CN109859372A - Watermark recognition methods, device, cloud server and the system of anti-forge paper - Google Patents
Watermark recognition methods, device, cloud server and the system of anti-forge paper Download PDFInfo
- Publication number
- CN109859372A CN109859372A CN201811492285.XA CN201811492285A CN109859372A CN 109859372 A CN109859372 A CN 109859372A CN 201811492285 A CN201811492285 A CN 201811492285A CN 109859372 A CN109859372 A CN 109859372A
- Authority
- CN
- China
- Prior art keywords
- watermark
- paper
- image
- identified
- neural network
- 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
- Editing Of Facsimile Originals (AREA)
Abstract
The present invention provides watermark recognition methods, device, cloud server and the systems of a kind of anti-forge paper, wherein this method comprises: acquiring the image of watermark paper to be identified；The image of watermark paper to be identified is issued；Receive the recognition result according to neural network recognization model feedback；The neural network recognization model is generated according to the training of multiple watermark sample images.Above-mentioned technical proposal improves the efficiency and accuracy of the watermark identification of anti-forge paper.
Description
Technical field
The present invention relates to watermark authentication technique field, in particular to the watermark recognition methods of a kind of anti-forge paper, device, cloud
Hold server and system.
Background technique
Watermark is one of bank-note paper and the important anti-counterfeiting technology of other anti-forge papers, which is different from the number that printing generates
Word watermark, it is to be formed in paper forming process during producing paper by the design of watermark net, is had saturating
Penetrate visible feature under light.The identification of true and false watermark is detected currently without special instrument, is also rested on manually with the naked eye
It goes to identify.But this manual identified mode is more difficult for ordinary populace, and it is relevant that this is primarily due to public shortage watermark
Professional knowledge does not know about the moulding mechanism of watermark, and true and false watermark is caused to be difficult to identify, and leads to the accuracy rate and efficiency mistake of identification
It is low.It is if things go on like this, public mainly to identify true and false banknote by printing anti-fake (such as: gravure printed hand feel, photochromatic printing ink, to printing),
It is seldom discerned the false from the genuine by watermark, this also makes the anti-fake effect of watermark have a greatly reduced quality.Paper watermark technology develops constantly,
But only watermark can be just set to play better anti-fake effect the means of identification promotion of watermark.
Summary of the invention
The embodiment of the invention provides a kind of watermark recognition methods of anti-forge paper, to improve watermark identification efficiency and
Accuracy, this method comprises:
Acquire the image of watermark paper to be identified；
The image of watermark paper to be identified is issued；
Receive the recognition result according to neural network recognization model feedback；The neural network recognization model is according to multiple water
Sample image training is printed to generate.
The embodiment of the invention also provides a kind of watermark recognition methods of anti-forge paper, to improve the efficiency of watermark identification
And accuracy, this method comprises:
Receive the image of watermark paper to be identified；
The image of the watermark paper to be identified is inputted into neural network recognization model, to the image of water marked paper to be identified
It is identified, obtains recognition result；The neural network recognization model is generated according to the training of multiple watermark sample images；
Recognition result is issued.
The embodiment of the invention also provides a kind of watermark identification devices of anti-forge paper, to improve the efficiency of watermark identification
And accuracy, the device include:
Acquisition unit, for acquiring the image of watermark paper to be identified；
First transmission unit, for issuing the image of watermark paper to be identified；
First receiving unit, for receiving the recognition result according to neural network recognization model feedback；The neural network
Identification model is generated according to the training of multiple watermark sample images.
The embodiment of the invention also provides a kind of watermarks of anti-forge paper to identify cloud server, to improve watermark identification
Efficiency and accuracy, which includes:
Second receiving unit, for receiving the image of watermark paper to be identified；
Recognition unit, for the image of the watermark paper to be identified to be inputted neural network recognization model, to be identified
The image of watermark paper is identified, recognition result is obtained；The neural network recognization model is according to multiple watermark sample images
Training generates；
Second transmission unit, for issuing recognition result.
The embodiment of the invention also provides a kind of watermark identifying systems of anti-forge paper, to improve the efficiency of watermark identification
And accuracy, the system include:
Watermark identification device as described above；
Watermark as described above identifies cloud server.
The embodiment of the invention also provides a kind of computer equipments, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, the processor execute the watermark recognition methods of the anti-forge paper.
The embodiment of the invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage
There is the computer program for the watermark recognition methods for executing anti-forge paper.
Technical solution provided in an embodiment of the present invention acquires watermark to be identified by the watermark identification device of an anti-forge paper
The image of paper；The image of watermark paper to be identified is issued to the cloud server of an anti-forge paper；The cloud of the anti-forge paper
End server receives the image of watermark paper to be identified, and the image of the watermark paper to be identified is inputted neural network recognization mould
Type identifies the image of water marked paper to be identified, obtains recognition result, and recognition result is fed back to watermark identification dress
It sets；Wherein, above-mentioned neural network recognization model is generated according to the training of multiple watermark sample images, is realized with this solution
Identification fast and accurately to the watermark of anti-forge paper improves the efficiency and accuracy of the watermark identification of anti-forge paper.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, not
Constitute limitation of the invention.In the accompanying drawings:
Fig. 1 is the structural schematic diagram of the watermark identifying system of anti-forge paper in the embodiment of the present invention；
Fig. 2 is that the process in the embodiment of the present invention applied to the watermark recognition methods of the watermark identification device of anti-forge paper is shown
It is intended to；
Fig. 3 is the stream in the embodiment of the present invention applied to the watermark identification cloud server watermark recognition methods of anti-forge paper
Journey schematic diagram；
Fig. 4 is the structural schematic diagram of the watermark identification device of anti-forge paper in the embodiment of the present invention；
Fig. 5 is the structural schematic diagram of the watermark identification cloud server of anti-forge paper in the embodiment of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, right below with reference to embodiment and attached drawing
The present invention is described in further details.Here, exemplary embodiment and its explanation of the invention is used to explain the present invention, but simultaneously
It is not as a limitation of the invention.
Inventor's discovery: the identification of true and false watermark is detected currently without special instrument, is also rested on and is manually used meat
Eye goes to identify.But this manual identified mode is more difficult for ordinary populace, and it is related that this is primarily due to public shortage watermark
Professional knowledge, the moulding mechanism of watermark is not known about, true and false watermark is caused to be difficult to identify.In addition, artificial intelligence is as one
Emerging industry, is rapidly developed in recent years, at present artificial intelligence finance, electric business retail, security protection, education,
The multiple fields such as medical treatment & health, personal assistant and automatic Pilot are applied.
Accordingly, it is considered to arrive above-mentioned technical problem, a kind of watermark of anti-forge paper based on artificial intelligence is inventors herein proposed
Then identification technology scheme, the program utilize the mind of artificial intelligence by carrying out Image Acquisition and processing to a large amount of watermark samples
Picture is analyzed through network model and algorithm, realizes the intelligent recognition to watermark, to reach the mesh that true and false watermark identifies
's.The technology can be adapted for bank-note paper and other water-mark fake-proof papers.Below to the watermark recognition methods scheme of the anti-forge paper
It describes in detail as follows.
Fig. 1 is the structural schematic diagram of the watermark identifying system of anti-forge paper in the embodiment of the present invention, as shown in Figure 1, this hair
The watermark identifying system of anti-forge paper can be divided into the part of front-end and back-end two in bright embodiment, and front end can be an anti-counterfeiting paper
The watermark identification device (abbreviation identification device 10, see Fig. 1) opened, rear end can be the watermark identification cloud service of an anti-forge paper
Device (abbreviation cloud server 20, see Fig. 1), specimen page to be measured is watermark paper to be identified in Fig. 1.Wherein, the anti-forge paper
Watermark identification device is responsible for acquiring the image of watermark paper to be identified, and the image of watermark paper to be identified is issued to anti-forge paper
Watermark identify cloud server, wait testing result.The watermark identification cloud server of the anti-forge paper is responsible for handling above-mentioned
The image of the watermark paper to be identified is inputted neural network recognization model, to be identified by the image of watermark paper to be identified
The image of watermark paper is identified, recognition result is obtained, and is returned to detection (identification) result and given watermark identification device, wherein
The neural network recognization model according to multiple watermark sample images training generate, user can realize whenever and wherever possible quickly,
The efficiently identification of watermark.It describes in detail below to the various pieces and its function of the watermark identifying system of the anti-forge paper
It is as follows.
Firstly, introducing watermark identification device and function.
Fig. 2 is the flow diagram of the watermark recognition methods of anti-forge paper in the embodiment of the present invention, and this method is applied to water
Identification device is printed, as shown in Fig. 2, this method comprises the following steps:
Step 101: acquiring the image of watermark paper to be identified；
Step 102: the image of watermark paper to be identified is issued；
Step 103: receiving the recognition result according to neural network recognization model feedback；The neural network recognization model root
It is generated according to the training of multiple watermark sample images.
Technical solution provided in an embodiment of the present invention acquires watermark to be identified by the watermark identification device of an anti-forge paper
The image of paper；The image of watermark paper to be identified is issued to the cloud server of an anti-forge paper；The cloud of the anti-forge paper
End server receives the image of watermark paper to be identified, and the image of the watermark paper to be identified is inputted neural network recognization mould
Type identifies the image of water marked paper to be identified, obtains recognition result, and recognition result will be fed back to anti-forge paper
Watermark identification device；Wherein, above-mentioned neural network recognization model is generated according to the training of multiple watermark sample images, by this
Scheme realizes the identification fast and accurately to watermark, improves the efficiency and accuracy of the watermark identification of anti-forge paper.
When it is implemented, introducing the generating process of neural network recognization model first.Deep learning model (know by neural network
Other model) need mass data to be trained and verify, therefore when taking a new watermark, need early period to be prepared big
The watermark sample of amount.Image Acquisition is top priority, and watermark sample can be placed in backlight and be carried out with mobile phone by Image Acquisition
It takes pictures, obtains sample image.By the neural network recognization model of computer software and algorithm to a large amount of watermark samples of acquisition
Picture carries out recognition training, and trained result (neural network model that training is completed, be also deep learning model) is put into
Cloud server.
In one embodiment, the image for acquiring watermark paper to be identified may include:
The image of water marked paper to be identified is pre-processed, pretreated watermark paper image is obtained；
The image of watermark paper to be identified is issued, may include:
By the sending of the pretreated watermark paper image.
When it is implemented, above-mentioned pretreated process may include cutting from the image of above-mentioned collected watermark paper
The image of watermark to be identified out.It is, of course, also possible to include some other pre-treatment step conducive to subsequent identification, such as to watermark
It rotated, deform to obtain the pretreatment works such as positive watermarking images.Pretreated process further improves watermark identification
Accuracy rate and efficiency.Watermark identification device can be mobile phone, carry out Image Acquisition to watermark to be measured by mobile phone, acquire laggard
Row is cut, and is then uploaded to cloud by cell phone network, is received the feedback testing result of cloud server, complete whenever and wherever possible
The identification of watermark improves the efficiency and accuracy of watermark identification.
In one embodiment, the recognition result according to neural network recognization model feedback is received, may include: reception root
According to the recognition result of updated neural network recognization model feedback.
When it is implemented, by the available more accurate recognition result of neural network recognization model constantly updated,
Improve the accuracy rate of watermark identification.
Secondly, introducing watermark identification cloud server and function.
Based on the same inventive concept, a kind of watermark recognition methods is additionally provided in the embodiment of the present invention, this method is applied to
Watermark identifies cloud server, such as the following examples.Due to being applied to the watermark recognition methods of watermark identification cloud server
The principle solved the problems, such as to it is above-mentioned be applied to the watermark recognition methods of watermark identification device it is similar, therefore be applied to watermark identify cloud
Hold the reality for implementing to refer to the above-mentioned watermark recognition methods applied to watermark identification device of the watermark recognition methods of server
It applies, overlaps will not be repeated.Used below, the software of predetermined function may be implemented in term " module " or " module "
And/or the combination of hardware.Although device described in following embodiment is preferably realized with software, hardware or soft
The realization of the combination of part and hardware is also that may and be contemplated.
Fig. 3 is the stream in the embodiment of the present invention applied to the watermark identification cloud server watermark recognition methods of anti-forge paper
Journey schematic diagram, as shown in figure 3, the watermark recognition methods includes the following steps:
Step 201: receiving the image of watermark paper to be identified；
Step 202: the image of the watermark paper to be identified being inputted into neural network recognization model, to water marked paper to be identified
The image opened is identified, recognition result is obtained；The neural network recognization model is given birth to according to the training of multiple watermark sample images
At；
Step 203: recognition result is issued.
In one embodiment, the image for receiving watermark paper to be identified may include:
Receive pretreated watermark paper image；
The image of the watermark paper to be identified is inputted into neural network recognization model, to the image of water marked paper to be identified
It is identified, obtains recognition result, may include:
The pretreated watermark paper image is inputted into neural network recognization model, to pretreated watermark paper
Image is identified, recognition result is obtained.
When it is implemented, identifying to pretreated watermark paper image, the standard of watermark identification is further improved
True rate and efficiency.
In one embodiment, above-mentioned watermark recognition methods can also include:
It, will be described when determining that the image of collected watermark paper to be identified is not present in history watermark sample image
The image of watermark paper to be identified is added in history watermark sample image, obtains updated history watermark sample image；
According to updated history watermark sample image, the training neural network recognization model obtains updated mind
Through Network Recognition model.
When it is implemented, by being continuously updated neural network recognization model, available more accurate recognition result,
Improve the accuracy rate of watermark identification.
Based on the same inventive concept, a kind of watermark identification device of anti-forge paper is additionally provided in the embodiment of the present invention, such as
The following examples.The principle and the above-mentioned watermark applied to watermark identification device solved the problems, such as due to watermark identification device is identified
Method is similar, therefore the implementation for implementing to refer to above-mentioned watermark recognition methods of watermark identification device, and it is no longer superfluous to repeat place
It states.Used below, the combination of the software and/or hardware of predetermined function may be implemented in term " module " or " module ".To the greatest extent
Device described in pipe following embodiment is preferably realized with software, but the combined reality of hardware or software and hardware
Now and may and it be contemplated.
Fig. 4 is the structural schematic diagram of the watermark identification device of anti-forge paper in the embodiment of the present invention；As shown in figure 4, the dress
It sets and includes:
Acquisition unit 11, for acquiring the image of watermark paper to be identified；
First transmission unit 12, for issuing the image of watermark paper to be identified；
First receiving unit 13, for receiving the recognition result according to neural network recognization model feedback；The nerve net
Network identification model is generated according to the training of multiple watermark sample images.
In one embodiment, the acquisition unit specifically can be used for:
The image of water marked paper to be identified is pre-processed, pretreated watermark paper image is obtained；
The image of watermark paper to be identified is issued, comprising:
By the sending of the pretreated watermark paper image.
In one embodiment, first receiving unit specifically can be used for: receiving and is known according to updated neural network
The recognition result of other model feedback.
Based on the same inventive concept, a kind of watermark identification cloud service of anti-forge paper is additionally provided in the embodiment of the present invention
Device, such as the following examples.Since the principle that watermark identification cloud server solves the problems, such as takes with watermark identification cloud is applied to
The watermark recognition methods of business device is similar, therefore the implementation of watermark identification cloud server can be with reference to above-mentioned watermark recognition methods
Implement, overlaps will not be repeated.Used below, the software of predetermined function may be implemented in term " module " or " module "
And/or the combination of hardware.Although device described in following embodiment is preferably realized with software, hardware or soft
The realization of the combination of part and hardware is also that may and be contemplated.
Fig. 5 is the structural schematic diagram of the watermark identification cloud server of anti-forge paper in the embodiment of the present invention, such as Fig. 5 institute
Show, which includes:
Second receiving unit 21, for receiving the image of watermark paper to be identified；
Recognition unit 22 treats knowledge for the image of the watermark paper to be identified to be inputted neural network recognization model
The image of other watermark paper is identified, recognition result is obtained；The neural network recognization model is according to multiple watermark sample drawings
As training generates；
Second transmission unit 23, for issuing recognition result.
In one embodiment, second receiving unit specifically can be used for:
Receive pretreated watermark paper image；
The recognition unit specifically can be used for: the pretreated watermark paper image is inputted neural network recognization
Model identifies pretreated watermark paper image, obtains recognition result.
In one embodiment, above-mentioned watermark identification cloud server can also include:
Sample updating unit, for determining that the image of collected watermark paper to be identified is not present in history watermark sample
When in product image, the image of the watermark paper to be identified is added in history watermark sample image, updated go through is obtained
History watermark sample image；
Training unit, for according to updated history watermark sample image, the training neural network recognization model to be obtained
To updated neural network recognization model.
The embodiment of the invention also provides a kind of watermark identifying systems of anti-forge paper, as shown in Figure 1, the system includes:
The watermark identification device of anti-forge paper as described above；
The watermark of anti-forge paper as described above identifies cloud server.
The embodiment of the invention also provides a kind of computer equipments, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, the processor execute the watermark recognition methods of the anti-forge paper.
The embodiment of the invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage
There is the computer program for the watermark recognition methods for executing anti-forge paper.
The present invention implements the advantageous effects of the technical solution provided are as follows: realize whenever and wherever possible to the quick of watermark and
Accurately identification improves the efficiency and accuracy of the watermark identification of anti-forge paper.
Obviously, those skilled in the art should be understood that each module of the above-mentioned embodiment of the present invention or each step can be with
It is realized with general computing device, they can be concentrated on a single computing device, or be distributed in multiple computing devices
On composed network, optionally, they can be realized with the program code that computing device can perform, it is thus possible to by it
Store and be performed by computing device in the storage device, and in some cases, can be held with the sequence for being different from herein
The shown or described step of row, perhaps they are fabricated to each integrated circuit modules or will be multiple in them
Module or step are fabricated to single integrated circuit module to realize.In this way, the embodiment of the present invention be not limited to it is any specific hard
Part and software combine.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the embodiment of the present invention can have various modifications and variations.All within the spirits and principles of the present invention, made
Any modification, equivalent substitution, improvement and etc. should all be included in the protection scope of the present invention.
Claims (15)
1. a kind of watermark recognition methods of anti-forge paper characterized by comprising
Acquire the image of watermark paper to be identified；
The image of watermark paper to be identified is issued；
Receive the recognition result according to neural network recognization model feedback；The neural network recognization model is according to multiple watermark samples
The training of product image generates.
2. the watermark recognition methods of anti-forge paper as described in claim 1, which is characterized in that acquire watermark paper to be identified
Image, comprising:
The image of water marked paper to be identified is pre-processed, pretreated watermark paper image is obtained；
The image of watermark paper to be identified is issued, comprising:
By the sending of the pretreated watermark paper image.
3. the watermark recognition methods of anti-forge paper as described in claim 1, which is characterized in that receive according to neural network recognization
The recognition result of model feedback, comprising: receive the recognition result according to updated neural network recognization model feedback.
4. a kind of watermark recognition methods of anti-forge paper characterized by comprising
Receive the image of watermark paper to be identified；
The image of the watermark paper to be identified is inputted into neural network recognization model, the image of water marked paper to be identified is carried out
Identification, obtains recognition result；The neural network recognization model is generated according to the training of multiple watermark sample images；
Recognition result is issued.
5. the watermark recognition methods of anti-forge paper as claimed in claim 4, which is characterized in that receive watermark paper to be identified
Image, comprising:
Receive pretreated watermark paper image；
The image of the watermark paper to be identified is inputted into neural network recognization model, the image of water marked paper to be identified is carried out
Identification, obtains recognition result, comprising:
The pretreated watermark paper image is inputted into neural network recognization model, to pretreated watermark paper image
It is identified, obtains recognition result.
6. the watermark recognition methods of anti-forge paper as claimed in claim 4, which is characterized in that further include:
When determining that the image of collected watermark paper to be identified is not present in history watermark sample image, by described wait know
The image of other watermark paper is added in history watermark sample image, obtains updated history watermark sample image；
According to updated history watermark sample image, the training neural network recognization model obtains updated nerve net
Network identification model.
7. a kind of watermark identification device of anti-forge paper characterized by comprising
Acquisition unit, for acquiring the image of watermark paper to be identified；
First transmission unit, for issuing the image of watermark paper to be identified；
First receiving unit, for receiving the recognition result according to neural network recognization model feedback；The neural network recognization
Model is generated according to the training of multiple watermark sample images.
8. the watermark identification device of anti-forge paper as claimed in claim 7, which is characterized in that the acquisition unit is specifically used
In:
The image of water marked paper to be identified is pre-processed, pretreated watermark paper image is obtained；
The image of watermark paper to be identified is issued, comprising:
By the sending of the pretreated watermark paper image.
9. the watermark identification device of anti-forge paper as claimed in claim 7, which is characterized in that first receiving unit is specific
For: receive the recognition result according to updated neural network recognization model feedback.
10. a kind of watermark of anti-forge paper identifies cloud server characterized by comprising
Second receiving unit, for receiving the image of watermark paper to be identified；
Recognition unit, for the image of the watermark paper to be identified to be inputted neural network recognization model, to watermark to be identified
The image of paper is identified, recognition result is obtained；The neural network recognization model is according to the training of multiple watermark sample images
It generates；
Second transmission unit, for issuing recognition result.
11. the watermark of anti-forge paper as claimed in claim 10 identifies cloud server, which is characterized in that described second receives
Unit is specifically used for:
Receive pretreated watermark paper image；
The recognition unit is specifically used for: the pretreated watermark paper image is inputted into neural network recognization model, it is right
Pretreated watermark paper image is identified, recognition result is obtained.
12. the watermark of anti-forge paper as claimed in claim 10 identifies cloud server, which is characterized in that further include:
Sample updating unit, for determining that the image of collected watermark paper to be identified is not present in history watermark sample drawing
When as in, the image of the watermark paper to be identified is added in history watermark sample image, updated history water is obtained
Print sample image；
Training unit, for according to updated history watermark sample image, the training neural network recognization model to be obtained more
Neural network recognization model after new.
13. a kind of watermark identifying system of anti-forge paper characterized by comprising
The watermark identification device of anti-forge paper as described in claim 7 to 9 is any；
The watermark of anti-forge paper as described in claim 10 to 12 is any identifies cloud server.
14. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes any side of claim 1 to 6 when executing the computer program
Method.
15. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has perform claim
It is required that the computer program of 1 to 6 any the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811492285.XA CN109859372A (en) | 2018-12-07 | 2018-12-07 | Watermark recognition methods, device, cloud server and the system of anti-forge paper |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811492285.XA CN109859372A (en) | 2018-12-07 | 2018-12-07 | Watermark recognition methods, device, cloud server and the system of anti-forge paper |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109859372A true CN109859372A (en) | 2019-06-07 |
Family
ID=66890689
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811492285.XA Pending CN109859372A (en) | 2018-12-07 | 2018-12-07 | Watermark recognition methods, device, cloud server and the system of anti-forge paper |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109859372A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992578A (en) * | 2019-12-04 | 2020-04-10 | 华南理工大学 | Deep learning target detection method for comprehensive identification of bills with multiple light sources |
| CN111046899A (en) * | 2019-10-09 | 2020-04-21 | 京东数字科技控股有限公司 | Method, device and equipment for identifying authenticity of identity card and storage medium |
| CN111325119A (en) * | 2020-02-09 | 2020-06-23 | 华瑞新智科技（北京）有限公司 | Video monitoring method and system for safety production |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1521685A (en) * | 2003-01-27 | 2004-08-18 | 艾斯恩科技股份有限公司 | True and counterfeit note identifying machine and method for identification |
| CN106096668A (en) * | 2016-08-18 | 2016-11-09 | 携程计算机技术（上海）有限公司 | The recognition methods of watermarked image and the system of identification |
| CN107633413A (en) * | 2017-10-17 | 2018-01-26 | 深圳市裕同包装科技股份有限公司 | A kind of anti-fake traceability system and method |
| CN107784730A (en) * | 2017-09-14 | 2018-03-09 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note and device |
| CN108257095A (en) * | 2016-12-07 | 2018-07-06 | 法国艾德米亚身份与安全公司 | For handling the system of image |
-
2018
- 2018-12-07 CN CN201811492285.XA patent/CN109859372A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1521685A (en) * | 2003-01-27 | 2004-08-18 | 艾斯恩科技股份有限公司 | True and counterfeit note identifying machine and method for identification |
| CN106096668A (en) * | 2016-08-18 | 2016-11-09 | 携程计算机技术（上海）有限公司 | The recognition methods of watermarked image and the system of identification |
| CN108257095A (en) * | 2016-12-07 | 2018-07-06 | 法国艾德米亚身份与安全公司 | For handling the system of image |
| CN107784730A (en) * | 2017-09-14 | 2018-03-09 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note and device |
| CN107633413A (en) * | 2017-10-17 | 2018-01-26 | 深圳市裕同包装科技股份有限公司 | A kind of anti-fake traceability system and method |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111046899A (en) * | 2019-10-09 | 2020-04-21 | 京东数字科技控股有限公司 | Method, device and equipment for identifying authenticity of identity card and storage medium |
| CN111046899B (en) * | 2019-10-09 | 2023-12-08 | 京东科技控股股份有限公司 | Identification card authenticity identification method, device, equipment and storage medium |
| CN110992578A (en) * | 2019-12-04 | 2020-04-10 | 华南理工大学 | Deep learning target detection method for comprehensive identification of bills with multiple light sources |
| CN111325119A (en) * | 2020-02-09 | 2020-06-23 | 华瑞新智科技（北京）有限公司 | Video monitoring method and system for safety production |
| CN111325119B (en) * | 2020-02-09 | 2023-10-20 | 华瑞新智科技（北京）有限公司 | Video monitoring method and system for safe production |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107423700B (en) | Method and device for verifying testimony of a witness | |
| CN104239858B (en) | A kind of method and apparatus of face characteristic checking | |
| CN109859372A (en) | Watermark recognition methods, device, cloud server and the system of anti-forge paper | |
| CN109034159A (en) | image information extracting method and device | |
| CN108875722A (en) | Character recognition and identification model training method, device and system and storage medium | |
| CN109800320B (en) | Image processing method, device and computer readable storage medium | |
| CN109255299A (en) | Identity identifying method and device, electronic equipment and storage medium | |
| Yadav et al. | An automatic recognition of fake Indian paper currency note using MATLAB | |
| CN108154105A (en) | Aquatic organism detects and recognition methods, device, server and terminal device | |
| CN108229591A (en) | Neural network adaptive training method and apparatus, equipment, program and storage medium | |
| CN106886774A (en) | The method and apparatus for recognizing ID card information | |
| CN108171127A (en) | A kind of invoice automatic identifying method based on deep learning | |
| CN108805005A (en) | Auth method and device, electronic equipment, computer program and storage medium | |
| CN104504579B (en) | A kind of signal auditing method and device | |
| CN108647595A (en) | Vehicle recognition methods again based on more attribute depth characteristics | |
| CN107038794B (en) | Method, device and equipment for identifying authenticity of paper money and storage medium | |
| CN113610540A (en) | River crab anti-counterfeiting tracing method and system | |
| CN110070115A (en) | A kind of single pixel attack sample generating method, device, equipment and storage medium | |
| CN105741404B (en) | The discrimination method of bill, device and system | |
| CN109740417A (en) | Invoice type recognition methods, device, storage medium and computer equipment | |
| CN110555830A (en) | Deep neural network skin detection method based on deep Labv3+ | |
| CN109598671A (en) | Image generating method, device, equipment and medium | |
| CN108846330A (en) | A kind of paper calligraphy and painting micro-image intelligent identifying system and recognition methods | |
| CN106898078B (en) | Port currency version identification method and device | |
| CN109086765A (en) | Licence plate recognition method, device, medium, server and automobile data recorder |
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: 20190607 |
|
| RJ01 | Rejection of invention patent application after publication |