CN109815970A - Recognition methods, device, computer equipment and the storage medium of reproduction image - Google Patents
Recognition methods, device, computer equipment and the storage medium of reproduction image Download PDFInfo
- Publication number
- CN109815970A CN109815970A CN201811572818.5A CN201811572818A CN109815970A CN 109815970 A CN109815970 A CN 109815970A CN 201811572818 A CN201811572818 A CN 201811572818A CN 109815970 A CN109815970 A CN 109815970A
- Authority
- CN
- China
- Prior art keywords
- images
- recognized
- gray value
- image
- spectrum signature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Facsimile Image Signal Circuits (AREA)
- Image Analysis (AREA)
Abstract
This application involves image recognition technology, in particular to a kind of recognition methods, device, computer equipment and the storage medium of reproduction image.The described method includes: obtaining images to be recognized；Fourier transformation is carried out to the images to be recognized, obtains spectrum signature figure；The spectrum signature figure is subjected to binary conversion treatment；Spectrum signature figure after binary conversion treatment is filtered, filtering characteristics figure is obtained；The gray value of each pixel on the gray value and neutrality line of each pixel in the central area block of the filtering characteristics figure is adjusted to the first default gray value；Calculate the quantity that gray value in filtering characteristics figure adjusted is equal to the second default gray value；Judge whether the quantity reaches amount threshold, if so, determining that the images to be recognized is reproduction image；If not, it is determined that the images to be recognized is non-reproduction image.Can be avoided third party using this method causes user information security risk occur using reproduction image.
Description
Technical field
This application involves image identification technical fields, more particularly to recognition methods, device, the calculating of a kind of reproduction image
Machine equipment and storage medium.
Background technique
With the continuous development of computer technology and Internet technology, opens an account or handle by online mode and is important
Business is increasingly liked by user.When carrying out above-mentioned business operation, it may be necessary to which user passes through mobile terminal or network
The equipment such as camera shoot and upload corresponding image, such as the certificate image of user or the true picture of user.
However, the image uploaded may not be that user is true by shooting my resulting true picture, or by shooting
The obtained certificate image of certificate, but the picture institute by being shown on the display screen of equipment such as reproduction computer or mobile phone
, so that the image uploaded be made to there are problems that forging, leading to user information, there are safety issues.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide recognition methods, the device, computer of a kind of reproduction image
Equipment and storage medium, can be avoided third party causes user information security risk occur using reproduction image.
A kind of recognition methods of reproduction image, which comprises
Obtain images to be recognized；
Fourier transformation is carried out to the images to be recognized, obtains spectrum signature figure；
The spectrum signature figure is subjected to binary conversion treatment；
Spectrum signature figure after binary conversion treatment is filtered, filtering characteristics figure is obtained；
By each pixel on the gray value and neutrality line of each pixel in the central area block of the filtering characteristics figure
Gray value is adjusted to the first default gray value；
Calculate the quantity that gray value in filtering characteristics figure adjusted is equal to the second default gray value；
Judge whether the quantity reaches amount threshold, if so, determining that the images to be recognized is reproduction image；If
It is no, it is determined that the images to be recognized is non-reproduction image.
In one of the embodiments, the method also includes:
Before carrying out Fourier transformation to the images to be recognized, the size of the images to be recognized is determined；
When the images to be recognized size be greater than preset first critical dimension, or be less than preset second critical dimension
When, the images to be recognized is zoomed in and out according to preset standard size；
Described to carry out Fourier transformation to the images to be recognized, obtaining spectrum signature figure includes:
Images to be recognized after scaling is decomposed into three width images of RGB triple channel；
Fourier transformation is carried out to the three width image respectively, image resulting after transformation is subjected to synthesis processing；
Resulting image will be synthesized and be converted to single pass spectrum signature figure.
It is described in one of the embodiments, to include: by spectrum signature figure progress binary conversion treatment
Determine gray threshold；
When the gray value of pixel in the spectrum signature figure is greater than or equal to the gray threshold, by the gray value
It is set to the first default gray value；
When the gray value of pixel in the spectrum signature figure is less than the gray threshold, the gray value is set to the
Two default gray values.
The spectrum signature figure to after binary conversion treatment is filtered in one of the embodiments, is filtered
Wave characteristic figure includes:
Obtain the sliding window for confining each pixel in image；
When being filtered to target pixel points, confined in the target pixel points field using the sliding window
Pixel；
It determines that the gray value for being confined pixel is equal to the first number of the described first default gray value, and is equal to described
Second number of the second default gray value；
When first number is greater than second number, the gray value of the target pixel points is set to described first
Default gray value；
When first number is less than second number, the gray value of the target pixel points is set to described second
Default gray value.
The method is applied to registration management system in one of the embodiments,；The method also includes:
When determining the images to be recognized is reproduction image, obtaining has administration authority in the registration management system
Auditor's communication identifier；
The identification request for carrying the images to be recognized is sent to auditor's communication identifier；
Receive the feedback information for the identification request；
When determining that the images to be recognized is reproduction image according to the feedback information, then refuse and the images to be recognized
Corresponding registration request.
The method is applied to social application in one of the embodiments,；The acquisition images to be recognized includes:
Images to be recognized transmitted by the contact person of opposite end is received by the social application；
The method also includes:
When determining the images to be recognized is reproduction image, detecting in the text information that the opposite end contact person sends is
No includes default sensitive keys word；
If so, sending prompt information to the common friend of the opposite end contact person.
A kind of identification device of reproduction image, described device include:
Image collection module, for obtaining images to be recognized；
Conversion module obtains spectrum signature figure for carrying out Fourier transformation to the images to be recognized；
Binary processing module, for the spectrum signature figure to be carried out binary conversion treatment；
Module is filtered and obtains filtering characteristics for being filtered to the spectrum signature figure after binary conversion treatment
Figure；
Gray value adjusts module, for by the gray value of each pixel in the central area block of the filtering characteristics figure, with
And the gray value of each pixel is adjusted to the first default gray value on neutrality line；
Number calculating section, the number for being equal to the second default gray value for calculating gray value in filtering characteristics figure adjusted
Amount；
Image determining module, for judging whether the quantity reaches amount threshold, if so, determining the figure to be identified
As being reproduction image；If not, it is determined that the images to be recognized is non-reproduction image.
Described device in one of the embodiments, further include:
Size determining module, for determining the size of the images to be recognized；
Image scaling module is greater than preset first critical dimension for the size when the images to be recognized, or is less than
When preset second critical dimension, the images to be recognized is zoomed in and out according to preset standard size；
The conversion module is also used to for the images to be recognized after scaling being decomposed into three width images of RGB triple channel；Respectively
Fourier transformation is carried out to the three width image, image resulting after transformation is subjected to synthesis processing；Resulting image will be synthesized
Be converted to single pass spectrum signature figure.
The binary processing module is also used to determine gray threshold in one of the embodiments,；When the frequency spectrum is special
When levying the gray value of pixel in figure more than or equal to the gray threshold, the gray value is set to the first default gray value；
When the gray value of pixel in the spectrum signature figure is less than the gray threshold, the gray value is set to the second default ash
Angle value.
The filtering processing module is also used to obtain for confining each pixel in image in one of the embodiments,
Sliding window；When being filtered to target pixel points, the target pixel points field is confined using the sliding window
Interior pixel；It determines that the gray value for being confined pixel is equal to the first number of the described first default gray value, and is equal to
Second number of the second default gray value；When first number is greater than second number, by the object pixel
The gray value of point is set to the described first default gray value；When first number is less than second number, by the target
The gray value of pixel is set to the described second default gray value.
The recognition methods of the reproduction image is applied to registration management system in one of the embodiments,；Described device
Further include:
Communication identifier obtains module, for when determining the images to be recognized is reproduction image, obtaining the registration pipe
With auditor's communication identifier of administration authority in reason system；
Request sending module is identified, for sending the knowledge for carrying the images to be recognized to auditor's communication identifier
It does not invite and asks；
Feedback information receiving module, for receiving the feedback information for being directed to the identification request；
Registration request refuses module, determines that the images to be recognized is reproduction image according to the feedback information for working as,
Then refuse registration request corresponding with the images to be recognized.
The method is applied to social application in one of the embodiments,；Image collection module is also used to by described
Social application receives images to be recognized transmitted by the contact person of opposite end；
Described device further include:
Keyword detection module, for when determining the images to be recognized is reproduction image, detecting the opposite end connection
It whether include default sensitive keys word in the text information that human hair is sent；
Prompt information sending module, when for including default sensitive keys word in detecting text information, to it is described
The common friend of opposite end contact person sends prompt information.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
Obtain images to be recognized；
Fourier transformation is carried out to the images to be recognized, obtains spectrum signature figure；
The spectrum signature figure is subjected to binary conversion treatment；
Spectrum signature figure after binary conversion treatment is filtered, filtering characteristics figure is obtained；
By each pixel on the gray value and neutrality line of each pixel in the central area block of the filtering characteristics figure
Gray value is adjusted to the first default gray value；
Calculate the quantity that gray value in filtering characteristics figure adjusted is equal to the second default gray value；
Judge whether the quantity reaches amount threshold, if so, determining that the images to be recognized is reproduction image；If
It is no, it is determined that the images to be recognized is non-reproduction image.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
Obtain images to be recognized；
Fourier transformation is carried out to the images to be recognized, obtains spectrum signature figure；
The spectrum signature figure is subjected to binary conversion treatment；
Spectrum signature figure after binary conversion treatment is filtered, filtering characteristics figure is obtained；
By each pixel on the gray value and neutrality line of each pixel in the central area block of the filtering characteristics figure
Gray value is adjusted to the first default gray value；
Calculate the quantity that gray value in filtering characteristics figure adjusted is equal to the second default gray value；
Judge whether the quantity reaches amount threshold, if so, determining that the images to be recognized is reproduction image；If
It is no, it is determined that the images to be recognized is non-reproduction image.
Recognition methods, device, computer equipment and the storage medium of above-mentioned reproduction image pass through the figure to be identified to acquisition
As carrying out Fourier transformation, the spectrum signature figure for being able to reflect spectrum energy point aggregation situation is obtained.Spectrum signature figure is carried out
Binary conversion treatment can reduce the size of image data.Spectrum signature figure after binary conversion treatment is filtered, can be disappeared
Except the noise spot isolated in image, be conducive to the accuracy for improving image reproduction identification.By the central area block of filtering characteristics figure
The gray value of each pixel is adjusted to the first default gray value on the gray value and neutrality line of interior each pixel, calculates adjustment
Gray value is equal to the quantity of the second default gray value in filtering characteristics figure afterwards, judges whether the quantity reaches amount threshold, if
It is, it is determined that images to be recognized is reproduction image；If not, it is determined that images to be recognized is non-reproduction image, may be implemented to treat
The reproduction identification for identifying image, to avoid images to be recognized by showing on the display screen of the equipment such as reproduction computer or mobile phone
Obtained by picture, so that it is guaranteed that the authenticity of image, avoid third party causes user information appearance safety hidden using reproduction image
Suffer from.
Detailed description of the invention
Fig. 1 is the application scenario diagram of the recognition methods of reproduction image in one embodiment；
Fig. 2 is the flow diagram of the recognition methods of reproduction image in one embodiment；
Fig. 3 is further to be identified and the images to be recognized for being determined as reproduction to registration request in one embodiment
The flow diagram for the step of being handled；
Fig. 4 is the structural block diagram of the identification device of reproduction image in one embodiment；
Fig. 5 is the structural block diagram of the identification device of reproduction image in another embodiment；
Fig. 6 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
The recognition methods of reproduction image provided by the present application, can be applied in application environment as shown in Figure 1.Wherein,
Terminal 102 is communicated with server 104 by network by network.The recognition methods of reproduction image can be applied to terminal 102,
It can also be applied to server 104.When usage scenario is the scene of user's registration finance account, the recognition methods of reproduction image can
Applied to server 104, server 104 obtains the images to be recognized sent by terminal 102, carries out Fourier to images to be recognized
Transformation obtains spectrum signature figure；Spectrum signature figure is subjected to binary conversion treatment；Spectrum signature figure after binary conversion treatment is carried out
Filtering processing, obtains filtering characteristics figure；By the gray value and neutrality line of each pixel in the central area block of filtering characteristics figure
The gray value of upper each pixel is adjusted to the first default gray value；It calculates gray value in filtering characteristics figure adjusted and is equal to second
The quantity of default gray value；Judge whether the quantity reaches amount threshold, if so, determining that images to be recognized is reproduction image；
If not, it is determined that images to be recognized is non-reproduction image.If it is determined that server 104 can when images to be recognized is not reproduction image
To allow terminal 102 to carry out corresponding business operation.
When the scene or user that usage scenario is user social contact carry out reproduction identification by terminal, the identification of reproduction image
The step of method can be applied to terminal 102, and the recognition methods of above-mentioned reproduction image is carried out by terminal 102.
Wherein, terminal 102 can be, but not limited to be various personal computers, laptop, smart phone, tablet computer
With portable wearable device.Server 104 can use the server set of the either multiple server compositions of independent server
Group realizes.
In one embodiment, as shown in Fig. 2, providing a kind of recognition methods of reproduction image, it is applied in this way
It is illustrated for terminal 102 in Fig. 1, comprising the following steps:
S202 obtains images to be recognized.
Wherein, image to be identified can be RGB triple channel 32 cromograms.
In one embodiment, the images to be recognized that terminal is shot by camera；Alternatively, terminal is obtained from local photograph album
The images to be recognized taken；Alternatively, the server of terminal from network side obtains images to be recognized.
In one embodiment, if the recognition methods of reproduction image is applied to registration management system namely usage scenario is
In the scene of user's registration account (such as registration finance account), terminal display is uploaded in the operation pages of image.The operation pages
Can be there are two function choosing-item, first is that supporting the function choosing-item of user's captured in real-time image, another is to support user's selection from phase
The function choosing-item of image is obtained in volume.If user selects the function choosing-item of captured in real-time image, terminal calls built-in take the photograph
As the image of head shooting user.If user's selection obtains the function choosing-item of image from photograph album, terminal is from local photograph album
Obtain the image of user.
It should be noted that for the true picture for obtaining user, in order to avoid third party is by shooting other people
Image is to be registered, and in the operation pages of upload user true picture, can not provide the function that image is obtained from photograph album
It can option.
For example, account opening system will show upload user when user is when progress credit card on the net is opened an account or security are opened an account
The operation pages of certificate image and the true picture of user.In the true picture of upload user, in operation pages
The function choosing-item that image is chosen from photograph album is not provided, and the automatic camera for calling terminal carries out image taking so as to user.Upper
When passing user certificate image, the function choosing-item that image is chosen from photograph album can be provided in operation pages, real-time bat can also be provided
The function choosing-item of image is taken the photograph, to call the camera of terminal to carry out image taking so as to user.
S204 carries out Fourier transformation to images to be recognized, obtains spectrum signature figure.
Wherein, obtained spectrum signature figure can be single channel 8 grayscale images, the frequency spectrum after Fourier transformation
Characteristic pattern reflects the aggregation situation of spectrum energy point.Fourier transformation can be discrete Fourier transform.
In one embodiment, before carrying out Fourier transformation, terminal can determine the size of images to be recognized, when to
When identifying that the size of image is greater than preset first critical dimension, or being less than preset second critical dimension, according to preset standard
Size zooms in and out images to be recognized.S204 can specifically include: the images to be recognized after scaling is decomposed into RGB triple channel
Three width images；Fourier transformation is carried out to three width images respectively, image resulting after transformation is subjected to synthesis processing；It will synthesis
Resulting image is converted to single pass spectrum signature figure.
For example, terminal first determines the size of images to be recognized, such as image before carrying out Fourier transformation to the image of acquisition
Resolution ratio or size.If the size of images to be recognized is excessive or too small, image is amplified or is compressed to preset normal size.
Image after scaling is decomposed into three width images according to RGB triple channel by terminal, carries out Fourier transformation to each sub-picture, then
Image after variation is synthesized, assemblage characteristic figure is obtained.Terminal carries out gradation conversion to this assemblage characteristic figure, so as to
To obtain single pass spectrum signature figure.In above-described embodiment, excessive image is compressed, can be reduced in identification process
Calculation amount.
Spectrum signature figure is carried out binary conversion treatment by S206.
In one embodiment, S206 can specifically include: terminal determines gray threshold；When pixel in spectrum signature figure
Gray value be greater than or equal to gray threshold when, gray value is set to the first default gray value；When pixel in spectrum signature figure
Gray value be less than gray threshold when, gray value is set to the second default gray value.
For example, gray threshold can be set as 145, the first default gray value can be 255, and the second default gray value can be 0.
Terminal is during carrying out binary conversion treatment to spectrum signature figure, for pixel of the gray value less than 145 in spectrum signature figure,
Its gray value is set to 0.It is greater than or equal to 145 pixel for gray value, gray value is set to 255.
S208 is filtered the spectrum signature figure after binary conversion treatment, obtains filtering characteristics figure.
Wherein, above-mentioned filtering can be median filtering.By being filtered operation to spectrum signature figure, frequency can be eliminated
The noise spot isolated in spectrum signature figure, to inhibit picture noise.
In one embodiment, S208 can specifically include: terminal obtains the sliding for confining each pixel in image
Window；When being filtered to target pixel points, the pixel in target pixel points field is confined using sliding window；Really
The fixed gray value for being confined pixel is equal to the first number of the first default gray value, and equal to the of the second default gray value
Two numbers；When the first number is greater than the second number, the gray value of target pixel points is set to the first default gray value；When first
When number is less than the second number, the gray value of target pixel points is set to the second default gray value.
Wherein, the size of sliding window can be x × y, can use matrix BxyIt indicates.X and y is odd number, and x can be waited
In y.
For example, it is assumed that spectrum signature figure is the matrix A of m row n columnmn, sliding window is the matrix B of 3 rows 3 column3×3.If
To matrix AmnIn the i-th row jth column element aijWhen (gray value) carries out binaryzation, then need in matrix AmnMiddle selection element aij
Field, the field be 3 rows 3 column matrix B3×3If the matrix B3×3In 0 quantity be greater than 255 quantity when, by element aij
It is set to 0；If when quantity of 0 quantity less than 255, by element aijIt is set to 255.It should be noted that above-mentioned field is 3 rows 3 column
Matrix B3×3In may include element aij, can not also include element aij.Moreover, sliding window avoids confining matrix A as far as possiblemn
In the element that has been adjusted.
S210, by each pixel on the gray value and neutrality line of each pixel in the central area block of filtering characteristics figure
Gray value be adjusted to the first default gray value.
In one embodiment, terminal chooses the central area block of setting ratio size from filtering characteristics figure, will be in this
The gray value of each pixel is adjusted to the first default gray value in heart region unit.Such as in the block of central area, if filtering characteristics figure
Size be S, then the central area block of 1/3S size can be chosen from filtering characteristics figure, by each pixel in the central area block
The gray value of point is adjusted to 255.
In one embodiment, terminal is using the center of filtering characteristics figure as origin, respectively with the neutrality line of filtering characteristics figure
Rectangular coordinate system is established for X-axis and Y-axis.The gray value of pixel each in X-axis and Y-axis is adjusted to the first default gray scale by terminal
Value.For example, the gray value of pixel each in X-axis and Y-axis is adjusted to 255.
It should be noted that in the central area block of filtering characteristics figure and on neutrality line, the mainly number of low frequency part
According to, and the frequency of image is mainly high frequency.Therefore, the gray value in the block of central area and on neutrality line first is adjusted to preset
Gray value can avoid interference of the low frequency part signal to recognition result when judging whether images to be recognized is reproduction image.
S212 calculates the quantity that gray value in filtering characteristics figure adjusted is equal to the second default gray value.
For example, gray value includes 0 and 255, meter in the filtering characteristics figure for the filtering characteristics figure after adjustment gray value
Calculate the quantity of quantity of the gray value equal to 0 and gray value equal to 255.
S214, judges whether the quantity reaches amount threshold, if so, determining that images to be recognized is reproduction image；If it is not,
Then determine that images to be recognized is non-reproduction image.
In one embodiment, S214 can specifically include: quantity and amount threshold of the terminal to the second default gray value
Carry out size judgement, when the quantity of the second default gray value be greater than or equal to preset amount threshold when, it is determined that acquisition to
Identify that image is reproduction image.When the quantity of the second default gray value be less than preset amount threshold when, it is determined that acquisition to
Identify that image is not reproduction image.
For example, it is assumed that preset amount threshold is 4000, when in filtering characteristics figure adjusted 0 quantity is greater than or equal to
When 4000, then determine that the image obtained is reproduction image.When in filtering characteristics figure adjusted 0 quantity is less than 4000, then
Determine that the image obtained is not reproduction image.
In above-described embodiment, by carrying out Fourier transformation to the images to be recognized of acquisition, acquisition is able to reflect frequency spectrum energy
The spectrum signature figure of amount point aggregation situation.Spectrum signature figure is subjected to binary conversion treatment, the size of image data can be reduced.To two
Treated that spectrum signature figure is filtered for value, can eliminate the noise spot isolated in image, is conducive to improve image
The accuracy of reproduction identification.By each picture on the gray value and neutrality line of each pixel in the central area block of filtering characteristics figure
The gray value of vegetarian refreshments is adjusted to the first default gray value, calculates gray value in filtering characteristics figure adjusted and is equal to the second default ash
The quantity of angle value, judges whether the quantity reaches amount threshold, if so, determining that images to be recognized is reproduction image；If it is not, then
It determines that images to be recognized is non-reproduction image, the reproduction identification to images to be recognized may be implemented, to avoid images to be recognized
By the picture gained shown on the display screen of the equipment such as reproduction computer or mobile phone, so that it is guaranteed that the authenticity of image, avoids
Third party causes user information security risk occur using reproduction image.
In one embodiment, the recognition methods of reproduction image can be applied to registration management system, as shown in figure 3, the party
Method can also include:
S302 obtains examining with administration authority in registration management system when determining images to be recognized is reproduction image
Core people's communication identifier.
Wherein, auditor's communication identifier can be the communications account of auditor, be also possible to the registration management system of auditor
System account.Administration authority can be audit permission.Communications account can be instant social software account or E-mail address account.
In order to reduce the error rate of reproduction identification, and then the accuracy of reproduction identification is improved, is determining that images to be recognized is
When reproduction image, need to carry out further to identify operation.
S304 sends the identification request for carrying images to be recognized to auditor's communication identifier.
In one embodiment, if auditor's communication identifier is communications account, terminal is carried to communications account transmission
The identification of images to be recognized is requested, and instruction auditor further identifies images to be recognized, and is provided after recognition anti-
Feedforward information.For example, the identification request for carrying images to be recognized is sent to the E-mail address of auditor by terminal, auditor is requested
The images to be recognized is audited, and the feedback information after identification is dealt into registration management system in a manner of Email.
In one embodiment, if auditor's communication identifier is the personal account of registration management system, terminal is to registration
The personal account of management system sends the identification request for carrying images to be recognized, when auditor's Login Register management system,
Images to be recognized can further be identified, and provide feedback information after recognition.
S306 receives the feedback information for identification request.
Wherein, which may include confirming that images to be recognized is the information of reproduction image or non-reproduction image.
S308 then refuses corresponding with images to be recognized when determining that images to be recognized is reproduction image according to feedback information
Registration request.
In one embodiment, identification priority has can be set in registration management system, i.e. the identification of professional is preferential
The identification priority of grade and machine recognition.
As an example, after determining images to be recognized for reproduction image, in order to further ensure that recognition result
Accuracy, can also be sent to professional for the images to be recognized, further be identified by professional to the image, and
Feedback identifying is as a result, if when the recognition result of feedback indicates that the image is reproduction image, it is determined that the image is reproduction image.If
The recognition result of feedback indicates the image not when being reproduction image, it is determined that the priority of two ways, if professional identifies
Priority be higher than machine recognition priority when, it is determined that the image is not reproduction image, otherwise determine the image be reproduction
Image.
In above-described embodiment, when images to be recognized is identified as reproduction image, carried out by professional further
Identification, the feedback information provided in conjunction with professional provide it is final as a result, so as to reduce reproduction identification error rate, into
And the accuracy rate of reproduction identification is improved, to avoid images to be recognized for institute's exhibition on the display screen of the equipment such as reproduction computer or mobile phone
Obtained by the picture shown, so that it is guaranteed that the authenticity of image, avoid third party causes user information to be pacified using reproduction image
Full hidden danger.
In one embodiment, the recognition methods of reproduction image is applied to social application, and S202 can specifically include: pass through
Social application receives images to be recognized transmitted by the contact person of opposite end；This method further include: when determine images to be recognized be reproduction
It whether include default sensitive keys word in the text information that detection opposite end contact person sends when image；If so, being contacted to opposite end
The common friend of people sends prompt information.
Specifically, when user receives the image of opposite end transmission by social software, terminal is known using the reproduction of this case
Other method carries out reproduction identification to received image, and the result of identification is shown with text mode, or with voice
Mode plays out.If also relate to sensitive keys word (such as borrowing money), terminal can also be carried out the account for sending reproduction image
Label, while the account of common friend is also obtained, it include then that transmission carrying is markd to the transmission of the account of common friend
Prompt information.
In one embodiment, it is that " account may that the mode of label, which can be the user's mark for sending reproduction image,
There are safety issues ", corresponding prompt information may is that the account YY of entitled XX, and there may be safety issues, please don't
Transfer operation is carried out to other side.
For example, prompt information are as follows: " there may be safety issues for the account 1234567 of a leaf canoe, please don't be flat to a leaf
Boat carries out transfer operation ".It is thus possible to which third party is avoided to usurp other people social accounts, the social activity is sent to using reproduction image
Contact person in account improves the property safety of user to carry out fraud.
Further, it is also possible to reproduction recognition methods is applied on small routine, if user does not know whether image is reproduction figure
When picture, it can be identified by the small routine.Wherein, which can be the small routine operated in social software.
In above-described embodiment, reproduction identification is carried out to image received in social software, if it is identified as reproduction image, and
The user for sending the reproduction image, which also has sent, the sensitive words such as borrows money, transfers accounts at the moment, then is labeled as having by the account of the user
The account of danger, and prompt information is sent to common friend, avoiding third party using reproduction image leads to user information
There is security risk, improves user's property safety.
It should be understood that although each step in the flow chart of Fig. 2-3 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-3
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 4, providing a kind of identification device of reproduction image, comprising: image obtains mould
Block 402, conversion module 404, binary processing module 406, filtering processing module 408, gray value adjust module 410, quantity meter
Calculate module 412 and image determining module 414, in which:
Image collection module 402, for obtaining images to be recognized；
Conversion module 404 obtains spectrum signature figure for carrying out Fourier transformation to images to be recognized；
Binary processing module 406, for spectrum signature figure to be carried out binary conversion treatment；
Module 408 is filtered, for being filtered to the spectrum signature figure after binary conversion treatment, it is special to obtain filtering
Sign figure；
Gray value adjusts module 410, for the gray value of each pixel in the central area block by filtering characteristics figure, and
The gray value of each pixel is adjusted to the first default gray value on neutrality line；
Number calculating section 412 is equal to the second default gray value for calculating gray value in filtering characteristics figure adjusted
Quantity；
Image determining module 414, for judging whether the quantity reaches amount threshold, if so, determining images to be recognized
For reproduction image；If not, it is determined that images to be recognized is non-reproduction image.
In above-described embodiment, by carrying out Fourier transformation to the images to be recognized of acquisition, acquisition is able to reflect frequency spectrum energy
The spectrum signature figure of amount point aggregation situation.Spectrum signature figure is subjected to binary conversion treatment, the size of image data can be reduced.To two
Treated that spectrum signature figure is filtered for value, can eliminate the noise spot isolated in image, is conducive to improve image
The accuracy of reproduction identification.By each picture on the gray value and neutrality line of each pixel in the central area block of filtering characteristics figure
The gray value of vegetarian refreshments is adjusted to the first default gray value, calculates gray value in filtering characteristics figure adjusted and is equal to the second default ash
The quantity of angle value, judges whether the quantity reaches amount threshold, if so, determining that images to be recognized is reproduction image；If it is not, then
It determines that images to be recognized is non-reproduction image, the reproduction identification to images to be recognized may be implemented, to avoid images to be recognized
By the picture gained shown on the display screen of the equipment such as reproduction computer or mobile phone, so that it is guaranteed that the authenticity of image, avoids
Third party causes user information security risk occur using reproduction image.
In one of the embodiments, as shown in figure 5, the device further include: size determining module 416 and image scaling mould
Block 418；Wherein:
Size determining module 416, for determining the size of images to be recognized；
Image scaling module 418 is greater than preset first critical dimension for the size when images to be recognized, or is less than pre-
If the second critical dimension when, images to be recognized is zoomed in and out according to preset standard size；
Conversion module 404 is also used to for the images to be recognized after scaling being decomposed into three width images of RGB triple channel；It is right respectively
Three width images carry out Fourier transformation, and image resulting after transformation is carried out synthesis processing；Resulting image will be synthesized to be converted to
Single pass spectrum signature figure.
Binary processing module 406 is also used to determine gray threshold in one of the embodiments,；When in spectrum signature figure
When the gray value of pixel is greater than or equal to gray threshold, gray value is set to the first default gray value；When in spectrum signature figure
When the gray value of pixel is less than gray threshold, gray value is set to the second default gray value.
Filtering processing module 408 is also used to obtain for confining each pixel in image in one of the embodiments,
Sliding window；When being filtered to target pixel points, the pixel in target pixel points field is confined using sliding window
Point；It determines that the gray value for being confined pixel is equal to the first number of the first default gray value, and is equal to the second default gray scale
Second number of value；When the first number is greater than the second number, the gray value of target pixel points is set to the first default gray value；
When the first number is less than the second number, the gray value of target pixel points is set to the second default gray value.
The recognition methods of reproduction image is applied to registration management system in one of the embodiments,；Device further include: logical
Believe that identifier acquisition module 420, identification request sending module 422, feedback information receiving module 424 and registration request refuse module
426；Wherein:
Communication identifier obtains module 420, for obtaining registration management system when determining images to be recognized is reproduction image
In with administration authority auditor's communication identifier；
Identify request sending module 422, the identification for carrying images to be recognized to the transmission of auditor's communication identifier is asked
It asks；
Feedback information receiving module 424, for receiving the feedback information for being directed to identification request；
Registration request refuses module 426, for when determining that images to be recognized is reproduction image according to feedback information, then refusing
Registration request corresponding with images to be recognized.
In above-described embodiment, when images to be recognized is identified as reproduction image, carried out by professional further
Identification, the feedback information provided in conjunction with professional provide it is final as a result, so as to reduce reproduction identification error rate, into
And the accuracy rate of reproduction identification is improved, to avoid images to be recognized for institute's exhibition on the display screen of the equipment such as reproduction computer or mobile phone
Obtained by the picture shown, so that it is guaranteed that the authenticity of image, avoid third party causes user information to be pacified using reproduction image
Full hidden danger.
Method is applied to social application in one of the embodiments,；Image collection module is also used to pass through social application
Receive images to be recognized transmitted by the contact person of opposite end；
Device further include: keyword detection module 428 and prompt information sending module 430；Wherein:
Keyword detection module 428, for when determining images to be recognized is reproduction image, detection opposite end contact person to be sent
Text information in whether include default sensitive keys word；
Prompt information sending module 430, when for including default sensitive keys word in detecting text information, to it is right
The common friend of contact person is held to send prompt information.
In above-described embodiment, reproduction identification is carried out to image received in social software, if it is identified as reproduction image, and
The user for sending the reproduction image, which also has sent, the sensitive words such as borrows money, transfers accounts at the moment, then is labeled as having by the account of the user
The account of danger, and prompt information is sent to common friend, avoiding third party using reproduction image leads to user information
There is security risk, improves user's property safety.
The specific restriction of identification device about reproduction image, may refer to the recognition methods above for reproduction image
Restriction, details are not described herein.Modules in the identification device of above-mentioned reproduction image can be fully or partially through software, hard
Part and combinations thereof is realized.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment,
It can also be stored in a software form in the memory in computer equipment, execute the above modules in order to which processor calls
Corresponding operation.
In one embodiment, a kind of computer equipment is provided, which can be terminal or server, with
For computer equipment to be illustrated for terminal, internal structure chart can be as shown in Figure 6.The computer equipment includes passing through to be
Processor, memory, network interface, display screen and the input unit of bus of uniting connection.Wherein, the processor of the computer equipment
For providing calculating and control ability.The memory of the computer equipment includes non-volatile memory medium, built-in storage.This is non-
Volatile storage medium is stored with operating system and computer program.The built-in storage is the operation in non-volatile memory medium
The operation of system and computer program provides environment.The network interface of the computer equipment is used to pass through network with external terminal
Connection communication.A kind of recognition methods of reproduction image is realized when the computer program is executed by processor.The computer equipment
Display screen can be liquid crystal display or electric ink display screen, the input unit of the computer equipment can be display screen
The touch layer of upper covering is also possible to the key being arranged on computer equipment shell, trace ball or Trackpad, can also be external
Keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, the processor perform the steps of acquisition images to be recognized when executing computer program；To images to be recognized into
Row Fourier transformation obtains spectrum signature figure；Spectrum signature figure is subjected to binary conversion treatment；It is special to the frequency spectrum after binary conversion treatment
Sign figure is filtered, and obtains filtering characteristics figure；By the gray value of each pixel in the central area block of filtering characteristics figure, with
And the gray value of each pixel is adjusted to the first default gray value on neutrality line；Calculate gray value in filtering characteristics figure adjusted
Equal to the quantity of the second default gray value；Judge whether the quantity reaches amount threshold, if so, determining that images to be recognized is to turn over
Clap image；If not, it is determined that images to be recognized is non-reproduction image.
In one embodiment, determining images to be recognized is also performed the steps of when processor executes computer program
Size；When the size of images to be recognized is greater than preset first critical dimension, or is less than preset second critical dimension, according to
Preset standard size zooms in and out images to be recognized；Fourier transformation is carried out to images to be recognized, obtains spectrum signature figure packet
It includes: the images to be recognized after scaling is decomposed into three width images of RGB triple channel；Fourier's change is carried out to three width images respectively
It changes, image resulting after transformation is subjected to synthesis processing；Resulting image will be synthesized and be converted to single pass spectrum signature figure.
In one embodiment, determining gray threshold is also performed the steps of when processor executes computer program；When frequency
When the gray value of pixel is greater than or equal to gray threshold in spectrum signature figure, gray value is set to the first default gray value；When frequency
When the gray value of pixel is less than gray threshold in spectrum signature figure, gray value is set to the second default gray value.
In one embodiment, acquisition is also performed the steps of when processor executes computer program for confining image
In each pixel sliding window；When being filtered to target pixel points, target pixel points are confined using sliding window
Pixel in field；It determines that the gray value for being confined pixel is equal to the first number of the first default gray value, and is equal to
Second number of the second default gray value；When the first number is greater than the second number, the gray value of target pixel points is set to the
One default gray value；When the first number is less than the second number, the gray value of target pixel points is set to the second default gray value.
In one embodiment, method is applied to registration management system；Processor execute computer program when also realize with
Lower step: when determining images to be recognized is reproduction image, the auditor obtained in registration management system with administration authority is logical
Beacon is known；The identification request for carrying images to be recognized is sent to auditor's communication identifier；Receive the feedback for identification request
Information；When determining that images to be recognized is reproduction image according to feedback information, then refuse registration request corresponding with images to be recognized.
In one embodiment, method is applied to social application；Following step is also realized when processor executes computer program
It is rapid: images to be recognized transmitted by the contact person of opposite end is received by social application；Method further include: when determining that images to be recognized is
It whether include default sensitive keys word in the text information that detection opposite end contact person sends when reproduction image；If so, to opposite end
The common friend of contact person sends prompt information.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of acquisition images to be recognized when being executed by processor；Fourier transformation is carried out to images to be recognized, is obtained
Obtain spectrum signature figure；Spectrum signature figure is subjected to binary conversion treatment；Place is filtered to the spectrum signature figure after binary conversion treatment
Reason, obtains filtering characteristics figure；By each picture on the gray value and neutrality line of each pixel in the central area block of filtering characteristics figure
The gray value of vegetarian refreshments is adjusted to the first default gray value；It calculates gray value in filtering characteristics figure adjusted and is equal to the second default ash
The quantity of angle value；Judge whether the quantity reaches amount threshold, if so, determining that images to be recognized is reproduction image；If it is not, then
Determine that images to be recognized is non-reproduction image.
In one embodiment, determining images to be recognized is also performed the steps of when computer program is executed by processor
Size；When the size of images to be recognized is greater than preset first critical dimension, or is less than preset second critical dimension, press
Images to be recognized is zoomed in and out according to preset standard size；Fourier transformation is carried out to images to be recognized, obtains spectrum signature figure
It include: the three width images that the images to be recognized after scaling is decomposed into RGB triple channel；Fourier's change is carried out to three width images respectively
It changes, image resulting after transformation is subjected to synthesis processing；Resulting image will be synthesized and be converted to single pass spectrum signature figure.
In one embodiment, determining gray threshold is also performed the steps of when computer program is executed by processor；When
When the gray value of pixel is greater than or equal to gray threshold in spectrum signature figure, gray value is set to the first default gray value；When
When the gray value of pixel is less than gray threshold in spectrum signature figure, gray value is set to the second default gray value.
In one embodiment, acquisition is also performed the steps of when computer program is executed by processor for confining figure
The sliding window of each pixel as in；When being filtered to target pixel points, object pixel is confined using sliding window
Pixel in point field；It determines that the gray value for being confined pixel is equal to the first number of the first default gray value, and waits
In the second number of the second default gray value；When the first number is greater than the second number, the gray value of target pixel points is set to
First default gray value；When the first number is less than the second number, the gray value of target pixel points is set to the second default gray scale
Value.
In one embodiment, method is applied to registration management system；It is also realized when computer program is executed by processor
Following steps: when determining images to be recognized is reproduction image, the auditor in registration management system with administration authority is obtained
Communication identifier；The identification request for carrying images to be recognized is sent to auditor's communication identifier；It receives for the anti-of identification request
Feedforward information；When determining that images to be recognized is reproduction image according to feedback information, then refuses registration corresponding with images to be recognized and ask
It asks.
In one embodiment, method is applied to social application；It is also realized when computer program is executed by processor following
Step: images to be recognized transmitted by the contact person of opposite end is received by social application；Method further include: when determining images to be recognized
It whether include default sensitive keys word in the text information that detection opposite end contact person sends when for reproduction image；If so, to it is right
The common friend of contact person is held to send prompt information.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of recognition methods of reproduction image, which comprises
Obtain images to be recognized；
Fourier transformation is carried out to the images to be recognized, obtains spectrum signature figure；
The spectrum signature figure is subjected to binary conversion treatment；
Spectrum signature figure after binary conversion treatment is filtered, filtering characteristics figure is obtained；
By the gray scale of each pixel on the gray value and neutrality line of each pixel in the central area block of the filtering characteristics figure
Value is adjusted to the first default gray value；
Calculate the quantity that gray value in filtering characteristics figure adjusted is equal to the second default gray value；
Judge whether the quantity reaches amount threshold, if so, determining that the images to be recognized is reproduction image；If it is not, then
Determine that the images to be recognized is non-reproduction image.
2. the method according to claim 1, wherein it is described to the images to be recognized carry out Fourier transformation it
Before, the method also includes:
Determine the size of the images to be recognized；
When the size of the images to be recognized is greater than preset first critical dimension, or is less than preset second critical dimension,
The images to be recognized is zoomed in and out according to preset standard size；
Described to carry out Fourier transformation to the images to be recognized, obtaining spectrum signature figure includes:
Images to be recognized after scaling is decomposed into three width images of RGB triple channel；
Fourier transformation is carried out to the three width image respectively, image resulting after transformation is subjected to synthesis processing；
Resulting image will be synthesized and be converted to single pass spectrum signature figure.
3. the method according to claim 1, wherein described carry out binary conversion treatment packet for the spectrum signature figure
It includes:
Determine gray threshold；
When the gray value of pixel in the spectrum signature figure is greater than or equal to the gray threshold, the gray value is set to
First default gray value；
When the gray value of pixel in the spectrum signature figure is less than the gray threshold, it is pre- that the gray value is set to second
If gray value.
4. the method according to claim 1, wherein the spectrum signature figure to after binary conversion treatment is filtered
Wave processing, obtaining filtering characteristics figure includes:
Obtain the sliding window for confining each pixel in image；
When being filtered to target pixel points, the picture in the target pixel points field is confined using the sliding window
Vegetarian refreshments；
It determines that the gray value for being confined pixel is equal to the first number of the described first default gray value, and is equal to described second
Second number of default gray value；
When first number is greater than second number, the gray value of the target pixel points is set to described first and is preset
Gray value；
When first number is less than second number, the gray value of the target pixel points is set to described second and is preset
Gray value.
5. method according to any one of claims 1 to 4, which is characterized in that the method is applied to registration management system；
The method also includes:
When determining the images to be recognized is reproduction image, the audit in the registration management system with administration authority is obtained
People's communication identifier；
The identification request for carrying the images to be recognized is sent to auditor's communication identifier；
Receive the feedback information for the identification request；
When determining that the images to be recognized is reproduction image according to the feedback information, then refuse corresponding with the images to be recognized
Registration request.
6. method according to any one of claims 1 to 4, which is characterized in that the method is applied to social application；It is described
Obtaining images to be recognized includes:
Images to be recognized transmitted by the contact person of opposite end is received by the social application；
The method also includes:
When determining the images to be recognized is reproduction image, detects and whether wrapped in the text information that the opposite end contact person sends
Include default sensitive keys word；
If so, sending prompt information to the common friend of the opposite end contact person.
7. a kind of identification device of reproduction image, described device include:
Image collection module, for obtaining images to be recognized；
Conversion module obtains spectrum signature figure for carrying out Fourier transformation to the images to be recognized；
Binary processing module, for the spectrum signature figure to be carried out binary conversion treatment；
Module is filtered and obtains filtering characteristics figure for being filtered to the spectrum signature figure after binary conversion treatment；
Gray value adjusts module, for by the gray value of each pixel in the central area block of the filtering characteristics figure, Yi Jizhong
The gray value of each pixel is adjusted to the first default gray value on bit line；
Number calculating section, the quantity for being equal to the second default gray value for calculating gray value in filtering characteristics figure adjusted；
Image determining module, for judging whether the quantity reaches amount threshold, if so, determining that the images to be recognized is
Reproduction image；If not, it is determined that the images to be recognized is non-reproduction image.
8. device according to claim 7, which is characterized in that described device further include:
Size determining module, for determining the size of the images to be recognized；
Image scaling module is greater than preset first critical dimension for the size when the images to be recognized, or is less than default
The second critical dimension when, the images to be recognized is zoomed in and out according to preset standard size；
The conversion module is also used to for the images to be recognized after scaling being decomposed into three width images of RGB triple channel；Respectively to institute
It states three width images and carries out Fourier transformation, image resulting after transformation is subjected to synthesis processing；Resulting image conversion will be synthesized
For single pass spectrum signature figure.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 6 is realized when being executed by processor.
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 true CN109815970A (en) | 2019-05-28 |
| CN109815970B 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) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111191568A (en) * | 2019-12-26 | 2020-05-22 | 中国平安人寿保险股份有限公司 | Method, device, equipment and medium for identifying copied image |
| CN113822095A (en) * | 2020-06-02 | 2021-12-21 | 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 |
| CN114005019A (en) * | 2021-10-29 | 2022-02-01 | 北京有竹居网络技术有限公司 | Method for identifying copied image and related equipment thereof |
| CN114241537A (en) * | 2021-12-31 | 2022-03-25 | 智慧眼科技股份有限公司 | Finger vein image authenticity identification method and device, computer equipment and storage medium |
| CN114913316A (en) * | 2022-04-02 | 2022-08-16 | 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" * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111191568A (en) * | 2019-12-26 | 2020-05-22 | 中国平安人寿保险股份有限公司 | Method, device, equipment and medium for identifying copied image |
| CN113822095A (en) * | 2020-06-02 | 2021-12-21 | 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 |
| 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 |
| CN114005019A (en) * | 2021-10-29 | 2022-02-01 | 北京有竹居网络技术有限公司 | Method for identifying copied image and related equipment thereof |
| 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 |
| CN114241537A (en) * | 2021-12-31 | 2022-03-25 | 智慧眼科技股份有限公司 | Finger vein image authenticity identification method and device, computer equipment and storage medium |
| 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 |
| CN114913316A (en) * | 2022-04-02 | 2022-08-16 | 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109815970B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109815970A (en) | Recognition methods, device, computer equipment and the storage medium of reproduction image | |
| WO2020147445A1 (en) | Rephotographed image recognition method and apparatus, computer device, and computer-readable storage medium | |
| US11354797B2 (en) | Method, device, and system for testing an image | |
| US10728499B2 (en) | Electronic apparatus and communication method thereof | |
| CN109284684A (en) | A kind of information processing method, device and computer storage medium | |
| US20200019970A1 (en) | System and method for authenticating transactions from a mobile device | |
| CN109409349A (en) | Credit certificate discrimination method, device, terminal and computer readable storage medium | |
| CN108388813A (en) | Electronic endorsement method, user equipment, storage medium and device | |
| CN109754059A (en) | Reproduction image-recognizing method, device, computer equipment and storage medium | |
| CN108288168A (en) | Borrow or lend money register method, terminal and the computer readable storage medium of service account | |
| CN107798610A (en) | Insurance payment golden collar takes method and apparatus | |
| JP2023539712A (en) | Generation of obfuscated identification templates for transaction validation | |
| CN107240023A (en) | client identity confirmation method, device and system | |
| US11711361B2 (en) | Biometric authentication during voice data transfers | |
| Tang et al. | Detection of GAN‐Synthesized Image Based on Discrete Wavelet Transform | |
| CN109711342B (en) | Face recognition method and device | |
| CN101488859A (en) | Network security authentication system based on handwriting recognition and implementing method thereof | |
| CN117114676A (en) | Card binding method and device | |
| CN110807630B (en) | Payment method and device based on face recognition, computer equipment and storage medium | |
| US20160344558A1 (en) | System and Method for Obtaining Authorization | |
| CN110738499A (en) | User identity authentication method and device, computer equipment and storage medium | |
| CN109145827A (en) | Video communication method and device | |
| CN107633194A (en) | A kind of recognition methods of Quick Response Code and terminal | |
| CN113449275B (en) | User identity authentication method and device and terminal equipment | |
| CN111539742A (en) | Information processing method, information processing device, electronic 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |