CN110046644B - Certificate anti-counterfeiting method and device, computing equipment and storage medium - Google Patents
Certificate anti-counterfeiting method and device, computing equipment and storage medium Download PDFInfo
- Publication number
- CN110046644B CN110046644B CN201910142956.8A CN201910142956A CN110046644B CN 110046644 B CN110046644 B CN 110046644B CN 201910142956 A CN201910142956 A CN 201910142956A CN 110046644 B CN110046644 B CN 110046644B
- Authority
- CN
- China
- Prior art keywords
- distance
- copying
- distance image
- image
- certificate
- 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.)
- Active
Links
Images
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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Editing Of Facsimile Originals (AREA)
- Image Analysis (AREA)
Abstract
The application provides a certificate anti-counterfeiting method and device, computing equipment and a storage medium, wherein the certificate anti-counterfeiting method comprises the following steps: acquiring two or more certificate images of a certificate, wherein the certificate images comprise a first distance image acquired from a first distance and a second distance image acquired from a second distance, and the first distance and the second distance are different; performing coincidence degree check on two or more certificate images; if the verification is passed, calculating a first copying probability of the first distance image and a second copying probability of the second distance image by using one or more copying models; and judging whether the certificate is copied or not according to the first copying probability and the second copying probability, so that the authenticity of the image does not need to be identified manually, the time consumed by certificate image identification is reduced, and the identification efficiency is improved.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a method and an apparatus for certificate counterfeiting prevention, a computing device, and a storage medium.
Background
For financial scenarios, it is important to authenticate the act of falsifying identity or counterfeiting using counterfeit documents. The act of counterfeiting a certificate by a black product user can be divided into two categories: physical and electronic document counterfeiting. Physical document counterfeiting refers to modifying document information directly on the physical entity of the document, including physically modifying the user identity information (e.g., by using paint, physical patches to tamper with name, birth date information) or directly creating a counterfeit document. The electronic certificate counterfeiting refers to the behavior of information tampering (for example, tampering by using a picture repairing tool) on an obtained electronic certificate image after a physical certificate is electronized by means of photographing and scanning.
Compared with physical certificate counterfeiting, electronic certificate counterfeiting has the characteristics that a counterfeit target is easy to obtain (only by taking a picture of a certificate, but not taking the physical certificate), counterfeiting cost is low, counterfeiting tools (such as Photoshop and other image changing software) are easy to obtain, effects are vivid and the like, batch attack is easy to cause, and important precaution is needed for electronic services such as internet finance and the like. However, the counterfeiting of the electronic certificate also has a weakness, namely after the counterfeiting is finished, the (forged) electronic certificate must be presented by means of a certain physical mode (such as computer or mobile phone screen display, printer printing and the like), and then is recorded into a target application (such as a certain internet banking remote account opening application) by using another terminal through a secondary copying mode.
Therefore, how to indirectly prevent and control the counterfeiting of the electronic certificate by means of the identification of the screen reproduction is a technical problem to be solved.
Disclosure of Invention
In view of the above, one or more embodiments of the present disclosure provide a method and an apparatus for document anti-counterfeiting, a computing device and a storage medium, so as to solve the technical defects in the prior art.
One or more embodiments of the present specification disclose a method of document authentication, the method comprising:
acquiring two or more certificate images of a certificate, wherein the certificate images comprise a first distance image acquired from a first distance and a second distance image acquired from a second distance, and the first distance and the second distance are different;
performing contact ratio verification on two or more certificate images;
if the verification is passed, calculating a first copying probability of the first distance image and a second copying probability of the second distance image by using one or more copying models;
and judging whether the certificate is copied or not according to the first copying probability and the second copying probability.
Optionally, performing a contact ratio check on two or more of the document images, including:
and acquiring a first coincidence degree of the first distance image and the second distance image, and verifying the first coincidence degree.
Optionally, acquiring two or more document images of the document comprises:
and acquiring a first distance image, a middle distance image and a second distance image of the certificate, wherein the first distance, the middle distance and the second distance are sequentially increased.
Optionally, performing a goodness-of-fit check on two or more of the document images, including:
and carrying out coincidence degree check on the first distance image, the middle distance image and the second distance image of the certificate.
Optionally, performing a coincidence check on the first distance image, the intermediate distance image, and the second distance image of the document includes:
acquiring a second coincidence degree of the first distance image and the middle distance image of the certificate, and verifying the second coincidence degree;
acquiring a third coincidence degree of the middle distance image and the second distance image of the certificate, and checking the third coincidence degree;
in the case that the second degree of overlap is greater than the first threshold and the third degree of overlap is greater than the second threshold, the verification passes;
and if the second coincidence degree is less than or equal to the first threshold value or the third coincidence degree is less than or equal to the second threshold value, the verification is not passed.
Optionally, acquiring a second degree of coincidence of the first range image and the intermediate range image of the document, comprises:
adjusting the first distance image into a first distance conversion image aligned with the spatial position of the intermediate distance image based on a preset algorithm;
and acquiring a second coincidence degree of the first distance conversion image and the second distance image.
Optionally, acquiring a third degree of coincidence of the intermediate range image and the second range image of the document comprises:
adjusting the intermediate distance image into an intermediate distance conversion image aligned with the second distance image in spatial position based on a preset algorithm;
and acquiring a third coincidence degree of the intermediate distance conversion image and the second distance image.
Optionally, calculating the first and second rendering probabilities using one or more rendering models comprises:
inputting the first distance image passing the verification into a first copying model to obtain a first copying probability;
and inputting the second distance image passing the verification into a second copying model to obtain a second copying probability.
Optionally, judging whether the document is copied according to the first copying probability and the second copying probability includes:
determining that the certificate is not copied under the condition that the first copying probability is less than or equal to a third threshold value and the second copying probability is less than or equal to a fourth threshold value;
and under the condition that the first copying probability is greater than a third threshold value or the second copying probability is greater than a fourth threshold value, determining that the certificate is copied.
Optionally, in case that the certificate is determined to be copied, outputting a copying prompt message.
Optionally, the first copying model is trained by:
extracting a feature vector from the first distance image marked with the copying type, wherein the feature vector comprises a frequency spectrum feature, a texture feature and/or a color feature of the first distance image;
the feature vector of the first distance image is used as a training sample, the mark of the copying type is used as a training label, and the first copying model is obtained by training through a two-classification model, wherein the copying type comprises copying and non-copying.
Optionally, the second copying model is trained by:
extracting a feature vector from the second distance image marked with the copying type, wherein the feature vector comprises a frequency spectrum feature and/or a contour feature of the second distance image;
and taking the feature vector of the second distance image as a training sample, taking the mark of the copying type as a training label, and training by adopting a binary model to obtain the second copying model, wherein the copying type comprises copying and non-copying.
One or more embodiments of the present specification disclose a device for the security of documents, the device comprising:
an acquisition module configured to acquire two or more document images of a document, the document images including a first distance image acquired from a first distance and a second distance image acquired from a second distance, wherein the first distance and the second distance are different;
a contact ratio check module configured to perform contact ratio check on two or more of the document images;
the copying probability calculation module is configured to calculate a first copying probability of the first distance image and a second copying probability of the second distance image by using one or more copying models if the verification passes;
and the copying judgment module is configured to judge whether the certificate is copied according to the first copying probability and the second copying probability.
Optionally, the contact ratio verification module is specifically configured to: and acquiring a first coincidence degree of the first distance image and the second distance image, and checking the first coincidence degree.
Optionally, the obtaining module is specifically configured to:
and acquiring a first distance image, a middle distance image and a second distance image of the certificate, wherein the first distance, the standard distance and the second distance are increased in sequence.
Optionally, the contact ratio verification module is specifically configured to: and carrying out coincidence degree check on the first distance image, the middle distance image and the second distance image of the certificate.
Optionally, the contact ratio verification module is specifically configured to: acquiring a second coincidence degree of the first distance image and the middle distance image of the certificate, and verifying the second coincidence degree;
acquiring a third coincidence degree of the middle distance image and the second distance image of the certificate, and checking the third coincidence degree;
in the case that the second degree of overlap is greater than the first threshold and the third degree of overlap is greater than the second threshold, the verification passes;
and if the second coincidence degree is less than or equal to the first threshold value or the third coincidence degree is less than or equal to the second threshold value, the verification is not passed.
Optionally, the contact ratio verification module is specifically configured to: adjusting the first distance image into a first distance conversion image aligned with the space position of the intermediate distance image based on a preset algorithm;
and acquiring a second coincidence degree of the first distance conversion image and the second distance image.
Optionally, the contact ratio coincidence check module is specifically configured to: adjusting the intermediate distance image into an intermediate distance conversion image aligned with the second distance image in spatial position based on a preset algorithm;
and acquiring a third coincidence degree of the intermediate distance conversion image and the second distance image.
Optionally, the flap probability calculation module is specifically configured to: inputting the first distance image passing the verification into a first copying model to obtain a first copying probability;
and inputting the second distance image passing the verification into a second copying model to obtain a second copying probability.
Optionally, the reproduction determination module is specifically configured to: determining that the certificate is not copied under the condition that the first copying probability is less than or equal to a third threshold value and the second copying probability is less than or equal to a fourth threshold value;
and under the condition that the first copying probability is greater than a third threshold value or the second copying probability is greater than a fourth threshold value, determining that the certificate is copied.
One or more embodiments of the present specification disclose a computing device comprising a memory, a processor, and computer instructions stored on the memory and executable on the processor, the processor implementing the steps of the method for document counterfeiting prevention as described above when executing the instructions.
One or more embodiments of the present specification disclose a computer readable storage medium storing computer instructions which, when executed by a processor, implement the steps of a method of document authentication as described above.
The method and the device for preventing the certificate from counterfeiting provided by one or more embodiments of the specification calculate a first copying probability of a first distance image and a second copying probability of a second distance image by acquiring two or more certificate images of the certificate, then performing coincidence degree check on two or more certificate images, and if the two or more certificate images pass the check, using one or more copying models, and judging whether the certificate is copied according to the first copying probability and the second probability, so that a plurality of images of the certificate are combined with the copying models to realize prevention and control of the certificate images. The certificate anti-counterfeiting method in one or more embodiments of the specification does not need manual identification of authenticity of the image, time consumed by certificate image identification is reduced, and identification efficiency is improved.
In addition, compared with a common single-picture anti-copying method, the certificate anti-counterfeiting method obtains the richer foreground information and background information of the certificate by obtaining the first distance image, the middle distance image and the second distance image of the certificate, improves the accuracy of screen copying identification, and has important significance for preventing and controlling counterfeit certificates in internet application.
Drawings
FIG. 1 is a schematic block diagram of a computing device according to one or more embodiments of the present description;
FIG. 2 is a schematic flow diagram of a method of securing documents according to one or more embodiments of the present disclosure;
FIG. 3 is a schematic flow diagram of a method of securing documents according to one or more embodiments of the present disclosure;
FIG. 4 is a schematic flow diagram of a method for securing documents according to one or more embodiments of the present disclosure;
FIG. 5 is a schematic structural diagram of a device for document authentication according to one or more embodiments of the present disclosure.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is capable of implementation in many different ways than those herein set forth and of similar import by those skilled in the art without departing from the spirit of this application and is therefore not limited to the specific implementations disclosed below.
The terminology used in the description of the one or more embodiments is for the purpose of describing the particular embodiments only and is not intended to be limiting of the description of the one or more embodiments. As used in one or more embodiments of the present specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present specification refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It will be understood that, although the terms first, second, etc. may be used herein in one or more embodiments to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first can be termed a second and, similarly, a second can be termed a first without departing from the scope of one or more embodiments of the present description. The word "if" as used herein may be interpreted as "at" \8230; "or" when 8230; \8230; "or" in response to a determination ", depending on the context.
First, the noun terms to which one or more embodiments of the present invention relate are explained.
OCR: optical character recognition, generally refers to a technique for locating and recognizing character information in pictures.
Core body: verifying authenticity of user identity
Certificate anti-counterfeiting: means for authenticating counterfeit documents.
Image characteristics: the image features include: color features, texture features, shape features, and spatial relationship features. Wherein, the color feature is a global feature describing surface properties of a scene corresponding to the image or the image area; texture features are also global features that also describe the surface properties of the scene corresponding to an image or image area; the shape features are represented by two types, one is outline features, the other is region features, the outline features of the image mainly aim at the outer boundary of the object, and the region features of the image are related to the whole shape region; the spatial relationship feature refers to a spatial position or a relative direction relationship between a plurality of objects segmented from an image, and these relationships can be classified into a connection/adjacency relationship, an overlapping/overlapping relationship, an inclusion/containment relationship, and the like.
In one or more embodiments of the present disclosure, a method and apparatus, computing device, and storage medium for providing authentication of a document are provided, each of which is described in detail in the following embodiments.
Fig. 1 is a block diagram illustrating a structure of a computing device 100 according to an embodiment of the present specification. The components of the computing device 100 include, but are not limited to, memory 110 and processor 120. The processor 120 is coupled to the memory 110 via a bus 130 and a database 150 is used to store data.
Computing device 100 also includes access device 140, access device 140 enabling computing device 100 to communicate via one or more networks 160. Examples of such networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. Access device 140 may include one or more of any type of network interface (e.g., a Network Interface Card (NIC)) whether wired or wireless, such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.
In one embodiment of the present description, the above-described components of computing device 100 and other components not shown in FIG. 1 may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device architecture shown in FIG. 1 is for purposes of example only and is not limiting as to the scope of the description. Other components may be added or replaced as desired by those skilled in the art.
Computing device 100 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), a mobile phone (e.g., smartphone), a wearable computing device (e.g., smartwatch, smartglasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 100 may also be a mobile or stationary server.
Wherein the processor 120 may perform the steps of the method shown in fig. 2. FIG. 2 is a schematic flow chart diagram illustrating a method of document authentication including steps 202 through 208 according to one embodiment of the present description.
202. Two or more document images of the document are acquired, the document images including a first distance image acquired from a first distance and a second distance image acquired from a second distance, wherein the first distance and the second distance are different.
The embodiment can be used for acquiring two images of the certificate, including a first distance image and a second distance image; the method can also be used for acquiring more than two images of the certificate, wherein the images comprise a first distance image, a middle distance image and a second distance image, and the first distance, the middle distance and the second distance are sequentially increased. By acquiring a plurality of images and comparing in subsequent steps, the accuracy of the certificate identification result can be increased.
The first distance image, the middle distance image and the second distance image of the certificate can be acquired in various manners, for example, by clicking and uploading by a user.
In the practical application process, the large and small target object view frames of the shooting device can be adopted for shooting once respectively. The large view-finding frame is used for photographing to obtain a close-range image of the certificate, so that more certificate foreground information (such as Moire patterns on a screen during copying) can be obtained; the small view finder is used for photographing to obtain the remote image of the certificate, so that more certificate background information (such as a screen frame of copying equipment) can be obtained, and thus, the corresponding images in two distances are obtained: a first range image and a second range image. It is then necessary to take the document once at a normal distance, wherein the image of the document taken at a normal distance only includes the entire image of the document itself. Thus, the intermediate distance image of the corresponding certificate is obtained.
204. And carrying out coincidence degree check on two or more certificate images.
The purpose of the contact ratio check is: in order to prevent the phenomenon of bag adjustment shooting in the process of shooting multiple pictures, two or more certificate images need to be checked.
For the case of acquiring a first range image and a second range image of a document, step 204 includes: and acquiring a first coincidence degree of the first distance image and the second distance image, and checking the first coincidence degree.
For the case of acquiring a first range image, an intermediate range image and a second range image of a document, step 204 includes: and carrying out coincidence degree check on the first distance image, the middle distance image and the second distance image of the certificate.
In this embodiment, there are various methods for performing the overlap ratio check, and a specific method for performing the overlap ratio check is described below to schematically illustrate the method for performing the overlap ratio check in this embodiment. Specifically, referring to fig. 3, the step of performing the coincidence degree check on the first distance image, the middle distance image and the second distance image of the certificate includes the following steps 302 to 308:
302. and acquiring the second coincidence degree of the first distance image and the middle distance image of the certificate, and verifying the second coincidence degree.
Specifically, step 302 includes:
s3022, adjusting the first distance image into a first distance conversion image aligned with the spatial position of the intermediate distance image based on a preset algorithm;
and S3024, acquiring a second coincidence degree of the first distance conversion image and the second distance image.
The preset algorithm includes, but is not limited to, an Image registration algorithm, that is, an Image registration algorithm, and the Image registration algorithm can match two images in a certain sense.
Specifically, in this step, the intermediate distance image is used as a basis, the first distance image is used as a transformed image, that is, feature extraction is performed on the first distance image and the intermediate distance image to obtain feature points, a matching feature point pair is found by performing similarity measurement, then an image space coordinate transformation parameter is obtained by the matching feature point pair, and finally image registration is performed by the coordinate transformation parameter. The feature points are feature information such as points, lines, and edges of the image.
Image registration (Image registration) is a process of matching and superimposing two or more images acquired at different times and different sensors (imaging devices) or under different conditions (weather, illuminance, camera position, angle, and the like), and has been widely applied to the fields of remote sensing data analysis, computer vision, image processing, and the like. There are many ways of image registration, such as using Scale-invariant feature transform (SIFT) algorithm, etc.
304. And acquiring a third coincidence degree of the middle distance image and the second distance image of the certificate, and checking the third coincidence degree.
Specifically, step 304 includes:
s3042, adjusting the intermediate distance image into an intermediate distance conversion image aligned with the second distance image in space position based on a preset algorithm;
s3044, a third coincidence ratio of the intermediate distance conversion image and the second distance image is obtained.
Specifically, in this step, the second distance image is used as a basis, the intermediate distance image is used as a transformed image, that is, feature extraction is performed on the intermediate distance image and the second distance image to obtain feature points, a matching feature point pair is found by performing similarity measurement, then an image space coordinate transformation parameter is obtained by the matching feature point pair, and finally image registration is performed by the coordinate transformation parameter. The feature points are feature information such as points, lines, and edges of the image.
306. In the case that the second degree of overlap is greater than the first threshold and the third degree of overlap is greater than the second threshold, the verification passes.
308. And if the second coincidence degree is less than or equal to the first threshold value or the third coincidence degree is less than or equal to the second threshold value, the verification is not passed.
The first threshold and the second threshold may be set according to actual requirements, for example, the first threshold and the second threshold are both set to 0.8.
It should be noted that in this embodiment, the three images are divided into two groups for coincidence degree check, and the check is passed when the coincidence degrees of the two groups of images are respectively greater than the threshold value; for the case of failed verification, in the case where the degree of coincidence of a group of images is equal to or less than the threshold value, the verification fails.
And under the condition that the verification is not passed, interrupting the execution of the subsequent flow and outputting prompt information. The prompting information can be output in various ways, for example, in an application program, the image input by the prompting user is not in compliance and needs to be input again. The images of the document are re-uploaded three distances after user confirmation and step 202 is re-executed.
206. And if the verification is passed, calculating a first copying probability of the first distance image and a second copying probability of the second distance image by using one or more copying models.
In this step, a first reproduction probability and a second reproduction probability can be calculated by using a reproduction model; the first and second rendering probabilities may also be calculated separately using two rendering models.
Specifically, step 206 includes:
s2062, inputting the first distance image passing the verification into the first copying model to obtain a first copying probability.
And S2064, inputting the second distance image passing the verification into a second copying model to obtain a second copying probability.
Specifically, extracting a characteristic vector from the first distance image passing the verification, and inputting the characteristic vector into a first copying model to obtain a first copying probability;
and extracting a characteristic vector from the second distance image passing the verification, and inputting the characteristic vector into a second copying model to obtain a second copying probability.
Wherein the first rendering model is trained by the following steps S12-S14:
s12, extracting a feature vector of the first distance image marked with the copying type, wherein the feature vector comprises a frequency spectrum feature, a texture feature and/or a color feature of the first distance image.
The spectral features can be used to identify the presence of screen reflections in the captured image.
The texture features may be used to identify moire or other distortion conditions in the first range image, such as resolution distortion, aliasing, and the like. Moire is a high frequency interference fringe on a light-sensitive element of a digital camera or scanner, which is a high frequency irregular fringe that causes a picture to appear in color. Moire patterns are important parameters for distinguishing between a copied image and a non-copied image. For a reproduced image, moire fringes in a frequency domain are more obvious, and colors of the moire fringes are also different from colors of moire fringes of a non-reproduced image.
The color features may be used to identify situations of local color distortion in the reproduced image.
S14, taking the feature vector of the first distance image as a training sample, taking the mark of the copying type as a training label, and training by adopting a binary model to obtain the first copying model, wherein the copying type comprises copying and non-copying.
Wherein the second rendering model is trained by the following steps S22 to S24:
and S22, extracting a feature vector from the second distance image marked with the copying type, wherein the feature vector comprises a spectrum feature and/or a contour feature of the second distance image.
The spectral features can be used to identify the presence of screen reflections in the captured image.
The outline features may be used to identify the presence of the border of the rendering device (cell phone or display) in the rendered image.
It can be seen that, for the first and second rendering models, the feature vectors of the input first and second distance images are different, because the first distance image focuses more on the local view, more document foreground details (such as moire on the screen during rendering) can be acquired; the second range image focuses more on the environment view, and can acquire more background information (such as a mobile phone or a display screen frame during reproduction).
And S24, taking the feature vector of the second distance image as a training sample, taking the mark of the copying type as a training label, and training by adopting a binary model to obtain the second copying model, wherein the copying type comprises copying and non-copying.
It can be seen from the above steps that the first and second copying models are obtained by training the two classification models, and the difference is that the input samples are different. The binary model may be various, such as a binary model generated by using a CNN convolutional neural network.
Generally, a convolutional neural network includes thousands of iteration parameters, but only a part of the iteration parameters may have an influence on the prediction result of an image. In the training stage of the model, the iterative parameters of the part which affect the prediction result of the image can be found out first, and then the iterative parameters of the part are adjusted, so that the prediction result of the trained first copying model or the trained second copying model can be more accurate.
208. And judging whether the certificate is copied or not according to the first copying probability and the second copying probability.
Specifically, step 208 includes:
s2082, determining that the certificate is not copied under the condition that the first copying probability is less than or equal to the third threshold value and the second copying probability is less than or equal to the fourth threshold value;
s2084, under the condition that the first copying probability is larger than the third threshold value or the second copying probability is larger than the fourth threshold value, the certificate is determined to be copied.
It should be noted that, both step S2082 and step S2084 need to determine the first and second flap probabilities, but the step S2082 needs to satisfy the condition of "and", that is, the first flap probability is less than or equal to the third threshold and the second flap probability is less than or equal to the fourth threshold; in step S2084, the condition of "or" needs to be satisfied, that is, the first copying probability is greater than the third threshold or the second copying probability is greater than the fourth threshold.
The third threshold and the fourth threshold may be set according to actual requirements, for example, both the third threshold and the fourth threshold are set to be 0.8.
And after determining that the certificate is not copied, outputting and processing the intermediate distance image as an image of the certificate. In actual use, for example, in an application program for remote account opening, the intermediate distance image can be output to a certificate character OCR recognition module of the application program as an image of the certificate for processing.
And after the copying of the certificate is determined, outputting prompt information. The prompt message can be output in various ways, such as a pop-up dialog box, output text message, and the like.
In the method for preventing the certificate from counterfeiting provided by one or more embodiments of the present specification, two or more certificate images of the certificate are acquired, then the coincidence degree of the two or more certificate images is checked, if the two or more certificate images pass the coincidence degree check, one or more copying models are used to calculate the first copying probability and the second copying probability, and whether the certificate is copied is judged according to the first copying probability and the second copying probability, so that the multiple images of the certificate are combined with the copying models to realize the prevention and control of the certificate images. The certificate anti-counterfeiting method in one or more embodiments of the specification does not need manual identification of authenticity of the image, time consumed by certificate image identification is reduced, and identification efficiency is improved.
In addition, compared with a common single-picture anti-copying method, the certificate anti-counterfeiting method in the embodiment of the description obtains the first distance image, the middle distance image and the second distance image of the certificate, so that richer foreground information and background information of the certificate are obtained, accuracy of screen copying identification is improved, and the method has important significance for internet application and anti-counterfeiting certificate control.
An embodiment of the present specification discloses a method for preventing a certificate from being faked, referring to fig. 4, comprising the following steps 402 to 420:
402. acquiring a first distance image, a middle distance image and a second distance image of the certificate, wherein the first distance, the middle distance and the second distance are increased in sequence.
The first distance image, the middle distance image and the second distance image of the certificate can be acquired in various manners, for example, by clicking and uploading by a user.
404. And (5) performing coincidence degree check on the first distance image, the middle distance image and the second distance image of the certificate, if the check is passed, executing step 406, and if the check is not passed, executing step 408.
406. Inputting the first distance image passing the verification into the first copying model to obtain a first copying probability of the first distance image, inputting the second distance image passing the verification into the second copying model to obtain a second copying probability of the second distance image, and then executing step 410.
408. And outputting a verification failure prompt message and returning to execute the step 402.
410. Determining whether the first copying probability is greater than a first threshold, if yes, executing step 412, and if not, executing step 414.
412. And determining that the first distance image is a copied image, and executing step 420.
414. It is determined whether the second copying probability is greater than the second threshold, if so, go to step 416, and if not, go to step 418.
416. And determining that the second distance image is a copied image, and executing step 420.
418. And outputting and processing the intermediate distance image as the image of the certificate.
420. And outputting the copying prompt information under the condition that the first distance image or the second distance image is determined to be the copied image, and returning to the step 402.
The flipping prompt may be a dialog box that pops up in the application, and after the user clicks confirmation, the step 402 is returned to.
In the certificate anti-counterfeiting method provided by the embodiment, a plurality of images of the certificate at different distances are acquired, then the first distance image passing the coincidence degree check is input into the first copying model to obtain the first copying probability of the first distance image, and the second distance image passing the check is input into the second copying model to obtain the second copying probability of the second distance image; and under the condition that the first copying probability is less than or equal to the first threshold value and the second copying probability is less than or equal to the second threshold value, the second distance image is output and processed as the image of the certificate, so that the multi-distance image of the certificate is combined with the copying model to realize the prevention and control of the certificate image. The certificate anti-counterfeiting method does not need to manually identify the authenticity of the image, reduces the time consumed by certificate image identification, and improves the identification efficiency.
The above is a detailed description of a method for document anti-counterfeiting according to one or more embodiments of the present specification, and one or more embodiments of the present specification further disclose a device for document anti-counterfeiting. It should be noted that the technical scheme of the device for preventing the certificate from counterfeiting and the technical scheme of the method for preventing the certificate from counterfeiting belong to the same concept, and details which are not described in detail in the technical scheme of the device for preventing the certificate from counterfeiting can be referred to the description of the technical scheme of the method for preventing the certificate from counterfeiting.
Referring to fig. 5, an embodiment of the present disclosure discloses a device for preventing forgery of a document, including:
an acquisition module 502 configured to acquire two or more document images of a document, the document images including a first distance image acquired from a first distance and a second distance image acquired from a second distance, wherein the first distance and the second distance are different;
a contact ratio verification module 504 configured to perform contact ratio verification on two or more of the document images;
a copying probability calculation module 506 configured to calculate a first copying probability of the first range image and a second copying probability of the second range image using one or more copying models if the verification passes;
and the copying judging module 508 is configured to judge whether the certificate is copied according to the first copying probability and the second copying probability.
Optionally, the contact ratio verification module 504 is specifically configured to: and acquiring a first coincidence degree of the first distance image and the second distance image, and checking the first coincidence degree.
Optionally, the obtaining module 502 is specifically configured to: and acquiring a first distance image, a middle distance image and a second distance image of the certificate, wherein the first distance, the standard distance and the second distance are increased in sequence.
Optionally, the contact ratio coincidence check module 504 is specifically configured to: and carrying out coincidence degree check on the first distance image, the middle distance image and the second distance image of the certificate.
Optionally, the overlap ratio checking module 504 is specifically configured to: acquiring a second coincidence degree of the first distance image and the middle distance image of the certificate, and verifying the second coincidence degree;
acquiring a third coincidence degree of the middle distance image and the second distance image of the certificate, and verifying the third coincidence degree;
the verification passes under the condition that the second coincidence degree is greater than the first threshold value and the third coincidence degree is greater than the second threshold value;
and if the second coincidence degree is less than or equal to the first threshold value or the third coincidence degree is less than or equal to the second threshold value, the verification is not passed.
Optionally, the overlap ratio checking module 504 is specifically configured to: adjusting the first distance image into a first distance conversion image aligned with the spatial position of the intermediate distance image based on a preset algorithm;
and acquiring a second coincidence degree of the first distance conversion image and the second distance image.
Optionally, the contact ratio verification module 504 is specifically configured to: adjusting the intermediate distance image into an intermediate distance conversion image aligned with the second distance image in spatial position based on a preset algorithm;
and acquiring a third coincidence degree of the intermediate distance conversion image and the second distance image.
Optionally, the flap probability calculation module 506 is specifically configured to: inputting the first distance image passing the verification into a first copying model to obtain a first copying probability; and inputting the second distance image passing the verification into a second copying model to obtain a second copying probability.
Optionally, the copying determining module 508 is specifically configured to: determining that the certificate is not copied under the condition that the first copying probability is less than or equal to a third threshold value and the second copying probability is less than or equal to a fourth threshold value; and under the condition that the first copying probability is greater than a third threshold value or the second copying probability is greater than a fourth threshold value, determining that the certificate is copied.
The anti-fake device of certificate that this embodiment provided is through the certificate image of two or more than two of acquireing the certificate, then right two or more carry out the coincidence degree check-up in the certificate image, if the check-up passes through, use one or more reproduction model, calculate first reproduction probability and second reproduction probability to judge whether the certificate is by the reproduction according to first reproduction probability and second reproduction probability, thereby utilize a plurality of images and the reproduction model of certificate to combine together, realize the prevention and control to the certificate image. The certificate anti-counterfeiting method in one or more embodiments of the specification does not need manual identification of authenticity of the image, time consumed by certificate image identification is reduced, and identification efficiency is improved.
An embodiment of the present specification also provides a computing device comprising a memory, a processor, and computer instructions stored on the memory and executable on the processor, wherein the processor executes the instructions to implement the steps of the method for preventing the forgery of the document.
An embodiment of the present specification also provides a computer readable storage medium storing computer instructions which, when executed by a processor, implement the steps of the method for document anti-counterfeiting as described above.
The above is an illustrative scheme of a computer-readable storage medium of the present embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned certificate anti-counterfeiting method belong to the same concept, and details that are not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned certificate anti-counterfeiting method.
The computer instructions comprise computer program code which may be in the form of source code, object code, an executable file or some intermediate form, or the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
It should be noted that, for the sake of simplicity, the foregoing method embodiments are described as a series of acts or combinations, but those skilled in the art should understand that the present disclosure is not limited by the described order of acts, as some steps may be performed in other orders or simultaneously according to the present disclosure. Further, those skilled in the art should also appreciate that the embodiments described in this specification are preferred embodiments and that acts and modules referred to are not necessarily required for this description.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The preferred embodiments of the present specification disclosed above are intended only to aid in the description of the specification. Alternative embodiments are not exhaustive and do not limit the invention to the precise embodiments described. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the specification and its practical application, to thereby enable others skilled in the art to best understand the specification and utilize the specification. The specification is limited only by the claims and their full scope and equivalents.
Claims (23)
1. A method of security of a document, the method comprising:
acquiring two or more certificate images of a certificate, wherein the certificate images comprise a first distance image acquired from a first distance and a second distance image acquired from a second distance, the first distance and the second distance are different, and the second distance is greater than the first distance;
performing contact ratio verification on two or more certificate images;
if the verification is passed, calculating a first copying probability of the first distance image and a second copying probability of the second distance image by using one or more copying models;
and judging whether the certificate is copied or not according to the first copying probability and the second copying probability.
2. The method of claim 1, wherein performing a coincidence check on two or more of the document images comprises:
and acquiring a first coincidence degree of the first distance image and the second distance image, and checking the first coincidence degree.
3. The method of claim 1, wherein acquiring two or more document images of the document comprises:
acquiring a first distance image, a middle distance image and a second distance image of the certificate, wherein the first distance, the middle distance and the second distance are increased in sequence.
4. A method as claimed in claim 3, wherein performing a coincidence check on two or more of the document images comprises:
and carrying out coincidence degree check on the first distance image, the middle distance image and the second distance image of the certificate.
5. The method of claim 4, wherein performing a coincidence check on the first range image, the intermediate range image, and the second range image of the document comprises:
acquiring a second coincidence degree of the first distance image and the middle distance image of the certificate, and verifying the second coincidence degree;
acquiring a third coincidence degree of the middle distance image and the second distance image of the certificate, and checking the third coincidence degree;
the verification passes under the condition that the second coincidence degree is greater than the first threshold value and the third coincidence degree is greater than the second threshold value;
and if the second coincidence degree is less than or equal to the first threshold value or the third coincidence degree is less than or equal to the second threshold value, the verification is not passed.
6. The method of claim 5, wherein obtaining a second degree of coincidence of the first range image and the intermediate range image of the document comprises:
adjusting the first distance image into a first distance conversion image aligned with the space position of the intermediate distance image based on a preset algorithm;
and acquiring a second coincidence degree of the first distance conversion image and the intermediate distance image.
7. The method of claim 6, wherein acquiring a third degree of overlap of the intermediate range image and the second range image of the document comprises:
adjusting the intermediate distance image into an intermediate distance conversion image aligned with the second distance image in spatial position based on a preset algorithm;
and acquiring a third coincidence degree of the intermediate distance conversion image and the second distance image.
8. The method of claim 1, wherein calculating the first and second rendering probabilities using one or more rendering models comprises:
inputting the first distance image passing the verification into a first copying model to obtain a first copying probability;
and inputting the second distance image passing the verification into a second copying model to obtain a second copying probability.
9. The method of claim 1 or 8, wherein determining whether the document is copied based on the first probability of copying and the second probability of copying comprises:
determining that the certificate is not copied under the condition that the first copying probability is less than or equal to a third threshold value and the second copying probability is less than or equal to a fourth threshold value;
and under the condition that the first copying probability is greater than a third threshold value or the second copying probability is greater than a fourth threshold value, determining that the certificate is copied.
10. The method of claim 9, wherein in the event that it is determined that the document is copied, outputting a copy hint.
11. The method of claim 8, wherein the first rendering model is trained by:
extracting a feature vector from the first distance image marked with the copying type, wherein the feature vector comprises a frequency spectrum feature, a texture feature and/or a color feature of the first distance image;
and taking the feature vector of the first distance image as a training sample, taking the mark of the copying type as a training label, and training by adopting a two-classification model to obtain the first copying model, wherein the copying type comprises copying and non-copying.
12. The method of claim 8, wherein the second rendering model is trained by:
extracting a feature vector from the second distance image marked with the copying type, wherein the feature vector comprises a frequency spectrum feature and/or a contour feature of the second distance image;
and taking the feature vector of the second distance image as a training sample, taking the mark of the copying type as a training label, and training by adopting a binary model to obtain the second copying model, wherein the copying type comprises copying and non-copying.
13. A device for securing documents against forgery, the device comprising:
an acquisition module configured to acquire two or more document images of a document, the document images including a first distance image acquired from a first distance and a second distance image acquired from a second distance, wherein the first distance and the second distance are different, the second distance being greater than the first distance;
a contact ratio verification module configured to perform contact ratio verification on two or more of the document images;
the copying probability calculation module is configured to calculate a first copying probability of the first distance image and a second copying probability of the second distance image by using one or more copying models if the verification passes;
and the copying judgment module is configured to judge whether the certificate is copied according to the first copying probability and the second copying probability.
14. The apparatus of claim 13, wherein the overlap ratio check module is specifically configured to: and acquiring a first coincidence degree of the first distance image and the second distance image, and checking the first coincidence degree.
15. The apparatus of claim 13, wherein the acquisition module is specifically configured to:
acquiring a first distance image, a middle distance image and a second distance image of the certificate, wherein the first distance, the middle distance and the second distance are increased in sequence.
16. The apparatus of claim 15, wherein the overlap ratio check module is specifically configured to: and (5) carrying out coincidence degree check on the first distance image, the middle distance image and the second distance image of the certificate.
17. The apparatus of claim 16, wherein the overlap ratio check module is specifically configured to: acquiring a second coincidence degree of the first distance image and the middle distance image of the certificate, and verifying the second coincidence degree;
acquiring a third coincidence degree of the middle distance image and the second distance image of the certificate, and checking the third coincidence degree;
the verification passes under the condition that the second coincidence degree is greater than the first threshold value and the third coincidence degree is greater than the second threshold value;
and if the second coincidence degree is less than or equal to the first threshold value or the third coincidence degree is less than or equal to the second threshold value, the verification is not passed.
18. The apparatus of claim 17, wherein the overlap ratio check module is specifically configured to: adjusting the first distance image into a first distance conversion image aligned with the spatial position of the intermediate distance image based on a preset algorithm;
and acquiring a second coincidence degree of the first distance conversion image and the intermediate distance image.
19. The apparatus of claim 18, wherein the overlap ratio check module is specifically configured to: adjusting the intermediate distance image into an intermediate distance conversion image aligned with the second distance image in spatial position based on a preset algorithm;
and acquiring a third coincidence degree of the intermediate distance conversion image and the second distance image.
20. The apparatus of claim 13, wherein the flap probability calculation module is specifically configured to: inputting the first distance image passing the verification into a first copying model to obtain a first copying probability;
and inputting the second distance image passing the verification into a second copying model to obtain a second copying probability.
21. The apparatus of claim 13 or 20, wherein the duplication decision module is specifically configured to: determining that the certificate is not copied under the condition that the first copying probability is less than or equal to a third threshold value and the second copying probability is less than or equal to a fourth threshold value;
and under the condition that the first copying probability is greater than a third threshold value or the second copying probability is greater than a fourth threshold value, determining that the certificate is copied.
22. A computing device comprising a memory, a processor and computer instructions stored on the memory and executable on the processor, wherein the processor when executing the instructions performs the steps of the method of securing the authenticity of a document as claimed in any one of claims 1 to 12.
23. A computer readable storage medium storing computer instructions which, when executed by a processor, carry out the steps of a method of securing the authenticity of a document as claimed in any one of claims 1 to 12.
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 CN110046644A (en) | 2019-07-23 |
| CN110046644B true 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) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11235613B2 (en) | 2019-04-08 | 2022-02-01 | iProov Ltd. | Document authentication by attitude-independent determination of surface appearance using controlled illumination |
| CN110648314B (en) * | 2019-09-05 | 2023-08-04 | 创新先进技术有限公司 | Method, device and equipment for identifying flip image |
| 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 |
| 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 |
| 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 |
| 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 |
| CN117237974A (en) * | 2020-01-19 | 2023-12-15 | 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 |
| CN111368944B (en) * | 2020-05-27 | 2020-09-08 | 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 |
| CN111898538B (en) * | 2020-07-30 | 2024-04-12 | 平安科技（深圳）有限公司 | Certificate authentication method and device, electronic equipment and storage medium |
| 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 |
| 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 |
| 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 |
| CN113628091B (en) * | 2021-10-09 | 2022-03-01 | 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 |
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 |
|---|
| 基于深度学习的图像翻拍检测;谢心谦等;《电脑知识与技术》;20170630(第16期);第161-162、177页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110046644A (en) | 2019-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110046644B (en) | Certificate anti-counterfeiting method and device, computing equipment and storage medium | |
| US11893777B2 (en) | Systems and methods for image based content capture and extraction utilizing deep learning neural network and bounding box detection training techniques | |
| Scherhag et al. | Detection of face morphing attacks based on PRNU analysis | |
| US20220406029A1 (en) | Tamper detection for identification documents | |
| Jourabloo et al. | Face de-spoofing: Anti-spoofing via noise modeling | |
| Birajdar et al. | Digital image forgery detection using passive techniques: A survey | |
| Swaminathan et al. | Digital image forensics via intrinsic fingerprints | |
| US20190213408A1 (en) | Document authenticity determination | |
| EP3772036A1 (en) | Detection of near-duplicate image | |
| US11023708B2 (en) | Within document face verification | |
| Armas Vega et al. | Copy-move forgery detection technique based on discrete cosine transform blocks features | |
| CN108288012A (en) | A kind of art work realized based on mobile phone is put on record verification method and its system | |
| Wang | A simple and effective image-statistics-based approach to detecting recaptured images from LCD screens | |
| Liu et al. | Detect image splicing with artificial blurred boundary | |
| CN110008943B (en) | Image processing method and device, computing equipment and storage medium | |
| CN113642639B (en) | Living body detection method, living body detection device, living body detection equipment and storage medium | |
| Mazumdar et al. | Universal image manipulation detection using deep siamese convolutional neural network | |
| CN112329786A (en) | Method, device and equipment for detecting copied image and storage medium | |
| Jwaid et al. | An efficient technique for image forgery detection using local binary pattern (hessian and center symmetric) and transformation method | |
| JP7421652B2 (en) | How to identify the authenticity of an object | |
| CN112101296B (en) | Face registration method, face verification method, device and system | |
| CN116434312A (en) | Safety detection method and device for image recognition model | |
| CN114241493B (en) | Training method and training device for training data of augmented document analysis model | |
| Hu et al. | Document recapture detection based on a unified distortion model of halftone cells | |
| CN110415424B (en) | Anti-counterfeiting identification method and device, computer equipment and storage medium |
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 |