CN109754059A - Reproduction image-recognizing method, device, computer equipment and storage medium - Google Patents
Reproduction image-recognizing method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109754059A CN109754059A CN201811574530.1A CN201811574530A CN109754059A CN 109754059 A CN109754059 A CN 109754059A CN 201811574530 A CN201811574530 A CN 201811574530A CN 109754059 A CN109754059 A CN 109754059A
- Authority
- CN
- China
- Prior art keywords
- reproduction
- probability
- value
- recognized
- images
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Image Analysis (AREA)
Abstract
This application involves technical field of image detection, in particular to a kind of reproduction image-recognizing method, device, computer equipment and storage medium.The described method includes: obtaining images to be recognized；Corresponding Lis Hartel sign figure is generated according to images to be recognized；LBP characteristic value is extracted from Lis Hartel sign figure；Calculate statistical probability of the LBP characteristic value in each default range of characteristic values；The statistical probability of the LBP characteristic value is inputted into neural network model, identifying processing is carried out by statistical probability of the neural network model to the LBP characteristic value, obtains the first reproduction probability；When the first reproduction probability reaches probability threshold value, then the images to be recognized is reproduction image.Reproduction image can be avoided using this method and user information is caused safety issue occur.
Description
Technical field
This application involves technical field of image detection, more particularly to a kind of reproduction image-recognizing method, device, computer
Equipment and storage medium.
Background technique
With the continuous development of computer technology and Internet technology, important industry is opened an account or handled online on the net
Business, it may be necessary to which user shoots and upload corresponding image by mobile terminal or the first-class equipment of network shooting, such as the card of user
Part image 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 will lead to user information there is safety issue.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of reproduction image-recognizing method, device, computer and set
Standby and storage medium can be avoided reproduction image and user information caused safety issue occur.
A kind of reproduction image-recognizing method, which comprises
Obtain images to be recognized；
Corresponding Lis Hartel sign figure is generated according to images to be recognized；
Local binary patterns LBP characteristic value is extracted from Lis Hartel sign figure；
Calculate statistical probability of the LBP characteristic value in each default range of characteristic values；
The statistical probability of the LBP characteristic value is inputted into neural network model, by the neural network model to described
The statistical probability of LBP characteristic value carries out identifying processing, obtains the first reproduction probability；
When the first reproduction probability reaches probability threshold value, then the images to be recognized is reproduction image.
The local binary patterns LBP characteristic value of extracting from Lis Hartel sign figure includes: in one of the embodiments,
Lis Hartel sign figure is divided into multiple sub- Lis Hartel sign segments；
Multiple block of pixels are divided into each sub- Lis Hartel sign segment respectively；
In each block of pixels, judge whether the gray value of non-central pixel is greater than the gray value of central pixel point；
If so, setting the first numerical value for the gray value of the non-central pixel；If it is not, then by the non-central picture
The gray value of vegetarian refreshments is set as second value；
Summation is weighted to the gray value of the non-central pixel in each block of pixels after setting gray value；
Using the result of weighted sum as the LBP characteristic value of each block of pixels.
The statistics for calculating the LBP characteristic value in each default range of characteristic values is general in one of the embodiments,
Rate includes:
To the LBP characteristic value in each sub- Lis Hartel sign segment, it is ranked up according to size order；
By the LBP characteristic value in the sub- Lis Hartel sign segment each after sequence, multiple spies are uniformly divided into according to preset step-length
Value indicative range；
Calculate the statistical probability for belonging to LBP characteristic value in each range of characteristic values.
After the then described images to be recognized is reproduction image in one of the embodiments, the method also includes:
Generate the image review request for carrying the images to be recognized；
Described image review request is sent to the review number of acknowledging a debt；
Receive feedback information that the review number of acknowledging a debt is sent, for described image review request；The feedback letter
Breath carries the second reproduction probability that the images to be recognized is reproduction image；
Obtain the second weight corresponding to the first weight corresponding to machine recognition and review people's identification；
Respectively according to first weight and second weight, to the first reproduction probability and the second reproduction probability into
Row weighted sum obtains the weighted sum of reproduction probability；
It is final to determine that images to be recognized is reproduction image when the weighted sum is greater than or equal to default weighted sum.
In one of the embodiments, the method also includes:
Sample graph to be identified is obtained, the sample graph to be identified is labeled, obtains the sample to be identified comprising label
Figure；The label is for indicating whether the sample graph to be identified is reproduction image；
Corresponding Lis Hartel, which is generated, according to the sample graph to be identified comprising the label levies sample graph；
LBP feature samples value is extracted from Lis Hartel sign sample graph；
Calculate statistical probability sample of the LBP feature samples value in each default range of characteristic values；
The statistical probability sample is inputted into neural network model, by the neural network model to the statistical probability
Sample carries out identifying processing, obtains third reproduction probability；
The difference between the third reproduction probability and the label is compared, the parameter of neural network model is adjusted.
The difference compared between the third reproduction probability and the label in one of the embodiments, adjustment
The parameter of neural network model includes:
Determine the error between the third reproduction probability and the label；
By the network layer of the error back propagation to neural network model, the gradient of each network layer parameter is obtained；
The parameter of each network layer in the neural network model is adjusted according to gradient obtained.
A kind of reproduction pattern recognition device, described device include:
Image collection module, for obtaining images to be recognized；
Characteristic pattern generation module, for generating corresponding Lis Hartel sign figure according to images to be recognized；
Characteristics extraction module, for extracting local binary patterns LBP characteristic value from Lis Hartel sign figure；
Computing module, for calculating statistical probability of the LBP characteristic value in each default range of characteristic values；
Processing module passes through the nerve net for the statistical probability of the LBP characteristic value to be inputted neural network model
Network model carries out identifying processing to the statistical probability of the LBP characteristic value, obtains the first reproduction probability；
Reproduction image determining module, for when the first reproduction probability reaches probability threshold value, then the figure to be identified
As being reproduction image.
The characteristics extraction module is also used in one of the embodiments:
Lis Hartel sign figure is divided into multiple sub- Lis Hartel sign segments；
Multiple block of pixels are divided into each sub- Lis Hartel sign segment respectively；
In each block of pixels, judge whether the gray value of non-central pixel is greater than the gray value of central pixel point；
If so, setting the first numerical value for the gray value of the non-central pixel；If it is not, then by the non-central picture
The gray value of vegetarian refreshments is set as second value；
Summation is weighted to the gray value of the non-central pixel in each block of pixels after setting gray value；
Using the result of weighted sum as the LBP characteristic value of each block of pixels.
The computing module is also used in one of the embodiments:
To the LBP characteristic value in each sub- Lis Hartel sign segment, it is ranked up according to size order；
By the LBP characteristic value in the sub- Lis Hartel sign segment each after sequence, multiple spies are uniformly divided into according to preset step-length
Value indicative range；
Calculate the statistical probability for belonging to LBP characteristic value in each range of characteristic values.
Described device in one of the embodiments, further include:
Generation module is requested, for generating the image review request for carrying the images to be recognized；
Sending module, for described image review request to be sent to the review number of acknowledging a debt；
Receiving module, for receiving feedback letter that the review number of acknowledging a debt is sent, for described image review request
Breath；The feedback information carries the second reproduction probability that the images to be recognized is reproduction image；
Weight Acquisition module, for obtaining the first weight corresponding to machine recognition and checking second corresponding to people's identification
Weight；
Weighting block, for respectively according to first weight and second weight, to the first reproduction probability and described
Second reproduction probability is weighted summation, obtains the weighted sum of reproduction probability；
The reproduction image determining module is also used to when the weighted sum is greater than or equal to default weighted sum, final to determine
Images to be recognized is reproduction image.
Described device in one of the embodiments, further include:
Described image obtains module and is also used to obtain sample graph to be identified, is labeled, obtains to the sample graph to be identified
Obtain the sample graph to be identified comprising label；The label is for indicating whether the sample graph to be identified is reproduction image；
Characteristic pattern generation module is also used to generate corresponding Lis Hartel sign according to the sample graph to be identified comprising the label
Sample graph；
Characteristics extraction module, which is also used to levy from the Lis Hartel, extracts LBP feature samples value in sample graph；
Computing module is also used to calculate statistical probability sample of the LBP feature samples value in each default range of characteristic values
This；
Processing module is also used to the statistical probability sample inputting neural network model, passes through the neural network model
Identifying processing is carried out to the statistical probability sample, obtains third reproduction probability；
Module is adjusted, for comparing the difference between the third reproduction probability and the label, adjusts neural network mould
The parameter of type.
The adjustment module is also used in one of the embodiments:
Determine the error between the third reproduction probability and the label；
By the network layer of the error back propagation to neural network model, the gradient of each network layer parameter is obtained；
The parameter of each network layer in the neural network model is adjusted according to gradient obtained.
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；
Corresponding Lis Hartel sign figure is generated according to images to be recognized；
Local binary patterns LBP characteristic value is extracted from Lis Hartel sign figure；
Calculate statistical probability of the LBP characteristic value in each default range of characteristic values；
The statistical probability of the LBP characteristic value is inputted into neural network model, by the neural network model to described
The statistical probability of LBP characteristic value carries out identifying processing, obtains the first reproduction probability；
When the first reproduction probability reaches probability threshold value, then the images to be recognized is 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；
Corresponding Lis Hartel sign figure is generated according to images to be recognized；
Local binary patterns LBP characteristic value is extracted from Lis Hartel sign figure；
Calculate statistical probability of the LBP characteristic value in each default range of characteristic values；
The statistical probability of the LBP characteristic value is inputted into neural network model, by the neural network model to described
The statistical probability of LBP characteristic value carries out identifying processing, obtains the first reproduction probability；
When the first reproduction probability reaches probability threshold value, then the images to be recognized is reproduction image.
Above-mentioned reproduction image-recognizing method, device, computer equipment and storage medium, it is raw according to the images to be recognized of acquisition
It levies and schemes at Lis Hartel, LBP characteristic value is extracted from Lis Hartel sign figure, to obtain the Local textural feature of images to be recognized.Meter
Statistical probability of the LBP characteristic value in each default range of characteristic values is calculated, the statistical probability of the LBP characteristic value is inputted into neural network
Model can determine whether images to be recognized is reproduction image by neural network model, so that avoiding images to be recognized is to turn over
It claps obtained by the picture shown on the display screen of the equipment such as computer or mobile phone, so that it is guaranteed that the authenticity of image, avoids third
Side causes user information security risk occur using reproduction image.
Detailed description of the invention
Fig. 1 is the application scenario diagram of reproduction image-recognizing method in one embodiment；
Fig. 2 is the flow diagram of reproduction image-recognizing method in one embodiment；
Fig. 3 is the schematic diagram that LBP feature is extracted in one embodiment；
The flow diagram for the step of Fig. 4 is training neural network model in another embodiment；
Fig. 5 is the structural block diagram of reproduction pattern recognition device in one embodiment；
Fig. 6 is the structural block diagram of reproduction pattern recognition device in another embodiment；
Fig. 7 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.
Reproduction image-recognizing method provided by the present application, can be applied in application environment as shown in Figure 1.Wherein, eventually
End 102 is communicated with server 104 by network by network.Server 104 obtains images to be recognized by terminal 102,
Lis Hartel sign figure is generated according to images to be recognized；Server 104 extracts LBP (Local Binary from Lis Hartel sign figure
Pattern, local binary patterns) characteristic value, statistical probability of the LBP characteristic value in each range of characteristic values is calculated, statistics is general
Rate inputs neural network model, can determine whether images to be recognized is reproduction image by the neural network model.Wherein, eventually
End 102 can be, but not limited to be various personal computers, laptop, smart phone, tablet computer and portable wearable
Equipment, server 104 can be realized with the server cluster of the either multiple server compositions of independent server.
In one embodiment, as shown in Fig. 2, providing a kind of reproduction image-recognizing method, it is applied to Fig. 1 in this way
In server for be illustrated, comprising the following steps:
S202 obtains images to be recognized.
Wherein, images to be recognized can be 32 cromograms including RGB channel, further, it is also possible to which being includes RGB channel
64 or 128 cromograms.
In one embodiment, server shoots images to be recognized by being mounted on the camera of terminal；Alternatively, server
Images to be recognized is obtained from being stored in terminal local photograph album by terminal.
In one embodiment, if the recognition methods of reproduction image is applied to user's registration account (such as registration finance account)
Scene in, can be there are two function choosing-item, first is that user is supported to clap in real time in the operation pages that terminal display uploads image
The function choosing-item of image is taken the photograph, another is that user's selection is supported to obtain the function choosing-item of image from photograph album.If user's selection is real-time
When shooting the function choosing-item of image, terminal then calls the image of camera shooting user or user certificate, and the image of shooting is made
For images to be recognized.If user's selection obtains the function choosing-item of image from photograph album, terminal obtains use from local photograph album
The image of family or user certificate, the image that will acquire is as images to be recognized.
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.It is shone in the true picture or user certificate of upload user
When, the camera of terminal can be called to carry out image taking so as to user, function provided in operation pages can also be provided
Option chooses corresponding images to be recognized from photograph album, and the camera of terminal can also be called to carry out image taking so as to user.
In one embodiment, after S202, server determines the size (resolution ratio of such as image) of images to be recognized, if
When the size of images to be recognized is greater than first size threshold value, then by compression of images to preset standard size.If images to be recognized
Size less than the second size threshold when, then image is amplified to preset standard size.Wherein, first size threshold value is greater than the
Two size thresholds.
S204 generates corresponding Lis Hartel sign figure according to images to be recognized.
Wherein, Ha Er (Haar) feature can reflect the grey scale change situation of images to be recognized, as used in images to be recognized
Some features of family face can simply be described by rectangular characteristic.Lis Hartel sign figure can be single pass grayscale image.
In one embodiment, server generates Lis Hartel sign corresponding with images to be recognized by way of integrogram
Figure.Wherein, the building mode of integrogram includes: that images to be recognized is arrived each point from the off and is formed by rectangle by server
The pixel accumulated value in region, the element as an array save in memory；When the pixel accumulated value for calculating the rectangular area
When, it can be with the element of direct index array, without the pixel accumulated value for recalculating this region.
For example, the building mode of integrogram includes: the accumulated value for 1) indicating line direction with s (i, j), initialize s (i, -1)
=0.2) integral image is indicated with p (i, j), initialize integral image p (- 1, i)=0.3) images to be recognized, recurrence are progressively scanned
Calculate the value of the accumulated value s (i, j) and integral image p (i, j) of each pixel (i, j) line direction.Wherein, s (i, j)=s (i, j-
1)+f (i, j), p (i, j)=p (i-1, j)+s (i, j), f (i, j) indicate original images to be recognized.4) when scanning is to be identified
When the lower right corner pixel of image, integral image p (i, j) is constructed.
S206 extracts local binary patterns LBP characteristic value from Lis Hartel sign figure.
In one embodiment, Lis Hartel sign figure is evenly dividing and levies segment for multiple sub- Lis Hartels by server, each
The pixel of sub- Lis Hartel sign segment extracts LBP characteristic value.
Specifically, Lis Hartel sign figure is divided into multiple sub- Lis Hartels and levies segment by server, is levied respectively to each sub- Lis Hartel
Segment is divided into multiple block of pixels.Server judges whether the gray value of non-central pixel is greater than center in each block of pixels
The gray value of pixel；If so, setting the first numerical value for the gray value of non-central pixel；If it is not, then by non-central picture
The gray value of vegetarian refreshments is set as second value.Gray scale of the server to the non-central pixel in each block of pixels after setting gray value
Value is weighted summation, using the result of weighted sum as the LBP characteristic value of each block of pixels.
For example, as shown in figure 3, for some pixel in sub- Lis Hartel sign segment, during server with the pixel is
The gray value of the central pixel point is compared with the gray value of field pixel each in 3 × 3 windows by imago vegetarian refreshments respectively,
If the gray value of field pixel is greater than or equal to the gray value of central pixel point, set the gray value of field pixel to
1；If the gray value of field pixel is less than the gray value of central pixel point, 0 is set by the gray value of field pixel, because
This binary system for calculating the gray value of the central pixel point is 01111100, and being converted to the decimal system is 124.Pass through above-mentioned side
Method, the LBP characteristic value of available each sub- Lis Hartel sign segment.
S208 calculates statistical probability of the LBP characteristic value in each default range of characteristic values.
In one embodiment, S208 can specifically include: server is to the LBP feature in each sub- Lis Hartel sign segment
Value, is ranked up according to size order；It is equal according to preset step-length by the LBP characteristic value in sub- Lis Hartel sign segment each after sequence
It is even to be divided into multiple range of characteristic values；Calculate the statistical probability for belonging to LBP characteristic value in each range of characteristic values.
In one embodiment, in every sub- Lis Hartel sign segment, LBP histogram is established according to LBP characteristic value, it will be every
The corresponding probability of a LBP histogram is stored in respectively in different subnumber group A1, A2 ... An, obtains each sub- Lis Hartel sign segment
Statistical probability of the LBP characteristic value in each default range of characteristic values.Before inputting neural network model, server is by subnumber group
A1, A2 ... An are stored in another array S.
The statistical probability of LBP characteristic value is inputted neural network model, by neural network model to LBP feature by S210
The statistical probability of value carries out identifying processing, obtains the first reproduction probability.
In one embodiment, the statistical probability of LBP characteristic value is inputted trained mind in the form of array by server
Through network model.
S212, when the first reproduction probability reaches probability threshold value, then images to be recognized is reproduction image.
For example, it is assumed that probability threshold value is 90%, when the first reproduction probability is greater than or equal to 90%, then images to be recognized is
Reproduction image.When the first reproduction probability is less than 90%, then images to be recognized is not reproduction image.
In one embodiment, in order to further ensure the accuracy of recognition result, after S212, this method further include:
Server generates the image review request for carrying images to be recognized；Image review request is sent to the review number of acknowledging a debt；It receives
Feedback information being sent to the review number of acknowledging a debt, for image review request；It is reproduction that feedback information, which carries images to be recognized,
Second reproduction probability of image；Obtain the second weight corresponding to the first weight corresponding to machine recognition and review people's identification；
Respectively according to the first weight and the second weight, summation is weighted to the first reproduction probability and the second reproduction probability, obtains reproduction
The weighted sum of probability；It is final to determine that images to be recognized is reproduction image when weighted sum is greater than or equal to default weighted sum.
Wherein, the first weight and the second weight are two different values, the first weight and the second weight and value be 1.
For example, in order to further ensure the accuracy of recognition result, when the machine recognition images to be recognized is reproduction image
When, also images to be recognized can be sent to professional, images to be recognized further be identified by professional, then instead
Feedback includes the feedback information of recognition result, which can be the probability that images to be recognized is reproduction image.If to be identified
Image be reproduction image probability very big (such as larger than 90%) when, then finally determine that images to be recognized is reproduction image.If wait know
When other image is probability smaller (such as less than 90%) of reproduction image, then two probability is weighted summation, it is general to obtain reproduction
The weighted sum of rate determines whether images to be recognized is reproduction image according to weighted sum.When weighted sum is greater than or equal to default add
Power and when, it is final to determine that images to be recognized is reproduction image.When weighted sum is less than default weighted sum, images to be recognized is finally determined
It is not reproduction image.
In one embodiment, server can combine the result of review people's identification to determine whether images to be recognized is to turn over
Clap image.Server can also not need the process for carrying out review people's identification again when the first reproduction probability reaches probability threshold value,
Directly determining images to be recognized is reproduction image.
In one embodiment, this method can be applied to finance and open an account.Determine that images to be recognized is reproduction image final
When, server refuses the account opening request of user；When determining images to be recognized is non-reproduction image, server is then further audited
The other materials that user is submitted allow the account opening request of user if all meeting requirement of opening an account.
As an example, Lis Hartel sign figure will be divided into multiple sub- Lis Hartel sign segments by (1) first, then by sub- Kazakhstan
You are divided into multiple block of pixels by feature segment；(2) in each block of pixels, by the gray value of central pixel point and 8 adjacent pictures
The gray value of vegetarian refreshments is compared, if the gray value of any of 8 pixels pixel is greater than the gray value of central pixel point,
1 then is set by the gray value of corresponding pixel points, is otherwise provided as 0.In this way, 8 pixels in 3 × 3 window neighborhoods can produce
Raw 8 bits are to get the LBP characteristic value for arriving the window center pixel；(3) statistics for then calculating each block of pixels is straight
Fang Tu, the statistic histogram are used to indicate that the frequency that LBP characteristic value occurs in each default range of characteristic values, the i.e. statistics to be general
Rate；Wherein, which can also be normalized.(4) statistics finally according to obtained each block of pixels is straight
Square figure obtains feature vector, obtains the LBP texture feature vector of whole picture images to be recognized, and LBP texture feature vector is inputted mind
It whether is reproduction image by the available images to be recognized of the processing of neural network through network model.
In above-described embodiment, Lis Hartel sign figure is generated according to the images to be recognized of acquisition, extracts LBP from Lis Hartel sign figure
Characteristic value, to obtain the Local textural feature of images to be recognized.Calculate system of the LBP characteristic value in each default range of characteristic values
Probability is counted, the statistical probability of the LBP characteristic value is inputted into neural network model, can be determined by neural network model to be identified
Whether image be reproduction 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.In addition, through the foregoing embodiment, the accuracy rate of reproduction image recognition can be effectively improved, and accuracy rate is by original
80% improves to 93%.
In one embodiment, as shown in figure 4, this method further include:
S402 obtains sample graph to be identified, and figure is labeled to the sample identified, obtains the sample to be identified comprising label
Figure；Label is for indicating whether sample graph to be identified is reproduction image.
Wherein, sample graph to be identified can be 32 cromograms including RGB channel, further, it is also possible to which being includes RGB logical
64 of road or 128 cromograms.
S404 generates corresponding Lis Hartel according to the sample graph to be identified comprising label and levies sample graph.
In one embodiment, before S404, this method can also include: server to the sample to be identified comprising label
Figure carries out the processing such as the Random-Rotation between 0 to 360 degree, and random scaling, adjustment brightness, coloration and clarity, then basis
Treated, and sample graph to be identified generates corresponding Lis Hartel sign sample graph, to increase the generalization ability of neural network model, from
And improve the accuracy rate of reproduction identification.
Wherein, Ha Er (Haar) feature can reflect the grey scale change situation of images to be recognized, as used in images to be recognized
Some features of family face can simply be described by rectangular characteristic.Lis Hartel sign figure can be single pass grayscale image.
In one embodiment, server generates Lis Hartel sign sample corresponding with images to be recognized by way of integrogram
This figure.Wherein, the building mode of integrogram includes: that images to be recognized is arrived each point from the off and is formed by square by server
The pixel accumulated value in shape region, the element as an array save in memory；When the pixel for calculating the rectangular area is cumulative
It, can be with the element of direct index array, without the pixel accumulated value for recalculating this region when value.
For example, the building mode of integrogram includes: the accumulated value for 1) indicating line direction with s (i, j), initialize s (i, -1)
=0.2) integral image is indicated with p (i, j), initialize p (- 1, i)=0.3) images to be recognized, recursive calculation are progressively scanned
The value of the accumulated value s (i, j) and integral image p (i, j) of each pixel (i, j) line direction.Wherein, s (i, j)=s (i, j-1)+f
(i, j), ii (i, j)=ii (i-1, j)+s (i, j).4) when the lower right corner pixel of images to be recognized is arrived in scanning, integral image p
(i, j) i.e. construction is good.
S406 extracts LBP feature samples value from Lis Hartel sign sample graph.
In one embodiment, Lis Hartel sign sample graph is evenly dividing and levies sample segment for multiple sub- Lis Hartels, every
The pixel extraction LBP feature samples value of a sub- Lis Hartel sign sample segment.
Specifically, Lis Hartel sign sample graph is divided into multiple sub- Lis Hartels and levies sample segment；Respectively to each sub- Lis Hartel
Sign sample segment is divided into multiple sampled pixel blocks；In each sample block of pixels, judge non-central pixel gray value whether
Greater than the gray value of central pixel point；If so, setting the first numerical value for the gray value of non-central pixel；If it is not, then will
The gray value of non-central pixel is set as second value；To the non-central pixel in each sample block of pixels after setting gray value
Gray value be weighted summation；Using the result of weighted sum as the LBP feature samples value of each sample block of pixels.
For example, as shown in figure 3, for some pixel in sub- Lis Hartel sign sample segment, centered on the pixel
The gray value of the central pixel point is compared with the gray value of field pixel each in 3 × 3 windows by pixel respectively, if
The gray value of field pixel is greater than or equal to the gray value of central pixel point, then sets 1 for the gray value of field pixel；
If the gray value of field pixel is less than the gray value of central pixel point, 0 is set by the gray value of field pixel, therefore
The binary system for calculating the gray value of the central pixel point is 01111100, and being converted to the decimal system is 124, therefore available each
The LBP feature samples value of sub- Lis Hartel sign sample segment.
S408 calculates statistical probability sample of the LBP feature samples value in each default range of characteristic values.
In one embodiment, S208 can specifically include: server is special to the LBP in each sub- Lis Hartel sign sample segment
Sample value is levied, is ranked up according to size order；Sub- Lis Hartel each after sequence is levied into the LBP feature samples value in sample segment,
Uniformly it is divided into multiple range of characteristic values according to preset step-length；Calculate the system for belonging to LBP feature samples value in each range of characteristic values
Count probability.
In one embodiment, in every sub- Lis Hartel sign sample segment, it is straight that LBP is established according to LBP feature samples value
The corresponding probability of each LBP histogram is stored in different subnumber group A1, A2 ... An respectively, obtains each sub- Ha Er by Fang Tu
Statistical probability of the LBP feature samples value of feature samples segment in each default range of characteristic values.In input neural network model
Before, subnumber group A1, A2 ... An is stored in a big array S by server.
S410, by statistical probability sample input neural network model, by neural network model to statistical probability sample into
Row identifying processing obtains third reproduction probability.
In one embodiment, server is trained the statistical probability input of LBP feature samples value in the form of array
Neural network model.
S412 compares the difference between third reproduction probability and label, adjusts the parameter of neural network model.
In one embodiment, S412 comprises determining that the error between third reproduction probability and label；Error is reversely passed
It is multicast to the network layer of neural network model, obtains the gradient of each network layer parameter；Neural network is adjusted according to gradient obtained
The parameter of each network layer in model.
Wherein, server can determine the error between third reproduction probability and label by loss function.Loss function
Can be following any: mean square error (Mean Squared Error), cross entropy loss function, L2Loss function and
Focal Loss function.
Although it should be understood that Fig. 2,4 flow chart in each step 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, Fig. 2, at least one in 4
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 5, providing a kind of reproduction pattern recognition device, comprising: image collection module
502, characteristic pattern generation module 504, characteristics extraction module 506, computing module 508, processing module 510 and reproduction image determine
Module 512, in which:
Image collection module 502, for obtaining images to be recognized；
Characteristic pattern generation module 504, for generating corresponding Lis Hartel sign figure according to images to be recognized；
Characteristics extraction module 506, for extracting local binary patterns LBP characteristic value from Lis Hartel sign figure；
Computing module 508, for calculating statistical probability of the LBP characteristic value in each default range of characteristic values；
Processing module 510 passes through neural network mould for the statistical probability of LBP characteristic value to be inputted neural network model
Type carries out identifying processing to the statistical probability of LBP characteristic value, obtains the first reproduction probability；
Reproduction image determining module 512, for when the first reproduction probability reaches probability threshold value, then images to be recognized to be to turn over
Clap image.
In one embodiment, characteristics extraction module 506 is also used to: Lis Hartel sign figure is divided into multiple sub- Lis Hartels
Levy segment；Multiple block of pixels are divided into each sub- Lis Hartel sign segment respectively；In each block of pixels, non-central pixel is judged
Whether gray value is greater than the gray value of central pixel point；If so, setting the first numerical value for the gray value of non-central pixel；
If it is not, then setting second value for the gray value of non-central pixel；To non-central in each block of pixels after setting gray value
The gray value of pixel is weighted summation；Using the result of weighted sum as the LBP characteristic value of each block of pixels.
In one embodiment, computing module 508 is also used to: the LBP characteristic value in segment is levied to each sub- Lis Hartel, according to
Size order is ranked up；By the LBP characteristic value in sub- Lis Hartel sign segment each after sequence, uniformly it is divided into according to preset step-length more
A range of characteristic values；Calculate the statistical probability for belonging to LBP characteristic value in each range of characteristic values.
In one embodiment, as shown in fig. 6, the device further include: request generation module 514, connects sending module 516
Receive module 518, Weight Acquisition module 520 and weighting block 522, in which:
Generation module 514 is requested, for generating the image review request for carrying images to be recognized；
Sending module 516, for image review request to be sent to the review number of acknowledging a debt；
Receiving module 518, for receiving feedback information that the review number of acknowledging a debt is sent, for image review request；Instead
Feedforward information carries the second reproduction probability that images to be recognized is reproduction image；
Weight Acquisition module 520, for obtaining the first weight corresponding to machine recognition and checking corresponding to people's identification
Second weight；
Weighting block 522 is used for respectively according to the first weight and the second weight, general to the first reproduction probability and the second reproduction
Rate is weighted summation, obtains the weighted sum of reproduction probability；
Reproduction image determining module 512 is also used to when weighted sum is greater than or equal to default weighted sum, final to determine wait know
Other image is reproduction image.
In one embodiment, device further include: adjustment module 524, in which:
Image collection module 502 is also used to obtain sample graph to be identified, and figure is labeled to the sample identified, is included
The sample graph to be identified of label；Label is for indicating whether sample graph to be identified is reproduction image；
Characteristic pattern generation module 504 is also used to generate corresponding Lis Hartel sign sample according to the sample graph to be identified comprising label
This figure；
Characteristics extraction module 506, which is also used to levy from Lis Hartel, extracts LBP feature samples value in sample graph；
Computing module 508 is also used to calculate statistical probability sample of the LBP feature samples value in each default range of characteristic values；
Processing module 510 is also used to statistical probability sample inputting neural network model, by neural network model to system
It counts probability sample and carries out identifying processing, obtain third reproduction probability；
It adjusts module 524 and adjusts the ginseng of neural network model for comparing the difference between third reproduction probability and label
Number.
In one embodiment, adjustment module 524 is also used to: determining the error between third reproduction probability and label；It will
Error back propagation obtains the gradient of each network layer parameter to the network layer of neural network model；According to gradient tune obtained
The parameter of each network layer in whole neural network model.
In above-described embodiment, Lis Hartel sign figure is generated according to the images to be recognized of acquisition, extracts LBP from Lis Hartel sign figure
Characteristic value, to obtain the Local textural feature of images to be recognized.Calculate system of the LBP characteristic value in each default range of characteristic values
Probability is counted, the statistical probability of the LBP characteristic value is inputted into neural network model, can be determined by neural network model to be identified
Whether image be reproduction 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.
Specific about reproduction pattern recognition device limits the limit that may refer to above for reproduction image-recognizing method
Fixed, details are not described herein.Modules in above-mentioned reproduction pattern recognition device can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 7.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing the data such as images to be recognized and sample graph to be identified.The network interface of the computer equipment is used
It is communicated in passing through network connection with external terminal.To realize that a kind of reproduction image is known when the computer program is executed by processor
Other method.
It will be understood by those skilled in the art that structure shown in Fig. 7, 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；According to images to be recognized
Generate corresponding Lis Hartel sign figure；Local binary patterns LBP characteristic value is extracted from Lis Hartel sign figure；LBP characteristic value is calculated to exist
Statistical probability in each default range of characteristic values；The statistical probability of LBP characteristic value is inputted into neural network model, passes through nerve net
Network model carries out identifying processing to the statistical probability of LBP characteristic value, obtains the first reproduction probability；When the first reproduction probability reaches general
When rate threshold value, then images to be recognized is reproduction image.
In one embodiment, it is also performed the steps of when processor executes computer program and divides equally Lis Hartel sign figure
Segment is levied for multiple sub- Lis Hartels；Multiple block of pixels are divided into each sub- Lis Hartel sign segment respectively；In each block of pixels, judgement
Whether the gray value of non-central pixel is greater than the gray value of central pixel point；If so, by the gray value of non-central pixel
It is set as the first numerical value；If it is not, then setting second value for the gray value of non-central pixel；To each picture after setting gray value
The gray value of non-central pixel in plain block is weighted summation；It is special using the result of weighted sum as the LBP of each block of pixels
Value indicative.
In one embodiment, it also performs the steps of when processor executes computer program to each sub- Lis Hartel sign figure
LBP characteristic value in block, is ranked up according to size order；By the LBP characteristic value in sub- Lis Hartel sign segment each after sequence, press
Uniformly it is divided into multiple range of characteristic values according to preset step-length；Calculate the statistical probability for belonging to LBP characteristic value in each range of characteristic values.
In one embodiment, processor execute computer program when also perform the steps of generation carry it is to be identified
The image of image checks request；Image review request is sent to the review number of acknowledging a debt；Receive review the number of acknowledging a debt send, be directed to
The feedback information of image review request；Feedback information carries the second reproduction probability that images to be recognized is reproduction image；It obtains
Second weight corresponding to first weight corresponding to machine recognition and review people's identification；It is weighed respectively according to the first weight and second
Weight, is weighted summation to the first reproduction probability and the second reproduction probability, obtains the weighted sum of reproduction probability；When weighted sum is greater than
It is final to determine that images to be recognized is reproduction image or when being equal to default weighted sum.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains sample graph to be identified,
Figure is labeled to the sample identified, obtains the sample graph to be identified comprising label；Label is for indicating that sample graph to be identified is
No is reproduction image；Corresponding Lis Hartel, which is generated, according to the sample graph to be identified comprising label levies sample graph；Sample is levied from Lis Hartel
LBP feature samples value is extracted in this figure；Calculate statistical probability sample of the LBP feature samples value in each default range of characteristic values；
Statistical probability sample is inputted into neural network model, identifying processing is carried out to statistical probability sample by neural network model, is obtained
Obtain third reproduction probability；The difference between third reproduction probability and label is compared, the parameter of neural network model is adjusted.
In one embodiment, determining third reproduction probability is also performed the steps of when processor executes computer program
Error between label；By the network layer of error back propagation to neural network model, the gradient of each network layer parameter is obtained；
The parameter of each network layer in neural network model is adjusted according to gradient obtained.
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；Corresponding Ha Er is generated according to images to be recognized
Characteristic pattern；Local binary patterns LBP characteristic value is extracted from Lis Hartel sign figure；LBP characteristic value is calculated in each default characteristic value model
Enclose interior statistical probability；The statistical probability of LBP characteristic value is inputted into neural network model, by neural network model to LBP spy
The statistical probability of value indicative carries out identifying processing, obtains the first reproduction probability；When the first reproduction probability reaches probability threshold value, then to
Identification image is reproduction image.
In one embodiment, it is also performed the steps of when computer program is executed by processor Lis Hartel sign figure is equal
It is divided into multiple sub- Lis Hartel sign segments；Multiple block of pixels are divided into each sub- Lis Hartel sign segment respectively；In each block of pixels, sentence
Whether the gray value of non-central pixel of breaking is greater than the gray value of central pixel point；If so, by the gray scale of non-central pixel
Value is set as the first numerical value；If it is not, then setting second value for the gray value of non-central pixel；To each after setting gray value
The gray value of non-central pixel in block of pixels is weighted summation；Using the result of weighted sum as the LBP of each block of pixels
Characteristic value.
In one embodiment, it is also performed the steps of when computer program is executed by processor and each sub- Lis Hartel is levied
LBP characteristic value in segment, is ranked up according to size order；Sub- Lis Hartel each after sequence is levied into the LBP characteristic value in segment,
Uniformly it is divided into multiple range of characteristic values according to preset step-length；The statistics that calculating belongs to LBP characteristic value in each range of characteristic values is general
Rate.
In one embodiment, generation is also performed the steps of when computer program is executed by processor to carry wait know
The image of other image checks request；Image review request is sent to the review number of acknowledging a debt；Receive the review number of acknowledging a debt is sent, needle
To the feedback information of image review request；Feedback information carries the second reproduction probability that images to be recognized is reproduction image；It obtains
It takes the first weight corresponding to machine recognition and checks the second corresponding weight of people's identification；Respectively according to the first weight and second
Weight is weighted summation to the first reproduction probability and the second reproduction probability, obtains the weighted sum of reproduction probability；When weighted sum is big
It is final to determine that images to be recognized is reproduction image when default weighted sum.
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains sample to be identified
Figure, figure is labeled to the sample identified, obtains the sample graph to be identified comprising label；Label is for indicating sample graph to be identified
It whether is reproduction image；Corresponding Lis Hartel, which is generated, according to the sample graph to be identified comprising label levies sample graph；It is levied from Lis Hartel
LBP feature samples value is extracted in sample graph；Calculate statistical probability sample of the LBP feature samples value in each default range of characteristic values
This；Statistical probability sample is inputted into neural network model, identifying processing is carried out to statistical probability sample by neural network model,
Obtain third reproduction probability；The difference between third reproduction probability and label is compared, the parameter of neural network model is adjusted.
In one embodiment, it is general that determining third reproduction is also performed the steps of when computer program is executed by processor
Error between rate and label；By the network layer of error back propagation to neural network model, the ladder of each network layer parameter is obtained
Degree；The parameter of each network layer in neural network model is adjusted according to gradient obtained.
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 reproduction image-recognizing method, which comprises
Obtain images to be recognized；
Corresponding Lis Hartel sign figure is generated according to images to be recognized；
Local binary patterns LBP characteristic value is extracted from Lis Hartel sign figure；
Calculate statistical probability of the LBP characteristic value in each default range of characteristic values；
The statistical probability of the LBP characteristic value is inputted into neural network model, it is special to the LBP by the neural network model
The statistical probability of value indicative carries out identifying processing, obtains the first reproduction probability；
When the first reproduction probability reaches probability threshold value, then the images to be recognized is reproduction image.
2. the method according to claim 1, wherein described extract local binary patterns from Lis Hartel sign figure
LBP characteristic value includes:
Lis Hartel sign figure is divided into multiple sub- Lis Hartel sign segments；
Multiple block of pixels are divided into each sub- Lis Hartel sign segment respectively；
In each block of pixels, judge whether the gray value of non-central pixel is greater than the gray value of central pixel point；
If so, setting the first numerical value for the gray value of the non-central pixel；If it is not, then by the non-central pixel
Gray value be set as second value；
Summation is weighted to the gray value of the non-central pixel in each block of pixels after setting gray value；
Using the result of weighted sum as the LBP characteristic value of each block of pixels.
3. according to the method described in claim 2, it is characterized in that, described calculate the LBP characteristic value in each default characteristic value
Statistical probability in range includes:
To the LBP characteristic value in each sub- Lis Hartel sign segment, it is ranked up according to size order；
By the LBP characteristic value in the sub- Lis Hartel sign segment each after sequence, multiple characteristic values are uniformly divided into according to preset step-length
Range；
Calculate the statistical probability for belonging to LBP characteristic value in each range of characteristic values.
4. method according to any one of claims 1 to 3, which is characterized in that the then described images to be recognized is reproduction
After image, the method also includes:
Generate the image review request for carrying the images to be recognized；
Described image review request is sent to the review number of acknowledging a debt；
Receive feedback information that the review number of acknowledging a debt is sent, for described image review request；The feedback information is taken
It is the second reproduction probability of reproduction image with the images to be recognized；
Obtain the second weight corresponding to the first weight corresponding to machine recognition and review people's identification；
Respectively according to first weight and second weight, the first reproduction probability and the second reproduction probability are added
Power summation, obtains the weighted sum of reproduction probability；
It is final to determine that images to be recognized is reproduction image when the weighted sum is greater than or equal to default weighted sum.
5. the method according to claim 1, wherein the method also includes:
Sample graph to be identified is obtained, the sample graph to be identified is labeled, obtains the sample graph to be identified comprising label；Institute
Label is stated for indicating whether the sample graph to be identified is reproduction image；
Corresponding Lis Hartel, which is generated, according to the sample graph to be identified comprising the label levies sample graph；
LBP feature samples value is extracted from Lis Hartel sign sample graph；
Calculate statistical probability sample of the LBP feature samples value in each default range of characteristic values；
The statistical probability sample is inputted into neural network model, by the neural network model to the statistical probability sample
Identifying processing is carried out, third reproduction probability is obtained；
The difference between the third reproduction probability and the label is compared, the parameter of neural network model is adjusted.
6. according to the method described in claim 5, it is characterized in that, the comparison third reproduction probability and the label it
Between difference, the parameter for adjusting neural network model includes:
Determine the error between the third reproduction probability and the label；
By the network layer of the error back propagation to neural network model, the gradient of each network layer parameter is obtained；
The parameter of each network layer in the neural network model is adjusted according to gradient obtained.
7. a kind of reproduction pattern recognition device, which is characterized in that described device includes:
Image collection module, for obtaining images to be recognized；
Characteristic pattern generation module, for generating corresponding Lis Hartel sign figure according to images to be recognized；
Characteristics extraction module, for extracting local binary patterns LBP characteristic value from Lis Hartel sign figure；
Computing module, for calculating statistical probability of the LBP characteristic value in each default range of characteristic values；
Processing module passes through the neural network mould for the statistical probability of the LBP characteristic value to be inputted neural network model
Type carries out identifying processing to the statistical probability of the LBP characteristic value, obtains the first reproduction probability；
Reproduction image determining module, for when the first reproduction probability reaches probability threshold value, then the images to be recognized to be
Reproduction image.
8. the method according to the description of claim 7 is characterized in that the characteristics extraction module is also used to:
Lis Hartel sign figure is divided into multiple sub- Lis Hartel sign segments；
Multiple block of pixels are divided into each sub- Lis Hartel sign segment respectively；
In each block of pixels, judge whether the gray value of non-central pixel is greater than the gray value of central pixel point；
If so, setting the first numerical value for the gray value of the non-central pixel；If it is not, then by the non-central pixel
Gray value be set as second value；
Summation is weighted to the gray value of the non-central pixel in each block of pixels after setting gray value；
Using the result of weighted sum as the LBP characteristic value of each block of pixels.
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 |
|---|---|---|---|
| CN201811574530.1A CN109754059A (en) | 2018-12-21 | 2018-12-21 | Reproduction image-recognizing method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811574530.1A CN109754059A (en) | 2018-12-21 | 2018-12-21 | Reproduction image-recognizing method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109754059A true CN109754059A (en) | 2019-05-14 |
Family
ID=66402854
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811574530.1A Pending CN109754059A (en) | 2018-12-21 | 2018-12-21 | Reproduction image-recognizing method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109754059A (en) |
Cited By (4)
| 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 |
| CN111260214A (en) * | 2020-01-15 | 2020-06-09 | 大亚湾核电运营管理有限责任公司 | Nuclear power station reserved work order material receiving method, device, equipment and storage medium |
| CN111461143A (en) * | 2020-03-31 | 2020-07-28 | 珠海格力电器股份有限公司 | Picture copying identification method and device and electronic equipment |
| CN112767394A (en) * | 2021-03-04 | 2021-05-07 | 重庆赛迪奇智人工智能科技有限公司 | Image detection method, device and equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105117729A (en) * | 2015-05-11 | 2015-12-02 | 杭州金培科技有限公司 | Method and device for recognizing copied image |
| WO2017088432A1 (en) * | 2015-11-26 | 2017-06-01 | 腾讯科技（深圳）有限公司 | Image recognition method and device |
| CN108197543A (en) * | 2017-12-22 | 2018-06-22 | 深圳云天励飞技术有限公司 | Image filtering method and device, embedded device and storage medium |
| CN108549836A (en) * | 2018-03-09 | 2018-09-18 | 通号通信信息集团有限公司 | Reproduction detection method, device, equipment and the readable storage medium storing program for executing of photo |
-
2018
- 2018-12-21 CN CN201811574530.1A patent/CN109754059A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105117729A (en) * | 2015-05-11 | 2015-12-02 | 杭州金培科技有限公司 | Method and device for recognizing copied image |
| WO2017088432A1 (en) * | 2015-11-26 | 2017-06-01 | 腾讯科技（深圳）有限公司 | Image recognition method and device |
| CN108197543A (en) * | 2017-12-22 | 2018-06-22 | 深圳云天励飞技术有限公司 | Image filtering method and device, embedded device and storage medium |
| CN108549836A (en) * | 2018-03-09 | 2018-09-18 | 通号通信信息集团有限公司 | Reproduction detection method, device, equipment and the readable storage medium storing program for executing of photo |
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 |
| CN111260214A (en) * | 2020-01-15 | 2020-06-09 | 大亚湾核电运营管理有限责任公司 | Nuclear power station reserved work order material receiving method, device, equipment and storage medium |
| CN111260214B (en) * | 2020-01-15 | 2024-01-26 | 大亚湾核电运营管理有限责任公司 | Method, device, equipment and storage medium for receiving reserved work orders of nuclear power station |
| CN111461143A (en) * | 2020-03-31 | 2020-07-28 | 珠海格力电器股份有限公司 | Picture copying identification method and device and electronic equipment |
| CN112767394A (en) * | 2021-03-04 | 2021-05-07 | 重庆赛迪奇智人工智能科技有限公司 | Image detection method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109886275A (en) | Reproduction image-recognizing method, device, computer equipment and storage medium | |
| CN110399799B (en) | Image recognition and neural network model training method, device and system | |
| CN109754059A (en) | Reproduction image-recognizing method, device, computer equipment and storage medium | |
| CN110163235B (en) | Training of image enhancement model, image enhancement method, device and storage medium | |
| CN111738357B (en) | Junk picture identification method, device and equipment | |
| CN111476268A (en) | Method, device, equipment and medium for training reproduction recognition model and image recognition | |
| CN109784153A (en) | Emotion identification method, apparatus, computer equipment and storage medium | |
| US20210166015A1 (en) | Certificate image extraction method and terminal device | |
| CN111476269B (en) | Balanced sample set construction and image reproduction identification method, device, equipment and medium | |
| CN112804464B (en) | HDR image generation method and device, electronic equipment and readable storage medium | |
| CN111126347B (en) | Human eye state identification method, device, terminal and readable storage medium | |
| WO2023206944A1 (en) | Semantic segmentation method and apparatus, computer device, and storage medium | |
| CN112101359A (en) | Text formula positioning method, model training method and related device | |
| CN110795714A (en) | Identity authentication method and device, computer equipment and storage medium | |
| Guo et al. | Rethinking gradient operator for exposing AI-enabled face forgeries | |
| CN116453232A (en) | Face living body detection method, training method and device of face living body detection model | |
| An | Pedestrian re-recognition algorithm based on optimization deep learning-sequence memory model | |
| WO2024041108A1 (en) | Image correction model training method and apparatus, image correction method and apparatus, and computer device | |
| CN112633200A (en) | Human face image comparison method, device, equipment and medium based on artificial intelligence | |
| CN109871814B (en) | Age estimation method and device, electronic equipment and computer storage medium | |
| CN116975828A (en) | Face fusion attack detection method, device, equipment and storage medium | |
| CN113240071B (en) | Method and device for processing graph neural network, computer equipment and storage medium | |
| CN112967216B (en) | Method, device, equipment and storage medium for detecting key points of face image | |
| CN113362249B (en) | Text image synthesis method, text image synthesis device, computer equipment and storage medium | |
| CN113283388B (en) | Training method, device, equipment and storage medium of living body face detection model |
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 |