CN109815970B - Method and device for identifying copied image, computer equipment and storage medium - Google Patents
Method and device for identifying copied image, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109815970B CN109815970B CN201811572818.5A CN201811572818A CN109815970B CN 109815970 B CN109815970 B CN 109815970B CN 201811572818 A CN201811572818 A CN 201811572818A CN 109815970 B CN109815970 B CN 109815970B
- Authority
- CN
- China
- Prior art keywords
- image
- gray value
- identified
- preset
- pixel point
- 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
Landscapes
- Facsimile Image Signal Circuits (AREA)
- Image Analysis (AREA)
Abstract
The present application relates to image recognition technologies, and in particular, to a method and an apparatus for recognizing a copied image, a computer device, and a storage medium. The method comprises the following steps: acquiring an image to be identified; carrying out Fourier transform on the image to be identified to obtain a frequency spectrum characteristic diagram; carrying out binarization processing on the frequency spectrum characteristic diagram; filtering the frequency spectrum characteristic diagram after the binarization processing to obtain a filtering characteristic diagram; adjusting the gray value of each pixel point in the central area block of the filtering characteristic graph and the gray value of each pixel point on the median line to be a first preset gray value; calculating the number of gray values in the adjusted filter characteristic graph equal to a second preset gray value; judging whether the number reaches a number threshold value, if so, determining that the image to be identified is a reproduction image; and if not, determining that the image to be identified is a non-reproduction image. By adopting the method, the potential safety hazard of the user information caused by the fact that a third party uses the copied image can be avoided.
Description
Technical Field
The present application relates to the field of image recognition technologies, and in particular, to a method and an apparatus for recognizing a copied image, a computer device, and a storage medium.
Background
With the continuous development of computer technology and internet technology, opening an account or transacting important services in an online manner is increasingly favored by users. When the above-mentioned service operation is performed, the user may be required to shoot and upload a corresponding image, such as a certificate image of the user or a real image of the user himself, through a mobile terminal or a network camera or other devices.
However, the uploaded image may not be a real image obtained by the user through shooting the user or a certificate image obtained by shooting a real certificate, but obtained by copying a picture displayed on a display screen of a computer or a mobile phone, and the like, so that the uploaded image has a problem of counterfeiting, and the user information has a safety problem.
Disclosure of Invention
Therefore, it is necessary to provide a method and an apparatus for identifying a copied image, a computer device, and a storage medium, which can avoid the potential safety hazard of user information caused by using the copied image by a third party.
A method of identifying a copied image, the method comprising:
acquiring an image to be identified;
carrying out Fourier transform on the image to be identified to obtain a frequency spectrum characteristic diagram;
carrying out binarization processing on the frequency spectrum characteristic diagram;
filtering the frequency spectrum characteristic diagram after the binarization processing to obtain a filtering characteristic diagram;
adjusting the gray value of each pixel point in the central area block of the filtering characteristic graph and the gray value of each pixel point on the median line to be a first preset gray value;
calculating the number of gray values in the adjusted filter characteristic graph equal to a second preset gray value;
judging whether the number reaches a number threshold value, if so, determining that the image to be identified is a reproduction image; and if not, determining that the image to be identified is a non-reproduction image.
In one embodiment, the method further comprises:
before Fourier transformation is carried out on the image to be recognized, the size of the image to be recognized is determined;
when the size of the image to be recognized is larger than a preset first critical size or smaller than a preset second critical size, zooming the image to be recognized according to a preset standard size;
the Fourier transform of the image to be identified to obtain a frequency spectrum characteristic diagram comprises the following steps:
decomposing the zoomed image to be recognized into three images of RGB three channels;
respectively carrying out Fourier transform on the three images, and carrying out synthesis processing on the images obtained after the Fourier transform;
and converting the synthesized image into a single-channel spectral feature map.
In one embodiment, the binarizing processing the spectrum feature map includes:
determining a gray threshold;
when the gray value of a pixel point in the frequency spectrum characteristic graph is larger than or equal to the gray threshold value, setting the gray value as a first preset gray value;
and when the gray value of the pixel point in the frequency spectrum characteristic graph is smaller than the gray threshold, setting the gray value as a second preset gray value.
In one embodiment, the filtering the spectrum feature map after the binarization processing to obtain a filtering feature map includes:
acquiring a sliding window for framing each pixel point in the image;
when filtering processing is carried out on a target pixel point, framing the pixel point in the target pixel point field by using the sliding window;
determining a first number of the framed pixel points with the gray value equal to the first preset gray value and a second number of the framed pixel points with the gray value equal to the second preset gray value;
when the first number is larger than the second number, setting the gray value of the target pixel point as the first preset gray value;
and when the first number is smaller than the second number, setting the gray value of the target pixel point as the second preset gray value.
In one embodiment, the method is applied to a registration management system; the method further comprises the following steps:
when the image to be recognized is determined to be a copied image, obtaining communication identification of an auditor with management authority in the registration management system;
sending an identification request carrying the image to be identified to the communication identifier of the auditor;
receiving feedback information for the identification request;
and when the image to be recognized is determined to be a copied image according to the feedback information, rejecting a registration request corresponding to the image to be recognized.
In one embodiment, the method is applied to social applications; the acquiring the image to be recognized comprises the following steps:
receiving an image to be identified sent by an opposite-end contact person through the social application;
the method further comprises the following steps:
when the image to be identified is determined to be a copied image, detecting whether text information sent by the opposite-end contact person comprises preset sensitive keywords;
and if so, sending prompt information to the common friends of the opposite-end contact person.
An apparatus for recognizing a reproduced image, the apparatus comprising:
the image acquisition module is used for acquiring an image to be identified;
the transformation module is used for carrying out Fourier transformation on the image to be identified to obtain a frequency spectrum characteristic diagram;
the binarization processing module is used for carrying out binarization processing on the frequency spectrum characteristic diagram;
the filtering processing module is used for carrying out filtering processing on the frequency spectrum characteristic diagram after the binarization processing to obtain a filtering characteristic diagram;
the gray value adjusting module is used for adjusting the gray value of each pixel point in the central area block of the filtering characteristic graph and the gray value of each pixel point on the median line to be a first preset gray value;
the quantity calculating module is used for calculating the quantity of the gray values in the adjusted filtering characteristic diagram equal to a second preset gray value;
the image determining module is used for judging whether the number reaches a number threshold value, and if so, determining the image to be identified as a copied image; and if not, determining that the image to be identified is a non-reproduction image.
In one embodiment, the apparatus further comprises:
the size determining module is used for determining the size of the image to be identified;
the image scaling module is used for scaling the image to be recognized according to a preset standard size when the size of the image to be recognized is larger than a preset first critical size or smaller than a preset second critical size;
the transformation module is also used for decomposing the zoomed image to be identified into three images of RGB three channels; respectively carrying out Fourier transform on the three images, and carrying out synthesis processing on the images obtained after the Fourier transform; and converting the synthesized image into a single-channel spectral feature map.
In one embodiment, the binarization processing module is further configured to determine a gray threshold; when the gray value of a pixel point in the frequency spectrum characteristic graph is larger than or equal to the gray threshold value, setting the gray value as a first preset gray value; and when the gray value of the pixel point in the frequency spectrum characteristic graph is smaller than the gray threshold value, setting the gray value as a second preset gray value.
In one embodiment, the filtering processing module is further configured to obtain a sliding window for framing each pixel point in the image; when filtering processing is carried out on a target pixel point, framing the pixel point in the target pixel point field by using the sliding window; determining a first number of the framed pixel points with the gray value equal to the first preset gray value and a second number of the framed pixel points with the gray value equal to the second preset gray value; when the first number is larger than the second number, setting the gray value of the target pixel point as the first preset gray value; and when the first number is smaller than the second number, setting the gray value of the target pixel point as the second preset gray value.
In one embodiment, the identification method of the copied image is applied to a registration management system; the device further comprises:
the communication identifier acquisition module is used for acquiring the communication identifier of the auditor with the management authority in the registration management system when the image to be identified is determined to be the copied image;
the identification request sending module is used for sending an identification request carrying the image to be identified to the communication identifier of the auditor;
a feedback information receiving module, configured to receive feedback information for the identification request;
and the registration request rejection module is used for rejecting the registration request corresponding to the image to be identified when the image to be identified is determined to be the copied image according to the feedback information.
In one embodiment, the method is applied to social applications; the image acquisition module is also used for receiving the image to be identified sent by the opposite-end contact person through the social application;
the device further comprises:
the keyword detection module is used for detecting whether text information sent by the opposite-end contact person comprises preset sensitive keywords or not when the image to be identified is determined to be a copied image;
and the prompt information sending module is used for sending prompt information to a common friend of the opposite-end contact person when the text information is detected to include the preset sensitive keywords.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring an image to be identified;
performing Fourier transform on the image to be identified to obtain a frequency spectrum characteristic diagram;
carrying out binarization processing on the frequency spectrum characteristic diagram;
filtering the frequency spectrum characteristic diagram after the binarization processing to obtain a filtering characteristic diagram;
adjusting the gray value of each pixel point in the central area block of the filtering characteristic graph and the gray value of each pixel point on the median line to be a first preset gray value;
calculating the number of gray values in the adjusted filter characteristic graph equal to a second preset gray value;
judging whether the number reaches a number threshold value, if so, determining that the image to be identified is a reproduction image; and if not, determining that the image to be identified is a non-reproduction image.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring an image to be identified;
carrying out Fourier transform on the image to be identified to obtain a frequency spectrum characteristic diagram;
carrying out binarization processing on the frequency spectrum characteristic diagram;
filtering the frequency spectrum characteristic diagram after the binarization processing to obtain a filtering characteristic diagram;
adjusting the gray value of each pixel point in the central area block of the filtering characteristic graph and the gray value of each pixel point on the median line to be a first preset gray value;
calculating the number of gray values in the adjusted filter characteristic graph equal to a second preset gray value;
judging whether the number reaches a number threshold value, if so, determining that the image to be identified is a reproduction image; if not, determining that the image to be identified is a non-reproduction image.
According to the identification method and device for the copied image, the computer equipment and the storage medium, the frequency spectrum characteristic diagram capable of reflecting the spectrum energy point aggregation condition is obtained by performing Fourier transform on the acquired image to be identified. The spectrum feature map is subjected to binarization processing, so that the size of image data can be reduced. The frequency spectrum characteristic graph after the binarization processing is subjected to filtering processing, so that isolated noise points in the image can be eliminated, and the accuracy of image copying identification can be improved. Adjusting the gray value of each pixel point in a central area block of the filtering characteristic graph and the gray value of each pixel point on a median line to be a first preset gray value, calculating the number of the gray values in the adjusted filtering characteristic graph equal to a second preset gray value, judging whether the number reaches a number threshold value, and if so, determining that the image to be identified is a reprinted image; if not, determining that the image to be recognized is a non-copied image, and realizing copying recognition of the image to be recognized, so that the image to be recognized is prevented from being obtained by copying a picture displayed on a display screen of equipment such as a computer or a mobile phone, authenticity of the image is ensured, and potential safety hazards of user information caused by using the copied image by a third party are avoided.
Drawings
FIG. 1 is a diagram illustrating an exemplary application of a method for recognizing a captured image;
FIG. 2 is a flowchart illustrating a method for recognizing a copied image according to an embodiment;
FIG. 3 is a flowchart illustrating steps of further identifying an image to be identified that is determined to be a snapshot and processing a registration request in one embodiment;
FIG. 4 is a block diagram showing the structure of an image recognition apparatus according to an embodiment;
FIG. 5 is a block diagram showing the construction of an image recognition apparatus according to another embodiment;
FIG. 6 is a diagram of the internal structure of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The method for recognizing the copied image can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The recognition method of the copied image can be applied to the terminal 102 and also applied to the server 104. When a use scene is a scene in which a financial account is registered for a user, the identification method of the copied image can be applied to the server 104, the server 104 obtains an image to be identified sent by the terminal 102, and performs Fourier transform on the image to be identified to obtain a frequency spectrum characteristic diagram; carrying out binarization processing on the frequency spectrum characteristic diagram; filtering the frequency spectrum characteristic diagram after the binarization processing to obtain a filtering characteristic diagram; adjusting the gray value of each pixel point in the central area block of the filtering characteristic graph and the gray value of each pixel point on the median line to be a first preset gray value; calculating the number of gray values in the adjusted filter characteristic graph equal to a second preset gray value; judging whether the number reaches a number threshold value, if so, determining that the image to be identified is a copied image; and if not, determining that the image to be identified is a non-reproduction image. If the image to be recognized is determined not to be a copied image, the server 104 may allow the terminal 102 to perform a corresponding business operation.
When the usage scene is a social scene of the user or the user performs the reproduction recognition through the terminal, the recognition method of the reproduced image may be applied to the terminal 102, and the terminal 102 performs the steps of the recognition method of the reproduced image.
The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server 104 may be implemented as a stand-alone server or a server cluster comprised of multiple servers.
In one embodiment, as shown in fig. 2, a method for recognizing a copied image is provided, which is described by taking the method as an example applied to the terminal 102 in fig. 1, and includes the following steps:
and S202, acquiring an image to be recognized.
The image to be recognized may be an RGB three-channel 32-bit color image.
In one embodiment, the terminal shoots an image to be identified through a camera; or the terminal acquires the image to be identified from the local album; or the terminal acquires the image to be identified from a server on the network side.
In one embodiment, if the identification method of the copied image is applied to a registration management system, that is, a usage scenario is a scenario of a user registration account (e.g., a registered financial account), the terminal displays an operation page for uploading the image. The operation page can have two function options, namely a function option for supporting a user to shoot images in real time, and a function option for supporting the user to select images acquired from the photo album. And if the user selects the function option for shooting the image in real time, the terminal calls a built-in camera to shoot the image of the user. And if the user selects the function option of acquiring the image from the photo album, the terminal acquires the image of the user from the local photo album.
It should be noted that, for acquiring the real image of the user himself, in order to avoid the third party from taking an image of another person for registration, on the operation page for uploading the real image of the user, a function option for acquiring an image from an album may not be provided.
For example, when a user opens an account on the internet with a credit card or securities, the account opening system displays an operation page for uploading a user certificate image and a real image of the user himself. When the real image of the user is uploaded, the function option for selecting the image from the photo album is not provided on the operation page, and the camera of the terminal is automatically called so that the user can shoot the image. When the user certificate image is uploaded, the operation page can provide a function option for selecting the image from the photo album, and also can provide a function option for shooting the image in real time so as to call a camera of the terminal to facilitate the user to shoot the image.
And S204, carrying out Fourier transform on the image to be identified to obtain a frequency spectrum characteristic diagram.
The obtained frequency spectrum characteristic diagram after Fourier transform can be a single-channel 8-bit gray scale diagram, and the frequency spectrum characteristic diagram reflects the aggregation condition of frequency spectrum energy points. The fourier transform may be a discrete fourier transform.
In one embodiment, before performing fourier transform, the terminal may determine a size of the image to be recognized, and when the size of the image to be recognized is greater than a preset first critical size or smaller than a preset second critical size, scale the image to be recognized according to a preset standard size. S204 may specifically include: decomposing the zoomed image to be recognized into three images of RGB three channels; fourier transformation is respectively carried out on the three images, and the images obtained after the transformation are subjected to synthesis processing; and converting the synthesized image into a single-channel spectral feature map.
For example, before performing fourier transform on the acquired image, the terminal determines the size of the image to be recognized, such as the image resolution or size. And if the size of the image to be recognized is too large or too small, the image is amplified or compressed to a preset standard size. And the terminal decomposes the zoomed image into three images according to RGB three channels, performs Fourier transform on each image, and then synthesizes the changed images to obtain a combined characteristic diagram. The terminal performs a gray scale conversion on the combined feature map, so that a single-channel spectral feature map can be obtained. In the above embodiment, the amount of calculation in the recognition process can be reduced by compressing an excessively large image.
And S206, performing binarization processing on the frequency spectrum characteristic diagram.
In an embodiment, S206 may specifically include: the terminal determines a gray threshold; when the gray value of a pixel point in the frequency spectrum characteristic graph is larger than or equal to a gray threshold, setting the gray value as a first preset gray value; and when the gray value of the pixel point in the frequency spectrum characteristic graph is smaller than the gray threshold, setting the gray value as a second preset gray value.
For example, the gray threshold may be set to 145, the first preset gray value may be 255, and the second preset gray value may be 0. In the process of carrying out binarization processing on the frequency spectrum characteristic diagram, the terminal sets the gray value of a pixel point with the gray value smaller than 145 in the frequency spectrum characteristic diagram to be 0. And for the pixel points with the gray value larger than or equal to 145, the gray value is 255.
And S208, filtering the frequency spectrum characteristic diagram after the binarization processing to obtain a filtering characteristic diagram.
Wherein the filtering may be median filtering. By performing filtering operation on the spectral feature map, isolated noise points in the spectral feature map can be eliminated, thereby suppressing image noise.
In an embodiment, S208 may specifically include: the method comprises the steps that a terminal obtains a sliding window used for framing each pixel point in an image; when filtering processing is carried out on the target pixel point, a sliding window is used for framing the pixel point in the field of the target pixel point; determining a first number of gray values of the framed pixel points equal to a first preset gray value and a second number of gray values equal to a second preset gray value; when the first number is larger than the second number, setting the gray value of the target pixel point as a first preset gray value; and when the first number is smaller than the second number, setting the gray value of the target pixel point as a second preset gray value.
Where the size of the sliding window may be x y, the matrix B may be used xy And (4) showing. x and y are both odd numbers, and x may be equal to y.
For example, assume that the spectral signature is a matrix A of m rows and n columns mn The sliding window is a 3-row and 3-column matrix B 3×3 . If it is to the matrix A mn Row i and column j element a in (1) ij (gradation value) binarizationThen, it is needed to be in the matrix A mn In which the element a is selected ij Of 3 rows and 3 columns of a matrix B 3×3 If the matrix B is 3×3 When the number of 0 s is larger than that of 255, the element a is added ij Setting to 0; if the number of 0 is less than the number of 255, the element a ij Is set to 255. The field is 3 rows and 3 columns of matrix B 3×3 May include the element a ij Or may not include the element a ij . Moreover, the sliding window avoids the framing matrix A as much as possible mn Of the element(s) that has been adjusted.
S210, adjusting the gray value of each pixel point in the central area block of the filtering characteristic graph and the gray value of each pixel point on the median line to be a first preset gray value.
In one embodiment, the terminal selects a central area block with a set proportion size from the filtering feature map, and adjusts the gray value of each pixel point in the central area block to be a first preset gray value. For example, in the central area block, if the size of the filter feature map is S, the central area block with the size of 1/3S may be selected from the filter feature map, and the gray value of each pixel in the central area block may be adjusted to 255.
In one embodiment, the terminal establishes a rectangular coordinate system with the center of the filter feature map as the origin and the median line of the filter feature map as the X-axis and the Y-axis, respectively. The terminal adjusts the gray value of each pixel point on the X axis and the Y axis to be a first preset gray value. For example, the gradation value of each pixel point on the X axis and the Y axis is adjusted to 255.
It should be noted that, in the central region block and on the median line of the filter feature map, data of a low-frequency part is mainly used, and the frequency of the image is mainly high-frequency. Therefore, the gray value on the median line in the central area block is adjusted to be the first preset gray value, and the interference of the low-frequency part signal to the identification result can be avoided when judging whether the image to be identified is a reproduction image.
S212, calculating the number of the gray values in the adjusted filter characteristic graph equal to a second preset gray value.
For example, for the filter feature map after adjusting the gray scale value, the gray scale value in the filter feature map includes 0 and 255, the number of gray scale values equal to 0 and the number of gray scale values equal to 255 are calculated.
S214, judging whether the number reaches a number threshold value, if so, determining that the image to be identified is a copied image; and if not, determining that the image to be identified is a non-reproduction image.
In one embodiment, S214 may specifically include: and the terminal judges the number and the number threshold of the second preset gray value, and when the number of the second preset gray value is greater than or equal to the preset number threshold, the acquired image to be identified is determined to be a copied image. And when the number of the second preset gray values is smaller than the preset number threshold, determining that the acquired image to be identified is not a reproduction image.
For example, assuming that the preset number threshold is 4000, when the number of 0 s in the adjusted filter feature map is greater than or equal to 4000, it is determined that the acquired image is a copied image. And when the number of 0 s in the adjusted filter characteristic map is less than 4000, judging that the acquired image is not a reproduced image.
In the embodiment, the acquired image to be identified is subjected to fourier transform, so that a spectrum characteristic diagram capable of reflecting the spectrum energy point aggregation condition is obtained. The spectrum feature map is subjected to binarization processing, so that the size of image data can be reduced. The frequency spectrum characteristic graph after the binarization processing is subjected to filtering processing, so that isolated noise points in the image can be eliminated, and the accuracy of image copying identification can be improved. Adjusting the gray value of each pixel point in a central area block of the filtering feature map and the gray value of each pixel point on a median line to be a first preset gray value, calculating the number of gray values in the adjusted filtering feature map which are equal to a second preset gray value, judging whether the number reaches a number threshold value, and if so, determining that the image to be identified is a reproduction image; if not, determining that the image to be recognized is a non-reproduction image, and realizing reproduction recognition of the image to be recognized, so that the image to be recognized is prevented from being a picture displayed on a display screen of a reproduction computer or a mobile phone and the like, authenticity of the image is ensured, and potential safety hazards of user information caused by the fact that a third party uses the reproduction image are avoided.
In one embodiment, the method for recognizing a copied image may be applied to a registration management system, and as shown in fig. 3, the method may further include:
s302, when the image to be identified is determined to be a copied image, obtaining a communication identifier of an auditor with management authority in the registration management system.
The communication identifier of the auditor can be a communication account of the auditor, and can also be a registration management system account of the auditor. The administrative rights may be audit rights. The communication account may be an instant social software account or an email account.
In order to reduce the error rate of the reproduction identification and further improve the accuracy of the reproduction identification, when the image to be identified is determined to be the reproduction image, further identification operation is required.
S304, sending an identification request carrying the image to be identified to the communication identifier of the auditor.
In one embodiment, if the communication identifier of the auditor is a communication account, the terminal sends an identification request carrying the image to be identified to the communication account, instructs the auditor to further identify the image to be identified, and gives feedback information after identification. For example, the terminal sends an identification request carrying an image to be identified to an e-mail box of an auditor, requests the auditor to audit the image to be identified, and sends identified feedback information to the registration management system in an e-mail manner.
In one embodiment, if the communication identifier of the auditor is a personal account of the registration management system, the terminal sends an identification request carrying an image to be identified to the personal account of the registration management system, when the auditor logs in the registration management system, the auditor can further identify the image to be identified, and feedback information is given after the identification.
S306, receiving feedback information for the identification request.
The feedback information may include information for confirming whether the image to be recognized is a copied image or a non-copied image.
And S308, when the image to be identified is determined to be the copied image according to the feedback information, rejecting the registration request corresponding to the image to be identified.
In one embodiment, the registration management system may be provided with an identification priority, i.e. an identification priority of the professional and an identification priority of the machine identification.
As an example, after determining that the image to be recognized is a copied image, in order to further ensure the accuracy of the recognition result, the image to be recognized is also sent to a professional, the professional performs further recognition on the image, and feeds back the recognition result, and if the fed back recognition result indicates that the image is a copied image, the image is determined to be a copied image. If the fed back recognition result shows that the image is not the copied image, determining the priority of the two modes, if the priority recognized by the professional is higher than the priority recognized by the machine, determining that the image is not the copied image, otherwise, determining that the image is the copied image.
In the above embodiment, when the image to be recognized is recognized as the copied image, the professional carries out further recognition, and the feedback information given by the professional is combined to give a final result, so that the error rate of the copied recognition can be reduced, the accuracy of the copied recognition can be improved, the picture displayed on the display screen of the device such as a copying computer or a mobile phone can be prevented from being obtained, the authenticity of the image is ensured, and the potential safety hazard of user information caused by the fact that a third party uses the copied image is avoided.
In an embodiment, the identification method of the copied image is applied to a social application, and S202 may specifically include: receiving an image to be identified sent by an opposite-end contact person through a social application; the method further comprises the following steps: when the image to be identified is determined to be a copied image, detecting whether text information sent by an opposite-end contact person includes preset sensitive keywords; and if so, sending prompt information to the common friends of the opposite-end contact person.
Specifically, when a user receives an image sent by an opposite terminal through social software, the terminal performs copying recognition on the received image by adopting the copying recognition method, and displays the recognition result in a text mode or plays the recognition result in a voice mode. If the sensitive keywords are involved (such as borrowing money), the terminal can mark the account number sending the copied image, meanwhile, the account number of the common friend is obtained, and then prompt information carrying the mark is sent to the account number of the common friend.
In one embodiment, the manner of marking may be to mark the user who sent the copied image as "there may be a security problem in the account", and the corresponding prompt information may be: the account YY named XX may present a security problem, and does not require a transfer operation to the other party.
For example, the prompt message is: "Account number 1234567 for one boat blade may present a security issue, do not transfer money to one boat blade". Therefore, the third party can be prevented from stealing other social account numbers, the copied image is sent to the contact in the social account number for fraudulent conduct, and property safety of the user is improved.
In addition, the method for identifying the reproduction can be applied to the small program, and if the user does not determine whether the image is the reproduced image, the user can identify the image through the small program. Wherein the applet may be an applet running on social software.
In the embodiment, the images received on the social software are copied and identified, if the images are recognized as the copied images and the user sending the copied images also sends sensitive words such as money borrowing and transfer, the account number of the user is marked as an account number with safety hazards, and prompt information is sent to common friends, so that the potential safety hazards of user information caused by the fact that a third party uses the copied images are avoided, and the property safety of the user is improved.
It should be understood that although the various steps in the flow charts of fig. 2-3 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-3 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 4, there is provided an apparatus for recognizing a copied image, including: an image acquisition module 402, a transformation module 404, a binarization processing module 406, a filtering processing module 408, a gray value adjustment module 410, a number calculation module 412 and an image determination module 414, wherein:
an image obtaining module 402, configured to obtain an image to be identified;
the transformation module 404 is configured to perform fourier transformation on an image to be identified to obtain a spectrum feature map;
a binarization processing module 406, configured to perform binarization processing on the frequency spectrum feature map;
the filtering processing module 408 is configured to perform filtering processing on the frequency spectrum feature map after the binarization processing to obtain a filtering feature map;
a gray value adjusting module 410, configured to adjust a gray value of each pixel point in the central region block of the filter feature map and a gray value of each pixel point on the median line to a first preset gray value;
a number calculating module 412, configured to calculate the number of gray values in the adjusted filter feature map that are equal to a second preset gray value;
an image determining module 414, configured to determine whether the number reaches a number threshold, and if yes, determine that the image to be recognized is a copied image; and if not, determining that the image to be identified is a non-reproduction image.
In the embodiment, the acquired image to be identified is subjected to fourier transform, so that the spectrum characteristic diagram capable of reflecting the spectrum energy point aggregation condition is obtained. The spectrum feature map is subjected to binarization processing, so that the size of image data can be reduced. The frequency spectrum characteristic graph after the binarization processing is subjected to filtering processing, so that isolated noise points in the image can be eliminated, and the accuracy of image copying identification can be improved. Adjusting the gray value of each pixel point in a central area block of the filtering feature map and the gray value of each pixel point on a median line to be a first preset gray value, calculating the number of gray values in the adjusted filtering feature map which are equal to a second preset gray value, judging whether the number reaches a number threshold value, and if so, determining that the image to be identified is a reproduction image; if not, determining that the image to be recognized is a non-reproduction image, and realizing reproduction recognition of the image to be recognized, so that the image to be recognized is prevented from being a picture displayed on a display screen of a reproduction computer or a mobile phone and the like, authenticity of the image is ensured, and potential safety hazards of user information caused by the fact that a third party uses the reproduction image are avoided.
In one embodiment, as shown in fig. 5, the apparatus further comprises: a size determination module 416 and an image scaling module 418; wherein:
a size determination module 416 for determining the size of the image to be recognized;
the image scaling module 418 is configured to scale the image to be recognized according to a preset standard size when the size of the image to be recognized is larger than a preset first critical size or smaller than a preset second critical size;
the transformation module 404 is further configured to decompose the scaled image to be recognized into three RGB three-channel images; fourier transformation is respectively carried out on the three images, and the images obtained after the transformation are subjected to synthesis processing; and converting the synthesized image into a single-channel spectral feature map.
In one embodiment, the binarization processing module 406 is further configured to determine a gray threshold; when the gray value of a pixel point in the frequency spectrum characteristic graph is larger than or equal to a gray threshold, setting the gray value as a first preset gray value; and when the gray value of the pixel point in the frequency spectrum characteristic graph is smaller than the gray threshold, setting the gray value as a second preset gray value.
In one embodiment, the filtering processing module 408 is further configured to obtain a sliding window for framing each pixel point in the image; when filtering processing is carried out on a target pixel point, a sliding window is used for framing the pixel points in the field of the target pixel point; determining a first number of gray values of the framed pixel points equal to a first preset gray value and a second number of gray values equal to a second preset gray value; when the first number is larger than the second number, setting the gray value of the target pixel point as a first preset gray value; and when the first number is smaller than the second number, setting the gray value of the target pixel point as a second preset gray value.
In one embodiment, the identification method of the copied image is applied to a registration management system; the device still includes: a communication identifier obtaining module 420, an identification request sending module 422, a feedback information receiving module 424 and a registration request rejecting module 426; wherein:
a communication identifier obtaining module 420, configured to obtain an auditor communication identifier with a management authority in the registration management system when it is determined that the image to be identified is a copied image;
an identification request sending module 422, configured to send an identification request carrying an image to be identified to an auditor communication identifier;
a feedback information receiving module 424, configured to receive feedback information for the identification request;
a registration request rejecting module 426, configured to reject the registration request corresponding to the image to be recognized when the image to be recognized is determined to be the copied image according to the feedback information.
In the above embodiment, when the image to be recognized is recognized as the copied image, the professional carries out further recognition, and the feedback information given by the professional is combined to give a final result, so that the error rate of the copied recognition can be reduced, the accuracy of the copied recognition can be improved, the picture displayed on the display screen of the device such as a copying computer or a mobile phone can be prevented from being obtained, the authenticity of the image is ensured, and the potential safety hazard of user information caused by the fact that a third party uses the copied image is avoided.
In one embodiment, the method is applied to social applications; the image acquisition module is also used for receiving the image to be identified sent by the opposite-end contact person through the social application;
the device still includes: a keyword detection module 428 and a prompt information sending module 430; wherein:
the keyword detection module 428 is configured to detect whether the text information sent by the opposite-end contact includes a preset sensitive keyword when it is determined that the image to be identified is a copied image;
and a prompt information sending module 430, configured to send prompt information to a common friend of the opposite-end contact when detecting that the text information includes a preset sensitive keyword.
In the embodiment, the images received on the social software are copied and identified, if the images are identified as the copied images and the user sending the copied images also sends sensitive words such as money borrowing and transfer, the account number of the user is marked as an account number with safety hazards, and prompt information is sent to common friends, so that the potential safety hazards of user information caused by the fact that a third party uses the copied images are avoided, and the property safety of the user is improved.
For specific limitations of the recognition device for the copied image, reference may be made to the above limitations on the recognition method for the copied image, and details are not repeated here. The modules in the device for recognizing the copied image can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, where the computer device may be a terminal or a server, and the computer device is taken as an example of a terminal, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of identifying a copied image. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program: acquiring an image to be identified; carrying out Fourier transform on an image to be identified to obtain a frequency spectrum characteristic diagram; carrying out binarization processing on the frequency spectrum characteristic diagram; filtering the frequency spectrum characteristic diagram after the binarization processing to obtain a filtering characteristic diagram; adjusting the gray value of each pixel point in a central area block of the filtering characteristic graph and the gray value of each pixel point on a median line to be a first preset gray value; calculating the number of gray values in the adjusted filter characteristic graph equal to a second preset gray value; judging whether the number reaches a number threshold value, if so, determining that the image to be identified is a copied image; and if not, determining that the image to be identified is a non-reproduction image.
In one embodiment, the processor, when executing the computer program, further performs the steps of: determining the size of an image to be identified; when the size of the image to be recognized is larger than a preset first critical size or smaller than a preset second critical size, zooming the image to be recognized according to a preset standard size; the Fourier transform is carried out on the image to be identified, and the spectrum characteristic diagram is obtained by the following steps: decomposing the zoomed image to be recognized into three images of RGB three channels; fourier transformation is respectively carried out on the three images, and the images obtained after the transformation are subjected to synthesis processing; and converting the synthesized image into a single-channel spectral feature map.
In one embodiment, the processor, when executing the computer program, further performs the steps of: determining a gray threshold; when the gray value of a pixel point in the frequency spectrum characteristic graph is larger than or equal to a gray threshold, setting the gray value as a first preset gray value; and when the gray value of the pixel point in the frequency spectrum characteristic graph is smaller than the gray threshold, setting the gray value as a second preset gray value.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring a sliding window for framing each pixel point in the image; when filtering processing is carried out on the target pixel point, a sliding window is used for framing the pixel point in the field of the target pixel point; determining a first number of the framed pixel points with the gray value equal to a first preset gray value and a second number of the framed pixel points with the gray value equal to a second preset gray value; when the first number is larger than the second number, setting the gray value of the target pixel point as a first preset gray value; and when the first number is smaller than the second number, setting the gray value of the target pixel point as a second preset gray value.
In one embodiment, the method is applied to a registration management system; the processor when executing the computer program further realizes the following steps: when the image to be identified is determined to be a copied image, acquiring a communication identifier of an auditor with management authority in a registration management system; sending an identification request carrying an image to be identified to an auditor communication identifier; receiving feedback information for the identification request; and when the image to be recognized is determined to be the copied image according to the feedback information, rejecting the registration request corresponding to the image to be recognized.
In one embodiment, the method is applied to social applications; the processor, when executing the computer program, further performs the steps of: receiving an image to be identified sent by an opposite-end contact person through a social application; the method further comprises the following steps: when the image to be identified is determined to be a copied image, detecting whether text information sent by an opposite-end contact person includes preset sensitive keywords; and if so, sending prompt information to a common friend of the opposite-end contact person.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring an image to be identified; carrying out Fourier transform on an image to be identified to obtain a frequency spectrum characteristic diagram; carrying out binarization processing on the frequency spectrum characteristic diagram; filtering the frequency spectrum characteristic diagram after the binarization processing to obtain a filtering characteristic diagram; adjusting the gray value of each pixel point in a central area block of the filtering characteristic graph and the gray value of each pixel point on a median line to be a first preset gray value; calculating the number of gray values in the adjusted filter characteristic graph equal to a second preset gray value; judging whether the number reaches a number threshold value, if so, determining that the image to be identified is a copied image; and if not, determining that the image to be identified is a non-reproduction image.
In one embodiment, the computer program when executed by the processor further performs the steps of: determining the size of an image to be identified; when the size of the image to be recognized is larger than a preset first critical size or smaller than a preset second critical size, zooming the image to be recognized according to a preset standard size; the Fourier transform is carried out on the image to be identified, and the spectrum characteristic diagram is obtained by the following steps: decomposing the zoomed image to be recognized into three images of RGB three channels; fourier transformation is respectively carried out on the three images, and the images obtained after the transformation are subjected to synthesis processing; and converting the synthesized image into a single-channel spectral feature map.
In one embodiment, the computer program when executed by the processor further performs the steps of: determining a gray threshold; when the gray value of a pixel point in the frequency spectrum characteristic graph is larger than or equal to a gray threshold, setting the gray value as a first preset gray value; and when the gray value of the pixel point in the frequency spectrum characteristic graph is smaller than the gray threshold, setting the gray value as a second preset gray value.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring a sliding window for framing each pixel point in the image; when filtering processing is carried out on the target pixel point, a sliding window is used for framing the pixel point in the field of the target pixel point; determining a first number of the framed pixel points with the gray value equal to a first preset gray value and a second number of the framed pixel points with the gray value equal to a second preset gray value; when the first number is larger than the second number, setting the gray value of the target pixel point as a first preset gray value; and when the first number is smaller than the second number, setting the gray value of the target pixel point as a second preset gray value.
In one embodiment, the method is applied to a registration management system; the computer program when executed by the processor further realizes the steps of: when the image to be recognized is determined to be a copied image, obtaining communication identification of an auditor with management authority in a registration management system; sending an identification request carrying an image to be identified to an auditor communication identifier; receiving feedback information for the identification request; and when the image to be identified is determined to be the copied image according to the feedback information, rejecting the registration request corresponding to the image to be identified.
In one embodiment, the method is applied to social applications; the computer program when executed by the processor further realizes the steps of: receiving an image to be identified sent by an opposite-end contact person through a social application; the method further comprises the following steps: when the image to be identified is determined to be a copied image, detecting whether text information sent by an opposite-end contact person includes preset sensitive keywords; and if so, sending prompt information to a common friend of the opposite-end contact person.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of identifying a copied image, the method comprising:
acquiring an image to be identified;
performing Fourier transform on the image to be identified to obtain a frequency spectrum characteristic diagram;
carrying out binarization processing on the frequency spectrum characteristic diagram;
filtering the frequency spectrum characteristic diagram after the binarization processing to obtain a filtering characteristic diagram;
adjusting the gray value of each pixel point in the central area block of the filtering characteristic graph and the gray value of each pixel point on the median line to be a first preset gray value;
calculating the number of gray values in the adjusted filter characteristic graph equal to a second preset gray value;
judging whether the number reaches a number threshold value, if so, determining that the image to be identified is a reproduction image; if not, determining that the image to be identified is a non-reproduction image.
2. The method of claim 1, wherein prior to the fourier transforming the image to be identified, the method further comprises:
determining the size of the image to be identified;
when the size of the image to be recognized is larger than a preset first critical size or smaller than a preset second critical size, zooming the image to be recognized according to a preset standard size;
the Fourier transform of the image to be identified to obtain the frequency spectrum characteristic diagram comprises the following steps:
decomposing the zoomed image to be recognized into three images of RGB three channels;
respectively carrying out Fourier transform on the three images, and carrying out synthesis processing on the images obtained after the Fourier transform;
and converting the synthesized image into a single-channel spectral feature map.
3. The method according to claim 1, wherein the binarizing the spectrum feature map comprises:
determining a gray threshold;
when the gray value of a pixel point in the frequency spectrum characteristic graph is larger than or equal to the gray threshold value, setting the gray value as a first preset gray value;
and when the gray value of the pixel point in the frequency spectrum characteristic graph is smaller than the gray threshold value, setting the gray value as a second preset gray value.
4. The method according to claim 1, wherein the filtering the spectrum feature map after the binarization processing to obtain a filtered feature map comprises:
acquiring a sliding window for framing each pixel point in the image;
when filtering processing is carried out on a target pixel point, framing the pixel point in the target pixel point field by using the sliding window;
determining a first number of gray values of the framed pixel points equal to the first preset gray value and a second number of gray values equal to the second preset gray value;
when the first number is larger than the second number, setting the gray value of the target pixel point as the first preset gray value;
and when the first number is smaller than the second number, setting the gray value of the target pixel point as the second preset gray value.
5. The method according to any one of claims 1 to 4, wherein the method is applied to a registration management system; the method further comprises the following steps:
when the image to be identified is determined to be a copied image, acquiring a communication identifier of an auditor with management authority in the registration management system;
sending an identification request carrying the image to be identified to the communication identifier of the auditor;
receiving feedback information for the identification request;
and when the image to be identified is determined to be a copied image according to the feedback information, rejecting the registration request corresponding to the image to be identified.
6. The method according to any one of claims 1 to 4, wherein the method is applied to social applications; the acquiring the image to be recognized comprises the following steps:
receiving an image to be identified sent by an opposite-end contact person through the social application;
the method further comprises the following steps:
when the image to be identified is determined to be a copied image, detecting whether text information sent by the opposite-end contact person comprises preset sensitive keywords or not;
and if so, sending prompt information to the common friends of the opposite-end contact person.
7. An apparatus for recognizing a reproduced image, the apparatus comprising:
the image acquisition module is used for acquiring an image to be identified;
the transformation module is used for carrying out Fourier transformation on the image to be identified to obtain a frequency spectrum characteristic diagram;
the binarization processing module is used for carrying out binarization processing on the frequency spectrum characteristic diagram;
the filtering processing module is used for carrying out filtering processing on the frequency spectrum characteristic diagram after the binarization processing to obtain a filtering characteristic diagram;
the gray value adjusting module is used for adjusting the gray value of each pixel point in the central area block of the filtering characteristic diagram and the gray value of each pixel point on the median line to be a first preset gray value;
the quantity calculation module is used for calculating the quantity of the adjusted grey values in the filtering characteristic graph equal to a second preset grey value;
the image determining module is used for judging whether the number reaches a number threshold value, and if so, determining the image to be identified as a copied image; and if not, determining that the image to be identified is a non-reproduction image.
8. The apparatus of claim 7, further comprising:
the size determining module is used for determining the size of the image to be recognized;
the image scaling module is used for scaling the image to be identified according to a preset standard size when the size of the image to be identified is larger than a preset first critical size or smaller than a preset second critical size;
the transformation module is also used for decomposing the zoomed image to be identified into three images of RGB three channels; fourier transformation is respectively carried out on the three images, and the images obtained after the transformation are subjected to synthesis processing; and converting the synthesized image into a single-channel spectral feature map.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811572818.5A CN109815970B (en) | 2018-12-21 | 2018-12-21 | Method and device for identifying copied image, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811572818.5A CN109815970B (en) | 2018-12-21 | 2018-12-21 | Method and device for identifying copied image, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109815970A CN109815970A (en) | 2019-05-28 |
| CN109815970B true CN109815970B (en) | 2023-04-07 |
Family
ID=66602252
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811572818.5A Active CN109815970B (en) | 2018-12-21 | 2018-12-21 | Method and device for identifying copied image, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109815970B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111191568B (en) * | 2019-12-26 | 2024-06-14 | 中国平安人寿保险股份有限公司 | Method, device, equipment and medium for identifying flip image |
| CN113822095B (en) * | 2020-06-02 | 2024-01-12 | 苏州科瓴精密机械科技有限公司 | Method, system, robot and storage medium for identifying working position based on image |
| CN114005019B (en) * | 2021-10-29 | 2023-09-22 | 北京有竹居网络技术有限公司 | Method for identifying flip image and related equipment thereof |
| CN114241537B (en) * | 2021-12-31 | 2022-12-23 | 智慧眼科技股份有限公司 | Finger vein image authenticity identification method and device, computer equipment and storage medium |
| CN114913316B (en) * | 2022-04-02 | 2023-04-07 | 淮沪电力有限公司田集第二发电厂 | Image classification method and device for meter recognition of industrial equipment, electronic equipment and storage medium |
Citations (3)
| 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 |
| WO2017024963A1 (en) * | 2015-08-11 | 2017-02-16 | 阿里巴巴集团控股有限公司 | Image recognition method, measure learning method and image source recognition method and device |
| CN107767541A (en) * | 2017-09-12 | 2018-03-06 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note, device, terminal device and storage medium |
-
2018
- 2018-12-21 CN CN201811572818.5A patent/CN109815970B/en active Active
Patent Citations (3)
| 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 |
| WO2017024963A1 (en) * | 2015-08-11 | 2017-02-16 | 阿里巴巴集团控股有限公司 | Image recognition method, measure learning method and image source recognition method and device |
| CN107767541A (en) * | 2017-09-12 | 2018-03-06 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note, device, terminal device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 谢心谦 ; 刘霞 ; 孔月萍 ; .基于深度学习的图像翻拍检测.电脑知识与技术.2017,(第16期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109815970A (en) | 2019-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109815970B (en) | Method and device for identifying copied image, computer equipment and storage medium | |
| US10348726B2 (en) | Online identity verification platform and process | |
| US20200211121A1 (en) | Credit-based claim settlement implementing method and device | |
| WO2020147445A1 (en) | Rephotographed image recognition method and apparatus, computer device, and computer-readable storage medium | |
| US10504202B2 (en) | Method and device for identifying whether standard picture contains watermark | |
| CN107292150B (en) | User identity confirmation method and device in security information processing | |
| US11074333B2 (en) | Anti-replay authentication systems and methods | |
| US9483629B2 (en) | Document authentication based on expected wear | |
| US20200065460A1 (en) | Method and computer readable storage medium for remote interview signature | |
| EP3837825A1 (en) | Methods, apparatuses, storage mediums and terminal devices for authentication | |
| US11521208B2 (en) | System and method for authenticating transactions from a mobile device | |
| CN110969570B (en) | Method and device for processing image | |
| CN110991231B (en) | Living body detection method and device, server and face recognition equipment | |
| CN107240023A (en) | client identity confirmation method, device and system | |
| WO2020082731A1 (en) | Electronic device, credential recognition method and storage medium | |
| US20210279316A1 (en) | Anti-replay authentication systems and methods | |
| CN110807630B (en) | Payment method and device based on face recognition, computer equipment and storage medium | |
| JP2021536601A (en) | Anti-replay authentication system and method | |
| CN111767845B (en) | Certificate identification method and device | |
| US9846982B2 (en) | Document geometric deformation watermarking and tracking | |
| CN109858339B (en) | Information verification method, information verification device, computer equipment and computer readable storage medium | |
| JPWO2006008992A1 (en) | Web site connection method using portable information communication terminal with camera | |
| CN111209546A (en) | Online multi-person identity authentication method, system and device and identity authentication equipment | |
| CN109544325A (en) | Switching method, device and the computer equipment of face label system based on data processing | |
| US11961315B1 (en) | Methods and systems for enhancing detection of a fraudulent identity document in an image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |