CN114066894A - Detection method for display image reproduction, storage medium and processing equipment - Google Patents
Detection method for display image reproduction, storage medium and processing equipment Download PDFInfo
- Publication number
- CN114066894A CN114066894A CN202210048947.4A CN202210048947A CN114066894A CN 114066894 A CN114066894 A CN 114066894A CN 202210048947 A CN202210048947 A CN 202210048947A CN 114066894 A CN114066894 A CN 114066894A
- Authority
- CN
- China
- Prior art keywords
- image
- reproduction
- original image
- probability
- prob
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 20
- 238000012545 processing Methods 0.000 title claims abstract description 9
- 238000000034 method Methods 0.000 claims description 26
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 4
- 238000012360 testing method Methods 0.000 abstract description 3
- 230000000903 blocking effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 241000209202 Bromus secalinus Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000011449 brick Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000004570 mortar (masonry) Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4084—Scaling of whole images or parts thereof, e.g. expanding or contracting in the transform domain, e.g. fast Fourier transform [FFT] domain scaling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a detection method, a storage medium and processing equipment for display image reproduction, and relates to the technical field of image processing. The invention comprises the following steps: s11, acquiring an original image to be detected, and zooming the original image for multiple times; s12, carrying out a reproduction probability test on each zoomed original image, and calculating a corresponding reproduction prediction probability; s13, determining the final reproduction probability of the original image according to the calculated plurality of reproduction prediction probabilities; and S14, if the final copying probability is larger than a preset threshold value, the original image to be detected is a copied image. The invention greatly improves the detection efficiency and has better detection effect on the display image which is locally copied.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a detection method, a storage medium and processing equipment for display image reproduction.
Background
In the physical retail link, brands need to verify the display conditions in the retail store in order to check the market. An efficient method is that the retail user takes pictures and uploads the pictures independently, and the brand dealer carries out image recognition and verification in the background. But this method inevitably causes counterfeiting by the retail user, such as uploading images of others. The method has the advantages that the situation that the retail user uploads images of others can be avoided by limiting the fact that the images can only be shot instantly from a mobile phone (the images cannot be selected from an album) when the images are uploaded, but the situation that the individual retail user cheats through image copying still exists, mainly means that the images are downloaded from a network and displayed on a display or the mobile phone or printed on paper, and then shot and uploaded through the mobile phone.
The display image reproduction detection has the following difficulties: the copying types are various, for example, different displays, different mobile phones and different paper printing modes; some of the traces are visible at high resolution and some are local and often very difficult to identify by means. The copied image is very similar to the real image, and even an experienced image auditor can hardly recognize the copied image. Therefore, identifying whether images uploaded by retail stores are being copied is a pressing need of a brick and mortar retail business.
Disclosure of Invention
The present invention is directed to a method for detecting a reproduction of a display image, so as to solve the above-mentioned problems and needs. The technical effects that can be produced by the preferred technical scheme in the technical schemes provided by the invention are described in detail in the following.
In order to achieve the purpose, the invention provides the following technical scheme:
the invention provides a method for detecting reproduction of a display image, which comprises the following steps:
s11, acquiring an original image to be detected, and zooming the original image for multiple times;
s12, predicting the reproduction probability of each zoomed original image, and calculating the corresponding reproduction prediction probability;
s13, determining the final reproduction probability of the original image according to the calculated reproduction prediction probabilities;
s14, judging the original image to be detected with the final copying probability larger than a preset threshold value as a copied image; returning to step S11, performing a copying detection on the original image to be detected next.
Further, step S12 includes the following steps:
s121, setting a sampling multiple;
s122, dividing each scaled original image into a plurality of image blocks according to the sampling multiple;
s123, respectively predicting the reproduction probability of each image block of each original image;
s124, respectively arranging all the image blocks of each original image in a descending order according to the predicted reproduction probability, and extracting a certain proportion of the image blocks arranged in the front;
s125, calculating average prediction probability for the image blocks extracted from each original image respectively to obtain the reproduction prediction probability of each original image.
Further, in step S122, dividing each scaled original image into a plurality of image blocks by using a full convolutional neural network; in step S123, a full convolution neural network is used to predict a reproduction probability for each image block of each original image.
Further, in step S126, the predicted probability Prob of copying the i-th zoomed original imageiThe calculation formula of (2) is as follows:
Probi= ∑j=1,2…,nProbij /n ;
wherein ProbijThe predicted copying probability of the j-th sequenced image block of the ith scaled original image is obtained, and n is the number of the image blocks extracted from all the image blocks of the ith scaled original image according to the certain proportion.
Further, in step S13, the final rendering probability Prob of the original image is calculated as:
Prob=max(Prob1、Prob2、…、Probm);
wherein max is a function of taking a maximum value, and m is the number of times of scaling the original image.
Further, before executing step S11, the method further includes training a plurality of the full convolution neural networks by using a BCELoss function, where the formula of the BCELoss function is as follows:
Loss(Probi,ChaVi)=-[ ChaVi×log (Probi)+ (1-ChaVi)×log (1-Probi)];
wherein, ChaVi=1, i-th image block is reproduction, ChaVi=0, the i-th image block is a real photograph.
According to another aspect of the present invention, there is also provided a storage medium for display image reproduction, the storage medium having stored thereon a computer program which, when executed, implements the display image reproduction detection method described above; the system also comprises a configuration module and an analysis module; the configuration module is used for configuring and editing a protocol file, and the protocol file is binary format data; the analysis module is used for analyzing the protocol file into JSON format data.
According to another aspect of the present invention, there is also provided a display image reproduction apparatus including: one or more processors and memory; the memory is used for storing one or more computer programs, and the processor or processors are used for executing the one or more computer programs stored in the memory so as to enable the processor or processors to execute the display image duplication detection method.
The implementation of one of the technical schemes of the invention has the following advantages or beneficial effects:
this embodiment is through zooming many times to the display image of gathering, carries out the blocking to the display image of zooming to adopt the mode of weak supervision to discern the image of blocking, promoted detection efficiency greatly, possessed better detection effect to the display image of local reproduction.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without inventive efforts, wherein:
FIG. 1 is a flow chart of a method for detecting a reproduction of an array image according to an embodiment of the present invention;
fig. 2 is a flowchart of step S12 in the method for detecting display image duplication according to the embodiment of the present invention.
Detailed Description
In order that the objects, aspects and advantages of the present invention will become more apparent, various exemplary embodiments will be described below with reference to the accompanying drawings, which form a part hereof, and in which are shown by way of illustration various exemplary embodiments in which the invention may be practiced. The same numbers in different drawings identify the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. It is to be understood that they are merely examples of processes, methods, apparatus, etc. consistent with certain aspects of the present disclosure as detailed in the appended claims, and that other embodiments may be used or structural and functional modifications may be made to the embodiments set forth herein without departing from the scope and spirit of the present disclosure.
In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," and the like are used in the orientations and positional relationships illustrated in the accompanying drawings for the purpose of facilitating the description of the present invention and simplifying the description, and do not indicate or imply that the elements so referred to must have a particular orientation, be constructed in a particular orientation, and be operated. The terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. The term "plurality" means two or more. The terms "coupled" and "connected" are to be construed broadly and may include, for example, a fixed connection, a removable connection, a unitary connection, a mechanical connection, an electrical connection, a communicative connection, a direct connection, an indirect connection via intermediate media, and may include, but are not limited to, a connection between two elements or an interactive relationship between two elements. The term "and/or" includes any and all combinations of one or more of the associated listed items. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In order to explain the technical solution of the present invention, the following description is made by way of specific examples, which only show the relevant portions of the embodiments of the present invention.
The first embodiment is as follows:
as shown in fig. 1-2, the present invention provides a method for detecting reproduction of a display image, comprising the steps of:
and S11, acquiring an original image to be detected, and zooming the original image for multiple times. Specifically, the present embodiment may scale the original image at a scaling of the resolution, which may be 1/2. The number of zooms may depend on the specific image, and the present embodiment is preferably 3 times. That is, the resolutions of the original images are scaled to 896 × 896, 448 × 448 and 224 × 224 according to the scaling ratio of 1/2, resulting in 3 scaled original images Img1, Img2 and Img 3. For different reproduction types, the method can select different resolutions for identification, for example, pictures with obvious screen borders are suitable for identification with a smaller resolution 224 × 224, and pictures with only local moire patterns need to be identified with a larger resolution 896 × 896;
and S12, predicting the reproduction probability of each zoomed original image, and calculating the corresponding reproduction prediction probability. Specifically, a plurality of full convolution neural networks are adopted to carry out copying probability test and copying prediction probability on a plurality of scaled original images, each scaled original image corresponds to one full convolution neural network, and the network structure of each full convolution neural network can be the same. In this embodiment, the 3 full convolution neural networks Net1, Net2, and Net3 are used to perform a tap probability test on the zoom maps Img1, Img2, and Img3, respectively. This step further divides the 3 zooms into a plurality of smaller image blocks and calculates the probability of a snap through the image blocks. The refining steps are as follows:
and S121, setting a sampling multiple. The property of the full convolution neural network is that each pixel of the output image corresponds to a block of the original image, and the size of the block is determined by the specific model structure. In the present embodiment, the sampling multiple of the 3 full convolution neural networks is set to be 32 times, and the number of output image blocks (hereinafter, divided image blocks) corresponding to the scaling maps Img1, Img2, and Img3 is 28 × 28, 14 × 14, and 7 × 7;
and S122, dividing each scaled original image into a plurality of image blocks according to sampling multiples. The trace of the reproduction may be only local, so a better approach would be to divide the picture into many small blocks. Thus, the present embodiment employs image segmentation to identify a snapshot. In order to improve the identification accuracy, a plurality of image blocks are equal in size, overlapped with one another and uniformly distributed in the corresponding scaled original image, and the process is automatically realized by the interior of a full convolution neural network;
and S123, respectively predicting the reproduction probability of each image block of each original image. Specifically, during training of the full convolution neural network, the network is trained through a large number of copied images and real photographed images, and then copied information (network parameters) of the copied images is formed, such as reduction or increase of pixels of the images, texture change of the images (whether the images have moire fringes), existence of obvious frames and the like. The trained network can predict whether the acquired image has the reproduction through the reproduction information and give a probability value of 0-1. This is not described herein in detail for the prior art;
and S124, respectively arranging all image blocks of each original image in a descending order according to the predicted copying probability, and extracting a certain proportion of the image blocks arranged in the front. The present embodiment can quickly find the image block which is easiest to copy by arranging the predicted copying probabilities in descending order. Since not all image blocks have a copy trace, only a part of the image blocks which are most likely to be copied are taken to participate in recognizing the copy. Therefore, the detection efficiency of the method is improved by adopting a weak supervision method, namely, only the image blocks which are arranged in the front 10 percent are extracted to predict the possibility of copying for each zoomed original image;
and S125, calculating the average prediction probability of the image blocks extracted from each original image respectively to obtain the reproduction prediction probability of each zoomed original image. Namely, the calculation formula of the reproduction prediction probability Probi of the ith zoomed original image is as follows:
Probi= ∑j=1,2…,nProbij /n (1);
wherein ProbijFor the predicted copying probability of the j-th ordered image block of the i-th scaled original image, n is the number of image blocks extracted from all image blocks of the i-th scaled original image according to a certain proportion (10%) (e.g. 7 × 7 × 10% =4.9, rounded to 5).
And S13, determining the final reproduction probability of the original image according to the calculated plurality of reproduction prediction probabilities.
Specifically, the maximum value of the reproduction prediction probabilities of the multiple original images is the final reproduction probability of the original images. Namely, it is
Prob =max(Prob1、Prob2、…、Probm) (2);
Where max is the maximum value, m is the number of times the original image is scaled, and m =3 in this embodiment.
S14, judging the original image to be detected with the final copying probability larger than a preset threshold value as a copied image; returning to step S11, the next original image to be detected is subjected to the duplication detection. The preset threshold value may be determined according to the actual detection, or may be obtained according to empirical data. The preset threshold value is 0.7 in this embodiment.
Further, before performing step S11, training a plurality of full convolution neural networks using a BCELoss function is further included. As known, the full convolution neural network needs to be trained (by adopting a conventional classification model training method, input image data needs to collect a batch of picture samples for labeling, namely 0-true and 1-reproduction, and finally, reproduction probability is determined through a BCELoss function). Specifically, the formula of the BCELoss function is as follows:
Loss(Probi,ChaVi)=-[ ChaVi×log (Probi)+ (1-ChaVi)×log (1-Probi)](3);
wherein, ChaVi=1, i-th image block is reproduction, ChaVi=0, the i-th image block is a real photograph. ChaV corresponding to minimum value of Loss calculationiAnd the image corresponding to the value is the real photographed image, otherwise, the image is a reproduction image.
In summary, the present embodiment divides the scaled display image into blocks by scaling the captured display image multiple times. The divided image blocks are identified in a weak supervision mode, so that the detection efficiency is greatly improved, and the display image with local reproduction has a better detection effect.
Example two:
the invention also provides a storage medium for display image reproduction, wherein the storage medium is stored with a computer program, and the computer program realizes the display image reproduction detection method in the embodiment one. Further, the storage medium for display image reproduction of the present embodiment further includes a configuration module and an analysis module; the configuration module is used for configuring and editing a protocol file, and the protocol file is binary format data; the analysis module is used for analyzing the protocol file into JSON format data.
The aforementioned storage medium that can store the program code includes: an electrostatic hard disk, a solid state hard disk, a random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), an optical storage device, a magnetic storage device, a flash memory, a magnetic or optical disk, and/or combinations thereof, may be implemented by any type of volatile or non-volatile storage device, or combinations thereof.
Example three:
the invention also provides a display image reproduction processing device which comprises one or more processors and a memory. A memory for storing one or more computer programs, the one or more processors being configured to execute the one or more computer programs stored in the memory to cause the one or more processors to perform the method for detecting a reproduction of an image as described in embodiment one.
It will be appreciated by those of ordinary skill in the art that all or part of the features/steps implementing the above-described method embodiments may be implemented by a method, a data processing system, or a computer program, and that such features may be implemented without hardware, in software or in a combination of hardware and software.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the spirit and scope of the invention. In addition, many modifications may be made to adapt a particular situation or material to the teachings of the invention without departing from the essential scope thereof. Therefore, it is intended that the invention not be limited to the particular embodiment disclosed, but that the invention will include all embodiments falling within the scope of the appended claims.
Claims (8)
1. A method for detecting reproduction of a display image, comprising the steps of:
s11, acquiring an original image to be detected, and zooming the original image for multiple times;
s12, predicting the reproduction probability of each zoomed original image, and calculating the corresponding reproduction prediction probability;
s13, determining the final reproduction probability of the original image according to the calculated reproduction prediction probabilities;
s14, judging the original image to be detected with the final copying probability larger than a preset threshold value as a copied image; returning to step S11, performing a copying detection on the original image to be detected next.
2. The method for detecting display image reproduction according to claim 1, wherein step S12 includes the steps of:
s121, setting a sampling multiple;
s122, dividing each scaled original image into a plurality of image blocks according to the sampling multiple;
s123, respectively predicting the reproduction probability of each image block of each original image;
s124, respectively arranging all the image blocks of each original image in a descending order according to the predicted reproduction probability, and extracting a certain proportion of the image blocks arranged in the front;
s125, calculating average prediction probability for the image blocks extracted from each original image respectively to obtain the reproduction prediction probability of each original image.
3. The method for detecting reproduction of an array image according to claim 2, wherein in step S122, a full convolution neural network is used to divide each scaled original image into a plurality of image blocks;
in step S123, a full convolution neural network is used to predict a reproduction probability for each image block of each original image.
4. The method for detecting reproduction of display image according to claim 3, wherein in step S126, the reproduction prediction probability Prob of the i-th scaled original imageiThe calculation formula of (2) is as follows:
Probi= ∑j=1,2…,nProbij /n ;
wherein ProbijThe predicted copying probability of the j-th sequenced image block of the ith scaled original image is obtained, and n is the number of the image blocks extracted from all the image blocks of the ith scaled original image according to the certain proportion.
5. The method for detecting display image reproduction according to claim 4, wherein in step S13, the final reproduction probability Prob of the original image is calculated by the following formula:
Prob=max(Prob1、Prob2、…、Probm);
wherein max is a function of taking a maximum value, and m is the number of times of scaling the original image.
6. The method for detecting display image reproduction of claim 5, further comprising training a plurality of said full convolution neural networks using a BCELoss function, wherein the formula of the BCELoss function is as follows:
Loss(Probi,ChaVi)=-[ ChaVi×log (Probi)+ (1-ChaVi)×log (1-Probi)];
wherein, ChaVi=1, i-th image block is reproduction, ChaVi=0, the i-th image block is a real photograph.
7. A storage medium for display image reproduction, characterized in that the storage medium has stored thereon a computer program which, when executed, implements a display image reproduction detection method according to any one of claims 1 to 6;
the system also comprises a configuration module and an analysis module; the configuration module is used for configuring and editing a protocol file, and the protocol file is binary format data; the analysis module is used for analyzing the protocol file into JSON format data.
8. A processing apparatus for display image reproduction, comprising:
one or more processors and memory;
the memory for storing one or more computer programs, the one or more processors for executing the one or more computer programs stored in the memory to cause the one or more processors to perform the method for detecting display image duplication according to any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210048947.4A CN114066894A (en) | 2022-01-17 | 2022-01-17 | Detection method for display image reproduction, storage medium and processing equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210048947.4A CN114066894A (en) | 2022-01-17 | 2022-01-17 | Detection method for display image reproduction, storage medium and processing equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114066894A true CN114066894A (en) | 2022-02-18 |
Family
ID=80231149
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210048947.4A Pending CN114066894A (en) | 2022-01-17 | 2022-01-17 | Detection method for display image reproduction, storage medium and processing equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114066894A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114565827A (en) * | 2022-04-29 | 2022-05-31 | 深圳爱莫科技有限公司 | Cigarette display anti-cheating detection method based on image recognition and model training method |
CN117333762A (en) * | 2023-12-02 | 2024-01-02 | 深圳爱莫科技有限公司 | Image reproduction identification method based on multi-feature fusion |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109325933A (en) * | 2017-07-28 | 2019-02-12 | 阿里巴巴集团控股有限公司 | A kind of reproduction image-recognizing method and device |
CN109859227A (en) * | 2019-01-17 | 2019-06-07 | 平安科技(深圳)有限公司 | Reproduction image detecting method, device, computer equipment and storage medium |
CN110348511A (en) * | 2019-07-08 | 2019-10-18 | 创新奇智(青岛)科技有限公司 | A kind of picture reproduction detection method, system and electronic equipment |
WO2020147445A1 (en) * | 2019-01-16 | 2020-07-23 | 深圳壹账通智能科技有限公司 | Rephotographed image recognition method and apparatus, computer device, and computer-readable storage medium |
CN112364824A (en) * | 2020-11-30 | 2021-02-12 | 天翼电子商务有限公司 | Copying detection method of multi-resolution network structure |
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 |
CN113344000A (en) * | 2021-06-29 | 2021-09-03 | 南京星云数字技术有限公司 | Certificate copying and recognizing method and device, computer equipment and storage medium |
CN113837310A (en) * | 2021-09-30 | 2021-12-24 | 四川新网银行股份有限公司 | Multi-scale fusion certificate copying and identifying method and device, electronic equipment and medium |
-
2022
- 2022-01-17 CN CN202210048947.4A patent/CN114066894A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109325933A (en) * | 2017-07-28 | 2019-02-12 | 阿里巴巴集团控股有限公司 | A kind of reproduction image-recognizing method and device |
WO2020147445A1 (en) * | 2019-01-16 | 2020-07-23 | 深圳壹账通智能科技有限公司 | Rephotographed image recognition method and apparatus, computer device, and computer-readable storage medium |
CN109859227A (en) * | 2019-01-17 | 2019-06-07 | 平安科技(深圳)有限公司 | Reproduction image detecting method, device, computer equipment and storage medium |
CN110348511A (en) * | 2019-07-08 | 2019-10-18 | 创新奇智(青岛)科技有限公司 | A kind of picture reproduction detection method, system and electronic equipment |
CN112364824A (en) * | 2020-11-30 | 2021-02-12 | 天翼电子商务有限公司 | Copying detection method of multi-resolution network structure |
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 |
CN113344000A (en) * | 2021-06-29 | 2021-09-03 | 南京星云数字技术有限公司 | Certificate copying and recognizing method and device, computer equipment and storage medium |
CN113837310A (en) * | 2021-09-30 | 2021-12-24 | 四川新网银行股份有限公司 | Multi-scale fusion certificate copying and identifying method and device, electronic equipment and medium |
Non-Patent Citations (1)
Title |
---|
李晶 等: "基于卷积神经网络的翻拍图片哈希检索方法", 《中国传媒大学学报(自然科学版)》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114565827A (en) * | 2022-04-29 | 2022-05-31 | 深圳爱莫科技有限公司 | Cigarette display anti-cheating detection method based on image recognition and model training method |
CN117333762A (en) * | 2023-12-02 | 2024-01-02 | 深圳爱莫科技有限公司 | Image reproduction identification method based on multi-feature fusion |
CN117333762B (en) * | 2023-12-02 | 2024-03-15 | 深圳爱莫科技有限公司 | Image reproduction identification method based on multi-feature fusion |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110853033B (en) | Video detection method and device based on inter-frame similarity | |
CN114066894A (en) | Detection method for display image reproduction, storage medium and processing equipment | |
US20220172476A1 (en) | Video similarity detection method, apparatus, and device | |
CN110705405A (en) | Target labeling method and device | |
CN108337505B (en) | Information acquisition method and device | |
CN112633255B (en) | Target detection method, device and equipment | |
CN111753775B (en) | Fish growth assessment method, device, equipment and storage medium | |
CN111401238A (en) | Method and device for detecting character close-up segments in video | |
CN112767394A (en) | Image detection method, device and equipment | |
CN111666945A (en) | Storefront violation identification method and device based on semantic segmentation and storage medium | |
Ahmed et al. | Temporal image forensic analysis for picture dating with deep learning | |
CN114005019B (en) | Method for identifying flip image and related equipment thereof | |
CN114419739A (en) | Training method of behavior recognition model, behavior recognition method and equipment | |
CN113486856A (en) | Driver irregular behavior detection method based on semantic segmentation and convolutional neural network | |
CN113486715A (en) | Image reproduction identification method, intelligent terminal and computer storage medium | |
CN112287905A (en) | Vehicle damage identification method, device, equipment and storage medium | |
CN114663731B (en) | Training method and system of license plate detection model, and license plate detection method and system | |
CN114170271B (en) | Multi-target tracking method, equipment and storage medium with self-tracking consciousness | |
US20110161443A1 (en) | Data management systems and methods for mobile devices | |
CN111400534B (en) | Cover determination method and device for image data and computer storage medium | |
CN115860026A (en) | Bar code detection method and device, bar code detection equipment and readable storage medium | |
CN112070094B (en) | Method and device for screening training data, electronic equipment and storage medium | |
CN111553408B (en) | Automatic test method for video recognition software | |
CN110460770B (en) | Image processing method and system | |
CN115004245A (en) | Target detection method, target detection device, electronic equipment and computer 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220218 |
|
RJ01 | Rejection of invention patent application after publication |