtaining multiple image, and carry out in the next steps
It compares, the accuracy of certificate recognition result can be increased.
Wherein, the acquisition modes of the first distance image of certificate, intermediate distance image and second distance image can have more
Kind, such as in such a way that user clicks and uploads.
During practical application, one can be shot respectively using large and small two target object view-finders of capture apparatus
It is secondary.Big view-finder, which is taken pictures, obtains the close-up images of certificate, so as to obtain more certificate foreground informations (screen when such as reproduction
Moire fringes on curtain)；Small view-finder, which is taken pictures, obtains the remote image of certificate, so as to obtain more certificate background informations
(such as screen frame of reproduction equipment), in this way, just having obtained the image of corresponding two distances: first distance image and second away from
From image.Then it also needs primary in normal distance shooting certificate, wherein the certificate image of normal distance shooting only includes certificate
The all images of itself.In this way, just having obtained the intermediate distance image of corresponding certificate.
204, in the certificate image two width or several, carry out registration verification.
The purpose of registration verification is: there is the phenomenon that shooting of stealthily substituting during shooting more figures in user in order to prevent,
Need in the certificate image two width or several verify.
For obtaining the first distance image of certificate and the situation of second distance image, step 204 includes: to obtain described the
First registration of one range image and the second distance image verifies first registration.
For obtaining the first distance image of certificate, the situation of intermediate distance image and second distance image, step 204 packet
It includes: the first distance image, intermediate distance image and second distance image of certificate is subjected to registration verification.
In the present embodiment, a kind of specific registration verification is set forth below in there are many ways to carrying out registration verification
Method schematically illustrates the method for the registration verification of the present embodiment.Specifically, referring to Fig. 3, by the first of certificate
Range image, intermediate distance image and second distance image carry out registration verification, include the following steps 302~308:
302, the first distance image of certificate and the second registration of intermediate distance image are obtained, to second registration
It is verified.
Specifically, step 302 includes:
S3022, it is and the intermediate distance image space positions by the first distance Image Adjusting based on preset algorithm
The first distance of alignment converts image；
S3024, the second registration for obtaining first distance the conversion image and second distance image.
Wherein, the preset algorithm includes but is not limited to image registration algorithm, i.e. Image registration algorithm, figure
As registration Algorithm can make to reach matching between two images in some sense.
It specifically, is to be transformed image with first distance image, i.e., to the in this step based on intermediate distance image
One range image and intermediate distance image carry out feature extraction and obtain characteristic point, find matched spy by carrying out similarity measurement
Sign point pair, then by matched characteristic point to image space coordinate conversion parameter is obtained, is finally carried out by coordinate conversion parameter
Image registration.Wherein, characteristic point is the characteristic informations such as point, line and the edge of image.
Wherein, image registration (Image registration) is exactly by different time, different sensors (imaging device)
Or the mistake that two width or multiple image that (weather, illumination, camera position and angle etc.) obtains under different condition are matched, are superimposed
Journey, it has been widely used in the fields such as remotely-sensed data analysis, computer vision, image procossing.The mode of image registration
Have very much, such as uses Scale invariant features transform (Scale-invariant feature transform, SIFT) algorithm
Deng.
304, the intermediate distance image of certificate and the third registration of second distance image are obtained, to the third registration
It is verified.
Specifically, step 304 includes:
S3042, it is and the second distance image space positions by the intermediate distance Image Adjusting based on preset algorithm
The intermediate distance of alignment converts image；
S3044, the third registration for obtaining intermediate distance the conversion image and second distance image.
It specifically, is to be transformed image, i.e. centering with intermediate distance image in this step based on second distance image
Between range image and second distance image carry out feature extraction and obtain characteristic point, find matched spy by carrying out similarity measurement
Sign point pair, then by matched characteristic point to image space coordinate conversion parameter is obtained, is finally carried out by coordinate conversion parameter
Image registration.Wherein, characteristic point is the characteristic informations such as point, line and the edge of image.
306, in the case where the second registration is greater than first threshold and third registration is greater than second threshold, verification is logical
It crosses.
308, in the case where the second registration is less than or equal to first threshold or third registration is less than or equal to second threshold,
Verification does not pass through.
Wherein, first threshold and second threshold can be arranged according to actual needs, such as setting first threshold and second
Threshold value is 0.8.
It should be noted that three images are divided into two groups of carry out registration verifications in the present embodiment, in two groups of images
In the case that registration is respectively greater than threshold value, verification passes through；For verifying unacceptable situation, in the coincidence of wherein one group of image
In the case that degree is less than or equal to threshold value, verification does not pass through.
In the case where verifying unacceptable situation, interrupts and execute follow-up process, and export prompt information.The output side of prompt information
Formula can there are many, such as in an application program prompt user input image irregularity, need to re-enter.In user
Again the image of three distances of certificate is uploaded after confirmation, and re-execute the steps 202.
If 206, verification passes through, using one or more reproduction models, the first reproduction probability of first distance image is calculated
With the second reproduction probability of second distance image.
In this step, a reproduction model can be used, calculate the first reproduction probability and the second reproduction probability；It can also make
With two reproduction models, the first reproduction probability and the second reproduction probability are calculated separately.
Specifically, step 206 includes:
S2062, the first distance image for passing through verification input the first reproduction model, obtain the first reproduction probability.
S2064, the second distance image for passing through verification input the second reproduction model, obtain the second reproduction probability.
Specifically, then first distance image zooming-out feature vector verification passed through is turned over feature vector input first
Model is clapped, the first reproduction probability is obtained；
Then feature vector is inputted the second reproduction model by the second distance image zooming-out feature vector that verification is passed through,
Obtain the second reproduction probability.
Wherein, the first reproduction model passes through following steps S12~S14 training:
S12, the first distance image zooming-out feature vector that reproduction type will be marked with, described eigenvector include first away from
Spectrum signature, textural characteristics and/or color characteristic from image.
Wherein, spectrum signature can be used for identifying the situation of the screen reflecting occurred in reproduction image.
Textural characteristics can be used for identifying moire fringes or other distortion situations in first distance image, such as resolution ratio
Distortion, crenellated phenomena etc..Moire fringes are one kind in the equipment such as digital camera or scanner, the high frequency that photosensitive element occurs
The striped of interference is a kind of irregular striped of high-frequency that picture can be made colour occur.Moire fringes be difference reproduction image and
The important parameter of non-reproduction image.For reproduction image, moire fringes in a frequency domain can be more obvious, and the color of moire fringes
It also can be with the color different from of the moire fringes of non-reproduction image.
Color characteristic can be used for identifying the situation that local color is distorted in reproduction image.
S14, using the feature vector of first distance image as training sample, marked the label of reproduction type as training
Label, are trained to obtain the first reproduction model using two disaggregated models, wherein the reproduction type includes reproduction and non-turns over
It claps.
Wherein, the second reproduction model passes through following steps S22~S24 training:
S22, the second distance image zooming-out feature vector that reproduction type will be marked with, described eigenvector include second away from
Spectrum signature and/or contour feature from image.
Wherein, spectrum signature can be used for identifying the situation of the screen reflecting occurred in reproduction image.
Contour feature can be used for identifying the frame of the reproduction equipment (mobile phone or display) occurred in reproduction image
Situation.
As can be seen that for the first reproduction model and the second reproduction model, the first distance image of input and second away from
Feature vector from image is different, because first distance image is more concerned with local field of view, available more certificates
Foreground detail (moire fringes when such as reproduction on screen)；Second distance image is more concerned with the environment visual field, available more
Background information (mobile phone or indicator screen frame when such as reproduction).
S24, using the feature vector of second distance image as training sample, marked the label of reproduction type as training
Label, are trained to obtain the second reproduction model using two disaggregated models, wherein the reproduction type includes reproduction and non-turns over
It claps.
By above-mentioned steps as it can be seen that the first reproduction model and the second reproduction model pass through two disaggregated model training obtains, no
Same is the sample difference of input.Wherein, two disaggregated models can there are many, such as utilize CNN convolutional neural networks generate
Two disaggregated models.
Generally, convolutional neural networks include thousands of iterative parameters, but only a fraction iterative parameter can be to image
Prediction result have an impact.In the training stage of model, it can first find out a part and shadow is generated to the prediction result of image
Then loud iterative parameter adjusts a part of iterative parameter, so as to so as to trained first reproduction model or second turn over
The prediction result for clapping model is more accurate.
208, according to the first reproduction probability and the second reproduction probability, judge certificate whether by reproduction.
Specifically, step 208 includes:
S2082, it is less than or equal to third threshold value and the second reproduction probability in the first reproduction probability and is less than or equal to the 4th threshold value
In the case of, determine certificate not by reproduction；
S2084, in the case where the first reproduction probability is greater than third threshold value or the second reproduction probability and is greater than four threshold values, really
Certificate is determined by reproduction.
It should be noted that step S2082 and step S2084 are required to judge that the first reproduction probability and the second reproduction are general
Rate, but need to meet the condition of "and" in step S2082, i.e. the first reproduction probability is less than or equal to third threshold value and the second reproduction
Probability is less than or equal to the 4th threshold value；Need to meet the condition of "or" in step S2084, i.e. the first reproduction probability is greater than third threshold value
Or second reproduction probability be greater than the 4th threshold value.
Wherein, third threshold value and the 4th threshold value can be arranged according to actual needs, such as setting third threshold value and the 4th
Threshold value is 0.8.
After determining the non-reproduction of certificate, exports and handle using intermediate distance image as the image of certificate.It is actually using
When, such as in the application program remotely opened an account, can the image using intermediate distance image as certificate export to application program
Certificate text OCR identification module is handled.
After determining certificate reproduction, prompt information is exported.The way of output of prompt information can there are many, such as pop-up
Dialog box, text information of output etc..
The method for the certificate false proof that this specification one or more embodiment provides, by two width or two width that obtain certificate
Above certificate image, then in the certificate image two width or several carry out registration verifications, if verification pass through, use
One or more reproduction models calculate the first reproduction probability and the second reproduction probability, and are turned over according to the first reproduction probability and second
Probabilistic determination certificate is clapped whether by reproduction, so that the multiple image using certificate is combined with reproduction model, is realized to certificate figure
The prevention and control of picture.The method of the certificate false proof of this specification one or more embodiment does not need manually to know the true and false of image
Not, reduce the time that certificate image identification expends, improve recognition efficiency.
In addition, comparing the common anti-conversion system of single picture, the method for the certificate false proof of one embodiment of this specification is logical
First distance image, intermediate distance image and the second distance image for obtaining certificate are crossed, to obtain the more horn of plenty of certificate
Foreground information and background information, improve the accuracy that identifies to screen reproduction, have to Internet application prevention and control forged certificate
Significance.
One embodiment of this specification discloses a kind of method of certificate false proof, referring to fig. 4, include the following steps 402~
420:
402, obtain certificate first distance image, intermediate distance image and second distance image, wherein first away from
It is sequentially increased from, intermediate distance and second distance.
Wherein, the acquisition modes of the first distance image of certificate, intermediate distance image and second distance image can have
It is a variety of, such as in such a way that user clicks and uploads.
404, the first distance image of certificate, intermediate distance image and second distance image are subjected to registration verification,
If verification passes through, step 406 is executed, if verification does not pass through, executes step 408.
406, the first distance image for passing through verification inputs the first reproduction model, and obtain first distance image first turns over
Probability is clapped, the second distance image that verification is passed through inputs the second reproduction model, and the second reproduction for obtaining second distance image is general
Then rate executes step 410.
408, output verification failure prompt information, and return to step 402.
410, judge whether the first reproduction probability is greater than first threshold, if so, step 412 is executed, if it is not, executing step
414。
412, it determines that the first distance image is reproduction image, executes step 420.
414, judge whether the second reproduction probability is greater than second threshold, if so, step 416 is executed, if it is not, executing step
418。
416, it determines that the second distance image is reproduction image, executes step 420.
418, it exports and handles using intermediate distance image as the image of the certificate.
420, in the case where determining the first distance image or second distance image is reproduction image, output reproduction is mentioned
Show information, return step 402.
Reproduction prompt information can be the dialog box popped up in the application, and after user clicks confirmation, return is held
Row step 402.
Then the method for certificate false proof provided in this embodiment, multiple images of the different distance by obtaining certificate will
The first distance image that registration verification passes through inputs the first reproduction model, obtains the first reproduction probability of first distance image,
The second distance image that verification is passed through inputs the second reproduction model, obtains the second reproduction probability of second distance image；?
One reproduction probability is less than or equal to first threshold and in the case that the second reproduction probability is less than or equal to second threshold, by second distance figure
Picture is exported and is handled as the image of certificate, so that more range images using certificate are combined with reproduction model, realizes verification
The prevention and control of part image.The method of the certificate false proof of the present embodiment do not need manually to identify the true and false of image, reduces card
The time that part image recognition expends, improve recognition efficiency.
Above content is the detailed description to the method for the certificate false proof of this specification one or more embodiment, this explanation
Book one or more embodiment also discloses a kind of device of certificate false proof.It should be noted that the device of the certificate false proof
The technical solution of technical solution and the method for above-mentioned certificate false proof belongs to same design, the technical solution of the device of certificate false proof
The detail content being not described in detail may refer to the description of the technical solution of the method for above-mentioned certificate false proof.
Referring to Fig. 5, the device of certificate false proof disclosed in one embodiment of this specification includes:
Module 502 is obtained, two width for obtaining certificate or certificate images more than two width, the certificate image packet are configured as
Include from first distance obtain first distance image and from second distance obtain second distance image, wherein first distance and
Second distance is different；
Registration correction verification module 504, be configured as in the certificate image two width or several, carry out registration school
It tests；
Reproduction probability evaluation entity 506 passes through if being configured as verification, using one or more reproduction models, calculates the
First reproduction probability of one range image and the second reproduction probability of second distance image；
Reproduction judgment module 508, is configured as according to the first reproduction probability and the second reproduction probability, judge certificate whether by
Reproduction.
Optionally, registration correction verification module 504 is specifically configured to: obtain the first distance image and described second away from
The first registration from image verifies first registration.
Optionally, obtain module 502 be specifically configured to: obtain first distance image, the intermediate distance image of certificate with
And second distance image, wherein first distance, gauged distance and second distance are sequentially increased.
Optionally, the registration correction verification module 504 is specifically configured to: by the first distance image of certificate, medium spacing
Registration verification is carried out from image and second distance image.
Optionally, the registration correction verification module 504 is specifically configured to: obtaining first distance image and the centre of certificate
Second registration of range image verifies second registration；
The intermediate distance image of certificate and the third registration of second distance image are obtained, the third registration is carried out
Verification；
In the case where the second registration is greater than first threshold and third registration is greater than second threshold, verification passes through；
In the case where the second registration is less than or equal to first threshold or third registration is less than or equal to second threshold, verification
Do not pass through.
Optionally, the registration correction verification module 504 is specifically configured to: being based on preset algorithm for the first distance figure
As being adjusted to the first distance being aligned with intermediate distance image space positions conversion image；
Obtain the second registration of first distance the conversion image and second distance image.
Optionally, registration correction verification module 504 is specifically configured to: being based on preset algorithm for the intermediate distance image tune
The whole intermediate distance to be aligned with the second distance image space positions converts image；
Obtain the third registration of intermediate distance the conversion image and second distance image.
Optionally, the reproduction probability evaluation entity 506 is specifically configured to: the first distance image that verification is passed through is defeated
Enter the first reproduction model, obtains the first reproduction probability；The second distance image that verification is passed through inputs the second reproduction model, obtains
Second reproduction probability.
Optionally, the reproduction judgment module 508 is specifically configured to: being less than or equal to third threshold value in the first reproduction probability
And second reproduction probability be less than or equal to the 4th threshold value in the case where, determine certificate not by reproduction；It is greater than the in the first reproduction probability
In the case that three threshold values or the second reproduction probability are greater than the 4th threshold value, determine certificate by reproduction.
Two width of the device of certificate false proof provided in this embodiment by obtaining certificate or certificate images more than two width, so
Afterwards in the certificate image two width or several carry out registration verifications, if verification pass through, use one or more reproduction moulds
Type calculates the first reproduction probability and the second reproduction probability, and is according to the first reproduction probability and the second reproduction probabilistic determination certificate
It is no by reproduction, so that the multiple image using certificate is combined with reproduction model, realize the prevention and control to certificate image.This specification
The method of the certificate false proof of one or more embodiments do not need manually to identify the true and false of image, reduces certificate image
It identifies the time expended, improves recognition efficiency.
One embodiment of this specification also provides a kind of calculating equipment, including memory, processor and storage are on a memory
And the computer instruction that can be run on a processor, the processor realize certificate false proof as previously described when executing described instruction
The step of method.
One embodiment of this specification also provides a kind of computer readable storage medium, is stored with computer instruction, this refers to
The step of order realizes the method for certificate false proof as previously described when being executed by processor.
A kind of exemplary scheme of above-mentioned computer readable storage medium for the present embodiment.It should be noted that this is deposited
The technical solution of the technical solution of storage media and the method for above-mentioned certificate false proof belongs to same design, the technical side of storage medium
The detail content that case is not described in detail may refer to the description of the technical solution of the method for above-mentioned certificate false proof.
The computer instruction includes computer program code, the computer program code can for source code form,
Object identification code form, executable file or certain intermediate forms etc..The computer-readable medium may include: that can carry institute
State any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disk, CD, the computer storage of computer program code
Device, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory),
Electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that the computer-readable medium include it is interior
Increase and decrease appropriate can be carried out according to the requirement made laws in jurisdiction with patent practice by holding, such as in certain jurisdictions of courts
Area does not include electric carrier signal and telecommunication signal according to legislation and patent practice, computer-readable medium.
It should be noted that for the various method embodiments described above, describing for simplicity, therefore, it is stated as a series of
Combination of actions, but those skilled in the art should understand that, this specification is not limited by the described action sequence, because
For according to this specification, certain steps can use other sequences or carry out simultaneously.Secondly, those skilled in the art also should
Know, the embodiments described in the specification are all preferred embodiments, and related actions and modules might not all be this
Necessary to specification.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, it may refer to the associated description of other embodiments.
This specification preferred embodiment disclosed above is only intended to help to illustrate this specification.Alternative embodiment is not
All details of detailed descriptionthe, do not limit the invention to the specific embodiments described.Obviously, according in this specification
Hold, can make many modifications and variations.These embodiments are chosen and specifically described to this specification, is in order to preferably explain this theory
The principle and practical application of bright book, so that skilled artisan be enable to better understand and utilize this specification.This
Specification is limited only by the claims and their full scope and equivalents.
Claims (23)
1. a kind of method of certificate false proof, which is characterized in that the described method includes:
Obtain certificate two width or certificate images more than two width, the certificate image include from first distance obtain first away from
From image and the second distance image obtained from second distance, wherein first distance and second distance difference；
To in the certificate image two width or several, carry out registration verification；
If verification passes through, using one or more reproduction models, calculate first distance image the first reproduction probability and second away from
The second reproduction probability from image；
According to the first reproduction probability and the second reproduction probability, judge certificate whether by reproduction.
2. the method as described in claim 1, which is characterized in that in the certificate image two width or several, be overlapped
Degree verification, comprising:
The first registration for obtaining the first distance image and the second distance image carries out school to first registration
It tests.
3. the method as described in claim 1, which is characterized in that obtain the certificate image of two width or two width of certificate or more, wrap
It includes:
Obtain first distance image, intermediate distance image and the second distance image of certificate, wherein first distance, medium spacing
It is sequentially increased from second distance.
4. method as claimed in claim 3, which is characterized in that in the certificate image two width or several, be overlapped
Degree verification, comprising:
The first distance image, intermediate distance image and second distance image of certificate are subjected to registration verification.
5. method as claimed in claim 4, which is characterized in that by the first distance image of certificate, intermediate distance image and
Second distance image carries out registration verification, comprising:
The first distance image of certificate and the second registration of intermediate distance image are obtained, school is carried out to second registration
It tests；
The intermediate distance image of certificate and the third registration of second distance image are obtained, school is carried out to the third registration
It tests；
In the case where the second registration is greater than first threshold and third registration is greater than second threshold, verification passes through；
In the case where the second registration is less than or equal to first threshold or third registration is less than or equal to second threshold, verify obstructed
It crosses.
6. method as claimed in claim 5, which is characterized in that obtain the first distance image and intermediate distance image of certificate
Second registration, comprising:
It by the first distance Image Adjusting is first be aligned with the intermediate distance image space positions based on preset algorithm
Distance conversion image；
Obtain the second registration of first distance the conversion image and second distance image.
7. method as claimed in claim 6, which is characterized in that obtain the intermediate distance image and second distance image of certificate
Third registration, comprising:
It by the intermediate distance Image Adjusting is the centre being aligned with the second distance image space positions based on preset algorithm
Distance conversion image；
Obtain the third registration of intermediate distance the conversion image and second distance image.
8. the method as described in claim 1, which is characterized in that using one or more reproduction models, it is general to calculate the first reproduction
Rate and the second reproduction probability, comprising:
The first distance image that verification is passed through inputs the first reproduction model, obtains the first reproduction probability；
The second distance image that verification is passed through inputs the second reproduction model, obtains the second reproduction probability.
9. method as claimed in claim 1 or 8, which is characterized in that according to the first reproduction probability and the second reproduction probability, judgement
Whether certificate is by reproduction, comprising:
In the case where the first reproduction probability is less than or equal to third threshold value and the second reproduction probability is less than or equal to four threshold values, determine
Certificate is not by reproduction；
In the case where the first reproduction probability is greater than third threshold value or the second reproduction probability is greater than four threshold values, determine that certificate is turned over
It claps.
10. method as claimed in claim 9, which is characterized in that in the case where determining certificate by reproduction, output reproduction prompt
Information.
11. method according to claim 8, which is characterized in that the first reproduction model is trained by the following method:
It will be marked with the first distance image zooming-out feature vector of reproduction type, described eigenvector includes first distance image
Spectrum signature, textural characteristics and/or color characteristic；
Using the feature vector of first distance image as training sample, using the label of reproduction type as training label, using two
Disaggregated model is trained to obtain the first reproduction model, wherein the reproduction type includes reproduction and non-reproduction.
12. method according to claim 8, which is characterized in that the second reproduction model is trained by the following method:
It will be marked with the second distance image zooming-out feature vector of reproduction type, described eigenvector includes second distance image
Spectrum signature and/or contour feature；
Using the feature vector of second distance image as training sample, using the label of reproduction type as training label, using two
Disaggregated model is trained to obtain the second reproduction model, wherein the reproduction type includes reproduction and non-reproduction.
13. a kind of device of certificate false proof, which is characterized in that described device includes:
Module is obtained, two width for obtaining certificate or certificate images more than two width are configured as, the certificate image includes from the
One distance obtain first distance image and from second distance obtain second distance image, wherein first distance and second away from
From difference；
Registration correction verification module, be configured as in the certificate image two width or several, carry out registration verification；
Reproduction probability evaluation entity passes through if being configured as verification, using one or more reproduction models, calculates first distance figure
First reproduction probability of picture and the second reproduction probability of second distance image；
Whether reproduction judgment module is configured as judging certificate by reproduction according to the first reproduction probability and the second reproduction probability.
14. device as claimed in claim 13, which is characterized in that the registration correction verification module is specifically configured to: obtaining
First registration of the first distance image and the second distance image verifies first registration.
15. device as claimed in claim 13, which is characterized in that the acquisition module is specifically configured to:
Obtain first distance image, intermediate distance image and the second distance image of certificate, wherein first distance, normal pitch
It is sequentially increased from second distance.
16. device as claimed in claim 15, which is characterized in that the registration correction verification module is specifically configured to: will be demonstrate,proved
First distance image, intermediate distance image and the second distance image of part carry out registration verification.
17. device as claimed in claim 16, which is characterized in that the registration correction verification module is specifically configured to: obtaining
The first distance image of certificate and the second registration of intermediate distance image, verify second registration；
The intermediate distance image of certificate and the third registration of second distance image are obtained, school is carried out to the third registration
It tests；
In the case where the second registration is greater than first threshold and third registration is greater than second threshold, verification passes through；
In the case where the second registration is less than or equal to first threshold or third registration is less than or equal to second threshold, verify obstructed
It crosses.
18. device as claimed in claim 17, which is characterized in that the registration correction verification module is specifically configured to: being based on
The first distance Image Adjusting is that the first distance being aligned with the intermediate distance image space positions is converted by preset algorithm
Image；
Obtain the second registration of first distance the conversion image and second distance image.
19. device as claimed in claim 18, which is characterized in that the registration correction verification module is specifically configured to: being based on
The intermediate distance Image Adjusting is that the intermediate distance being aligned with the second distance image space positions is converted by preset algorithm
Image；
Obtain the third registration of intermediate distance the conversion image and second distance image.
20. device as claimed in claim 13, which is characterized in that the reproduction probability evaluation entity is specifically configured to: will
It verifies the first distance image passed through and inputs the first reproduction model, obtain the first reproduction probability；
The second distance image that verification is passed through inputs the second reproduction model, obtains the second reproduction probability.
21. the device as described in claim 13 or 20, which is characterized in that the reproduction judgment module is specifically configured to:
First reproduction probability is less than or equal to third threshold value and the second reproduction probability is less than or equal in the case where the 4th threshold value, determines certificate not
By reproduction；
In the case where the first reproduction probability is greater than third threshold value or the second reproduction probability is greater than four threshold values, determine that certificate is turned over
It claps.
22. a kind of calculating equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine instruction, which is characterized in that the processor realizes that certificate described in claim 1-12 any one is anti-when executing described instruction
The step of method of puppet.
23. a kind of computer readable storage medium, is stored with computer instruction, which is characterized in that the instruction is held by processor
The step of method of certificate false proof described in claim 1-12 any one is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910142956.8A CN110046644B (en) | 2019-02-26 | 2019-02-26 | Certificate anti-counterfeiting method and device, computing equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910142956.8A CN110046644B (en) | 2019-02-26 | 2019-02-26 | Certificate anti-counterfeiting method and device, computing equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110046644A true CN110046644A (en) | 2019-07-23 |
| CN110046644B CN110046644B (en) | 2023-04-07 |
Family
ID=67274280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910142956.8A Active CN110046644B (en) | 2019-02-26 | 2019-02-26 | Certificate anti-counterfeiting method and device, computing equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110046644B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110648314A (en) * | 2019-09-05 | 2020-01-03 | 阿里巴巴集团控股有限公司 | Method, device and equipment for identifying copied image |
| CN110705532A (en) * | 2019-09-05 | 2020-01-17 | 阿里巴巴集团控股有限公司 | Method, device and equipment for identifying copied image |
| CN110827219A (en) * | 2019-10-31 | 2020-02-21 | 北京小米智能科技有限公司 | Training method, device and medium of image processing model |
| CN111062922A (en) * | 2019-12-14 | 2020-04-24 | 创新奇智(北京)科技有限公司 | Method and system for judging copied image and electronic equipment |
| CN111127398A (en) * | 2019-11-25 | 2020-05-08 | 深圳前海微众银行股份有限公司 | Method and device for detecting certificate photo duplication, terminal equipment and storage medium |
| CN111259894A (en) * | 2020-01-20 | 2020-06-09 | 普信恒业科技发展（北京）有限公司 | Certificate information identification method and device and computer equipment |
| CN111275105A (en) * | 2020-01-19 | 2020-06-12 | 支付宝实验室(新加坡)有限公司 | Certificate verification method and device and electronic equipment |
| CN111368944A (en) * | 2020-05-27 | 2020-07-03 | 支付宝(杭州)信息技术有限公司 | Method and device for recognizing copied image and certificate photo and training model and electronic equipment |
| GB2584547A (en) * | 2019-04-08 | 2020-12-09 | Bud Andrew | Document authentication by attitude-independent determination of surface appearance using controlled illumination |
| 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 |
| CN112257709A (en) * | 2020-10-23 | 2021-01-22 | 北京云杉世界信息技术有限公司 | Signboard photo auditing method and device, electronic equipment and readable storage medium |
| WO2021068142A1 (en) * | 2019-10-09 | 2021-04-15 | 深圳大学 | Training method and detection method for automatically identifying recaptured image of original document |
| WO2021151313A1 (en) * | 2020-07-30 | 2021-08-05 | 平安科技（深圳）有限公司 | Method and apparatus for document forgery detection, electronic device, and storage medium |
| CN113222952A (en) * | 2021-05-20 | 2021-08-06 | 支付宝(杭州)信息技术有限公司 | Method and device for identifying copied image |
| CN113628091A (en) * | 2021-10-09 | 2021-11-09 | 杭州海康威视数字技术股份有限公司 | Safety information extraction method and device for electronic display screen content reproduction scene |
| CN112257709B (en) * | 2020-10-23 | 2024-05-07 | 北京云杉世界信息技术有限公司 | Signboard photo auditing method and device, electronic equipment and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105118048A (en) * | 2015-07-17 | 2015-12-02 | 北京旷视科技有限公司 | Method and device for identifying copying certificate image |
| CN106599772A (en) * | 2016-10-31 | 2017-04-26 | 北京旷视科技有限公司 | Living body authentication method, identity authentication method and device |
| CN107729847A (en) * | 2017-10-20 | 2018-02-23 | 阿里巴巴集团控股有限公司 | A kind of certificate verification, auth method and device |
| CN107944339A (en) * | 2017-10-20 | 2018-04-20 | 阿里巴巴集团控股有限公司 | A kind of certificate verification, auth method and device |
| CN109325933A (en) * | 2017-07-28 | 2019-02-12 | 阿里巴巴集团控股有限公司 | A kind of reproduction image-recognizing method and device |
| CN109359502A (en) * | 2018-08-13 | 2019-02-19 | 北京市商汤科技开发有限公司 | False-proof detection method and device, electronic equipment, storage medium |
-
2019
- 2019-02-26 CN CN201910142956.8A patent/CN110046644B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105118048A (en) * | 2015-07-17 | 2015-12-02 | 北京旷视科技有限公司 | Method and device for identifying copying certificate image |
| CN106599772A (en) * | 2016-10-31 | 2017-04-26 | 北京旷视科技有限公司 | Living body authentication method, identity authentication method and device |
| CN109325933A (en) * | 2017-07-28 | 2019-02-12 | 阿里巴巴集团控股有限公司 | A kind of reproduction image-recognizing method and device |
| CN107729847A (en) * | 2017-10-20 | 2018-02-23 | 阿里巴巴集团控股有限公司 | A kind of certificate verification, auth method and device |
| CN107944339A (en) * | 2017-10-20 | 2018-04-20 | 阿里巴巴集团控股有限公司 | A kind of certificate verification, auth method and device |
| CN109359502A (en) * | 2018-08-13 | 2019-02-19 | 北京市商汤科技开发有限公司 | False-proof detection method and device, electronic equipment, storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 谢心谦等: "基于深度学习的图像翻拍检测", 《电脑知识与技术》 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2584547A (en) * | 2019-04-08 | 2020-12-09 | Bud Andrew | Document authentication by attitude-independent determination of surface appearance using controlled illumination |
| GB2584547B (en) * | 2019-04-08 | 2023-02-22 | Bud Andrew | Document authentication by attitude-independent determination of surface appearance using controlled illumination |
| US11235613B2 (en) | 2019-04-08 | 2022-02-01 | iProov Ltd. | Document authentication by attitude-independent determination of surface appearance using controlled illumination |
| CN110705532B (en) * | 2019-09-05 | 2023-04-18 | 创新先进技术有限公司 | Method, device and equipment for identifying copied image |
| CN110648314A (en) * | 2019-09-05 | 2020-01-03 | 阿里巴巴集团控股有限公司 | Method, device and equipment for identifying copied image |
| CN110705532A (en) * | 2019-09-05 | 2020-01-17 | 阿里巴巴集团控股有限公司 | Method, device and equipment for identifying copied image |
| WO2021068142A1 (en) * | 2019-10-09 | 2021-04-15 | 深圳大学 | Training method and detection method for automatically identifying recaptured image of original document |
| CN110827219A (en) * | 2019-10-31 | 2020-02-21 | 北京小米智能科技有限公司 | Training method, device and medium of image processing model |
| CN110827219B (en) * | 2019-10-31 | 2023-04-07 | 北京小米智能科技有限公司 | Training method, device and medium of image processing model |
| CN111127398A (en) * | 2019-11-25 | 2020-05-08 | 深圳前海微众银行股份有限公司 | Method and device for detecting certificate photo duplication, terminal equipment and storage medium |
| CN111127398B (en) * | 2019-11-25 | 2023-09-26 | 深圳前海微众银行股份有限公司 | Certificate photo copying detection method and device, terminal equipment and storage medium |
| CN111062922B (en) * | 2019-12-14 | 2024-02-20 | 创新奇智(北京)科技有限公司 | Method and system for distinguishing flip image and electronic equipment |
| CN111062922A (en) * | 2019-12-14 | 2020-04-24 | 创新奇智(北京)科技有限公司 | Method and system for judging copied image and electronic equipment |
| CN111275105A (en) * | 2020-01-19 | 2020-06-12 | 支付宝实验室(新加坡)有限公司 | Certificate verification method and device and electronic equipment |
| CN111275105B (en) * | 2020-01-19 | 2023-10-20 | 支付宝实验室(新加坡)有限公司 | Certificate verification method and device and electronic equipment |
| CN111259894B (en) * | 2020-01-20 | 2023-07-07 | 普信恒业科技发展（北京）有限公司 | Certificate information identification method and device and computer equipment |
| CN111259894A (en) * | 2020-01-20 | 2020-06-09 | 普信恒业科技发展（北京）有限公司 | Certificate information identification method and device and computer equipment |
| CN111368944A (en) * | 2020-05-27 | 2020-07-03 | 支付宝(杭州)信息技术有限公司 | Method and device for recognizing copied image and certificate photo and training model and electronic equipment |
| WO2021151313A1 (en) * | 2020-07-30 | 2021-08-05 | 平安科技（深圳）有限公司 | Method and apparatus for document forgery detection, electronic device, and storage medium |
| 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 |
| CN112257709A (en) * | 2020-10-23 | 2021-01-22 | 北京云杉世界信息技术有限公司 | Signboard photo auditing method and device, electronic equipment and readable storage medium |
| CN112257709B (en) * | 2020-10-23 | 2024-05-07 | 北京云杉世界信息技术有限公司 | Signboard photo auditing method and device, electronic equipment and readable storage medium |
| CN113222952A (en) * | 2021-05-20 | 2021-08-06 | 支付宝(杭州)信息技术有限公司 | Method and device for identifying copied image |
| CN113222952B (en) * | 2021-05-20 | 2022-05-24 | 蚂蚁胜信(上海)信息技术有限公司 | Method and device for identifying copied image |
| CN113628091A (en) * | 2021-10-09 | 2021-11-09 | 杭州海康威视数字技术股份有限公司 | Safety information extraction method and device for electronic display screen content reproduction scene |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110046644B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110046644A (en) | A kind of method and device of certificate false proof calculates equipment and storage medium | |
| EP2595092B1 (en) | Methods and systems for improved license plate signature matching | |
| Swaminathan et al. | Digital image forensics via intrinsic fingerprints | |
| US8582819B2 (en) | Methods and systems for improving yield in wanted vehicle searches | |
| CN108596026B (en) | Cross-view gait recognition device and training method based on double-flow generation countermeasure network | |
| CN110457511B (en) | Image classification method and system based on attention mechanism and generation countermeasure network | |
| CN109871845B (en) | Certificate image extraction method and terminal equipment | |
| CN108288012A (en) | A kind of art work realized based on mobile phone is put on record verification method and its system | |
| Kanwal et al. | Digital image splicing detection technique using optimal threshold based local ternary pattern | |
| Christlein et al. | A study on features for the detection of copy-move forgeries | |
| EP3588380A1 (en) | Information processing method and information processing apparatus | |
| CN115244542A (en) | Method and device for verifying authenticity of product | |
| CN111209858A (en) | Real-time license plate detection method based on deep convolutional neural network | |
| CN108323209A (en) | Information processing method, system, cloud processing device and computer program product | |
| EP3657390A1 (en) | Object recognition system and method using simulated object images | |
| Triantoro et al. | Image based water gauge reading developed with ANN Kohonen | |
| CN110674689B (en) | Vehicle re-identification method and system based on feature embedding space geometric constraint | |
| CN110826551B (en) | Intelligent screening method for VIN code topology printing mode image of motor vehicle | |
| CN105513071A (en) | Topographic map schema quality evaluation method | |
| CN109784257A (en) | A kind of detection of transformer thermometer and recognition methods | |
| CN111046899B (en) | Identification card authenticity identification method, device, equipment and storage medium | |
| CN112597810A (en) | Identity document authentication method and system | |
| CN111080586A (en) | Method for obtaining evidence of tampered image source based on convolutional neural network | |
| CN114494038B (en) | Target surface perspective distortion correction method based on improved YOLOX-S | |
| CN113111833B (en) | Safety detection method and device of artificial intelligence system and terminal equipment |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201019 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. Effective date of registration: 20201019 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |