CN110147787A - Bank's card number automatic identifying method and system based on deep learning - Google Patents
Bank's card number automatic identifying method and system based on deep learning Download PDFInfo
- Publication number
- CN110147787A CN110147787A CN201910409948.5A CN201910409948A CN110147787A CN 110147787 A CN110147787 A CN 110147787A CN 201910409948 A CN201910409948 A CN 201910409948A CN 110147787 A CN110147787 A CN 110147787A
- Authority
- CN
- China
- Prior art keywords
- bank
- card number
- text
- card
- picture
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/146—Aligning or centring of the image pick-up or image-field
- G06V30/1475—Inclination or skew detection or correction of characters or of image to be recognised
- G06V30/1478—Inclination or skew detection or correction of characters or of image to be recognised of characters or characters lines
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Character Discrimination (AREA)
Abstract
The invention discloses a kind of bank's card number automatic identifying method and system based on deep learning, wherein should bank's card number automatic identifying method based on deep learning include: the bank card picture for obtaining and uploading；Processing of becoming a full member is carried out to the bank card picture of upload；Text detection is carried out to the bank card picture of upload, to obtain the image of bank's card number field；Text region is carried out to the image of bank's card number field, to obtain bank's card number text；Export bank's card number text.Technical solution of the present invention can automatic identification bank card number, can guarantee bank's card number identification accuracy and high efficiency, be particularly adapted to the typing of bank's card number information.
Description
Technical field
The present invention relates to field of information processing more particularly to a kind of card number automatic identification sides, bank based on deep learning
Method, system, computer equipment and storage medium.
Background technique
As bank card is more and more wider using crowd, trade company to the manual entries of a large amount of bank's card number pictures of user at
This is also gradually increased.Currently, most bank's card number picture passes through bank card character identification system.However traditional bank
Cavan word recognition system is that the image district to match with its template picture is searched for that is, in figure based on template matching algorithm mostly
Domain.The recognizer of the identifying system is time-consuming high, and, rotation complicated to background, picture not of uniform size cannot be given well
Recognition effect.
In view of this, it is necessary to which current bank card character recognition method is further improved in proposition.
Summary of the invention
To solve an above-mentioned at least technical problem, the main object of the present invention is to provide a kind of bank based on deep learning
Card number automatic identifying method, system, computer equipment and storage medium.
To achieve the above object, first technical solution that the present invention uses are as follows: a kind of silver based on deep learning is provided
Row card number automatic identifying method, comprising:
Obtain the bank card picture uploaded；
Processing of becoming a full member is carried out to the bank card picture of upload；
Text detection is carried out to the bank card picture of upload, to obtain the image of bank's card number field；
Text region is carried out to the image of bank's card number field, to obtain bank's card number text；
Export bank's card number text.
Wherein, the bank card picture of described pair of upload carries out processing of becoming a full member, comprising:
Unionpay's mark in the bank card picture of upload is detected according to target detection model, if it is detected that bank card
Unionpay's mark in picture, then perform the next step rapid；If the Unionpay's mark being not detected in bank card picture, to bank card
Picture carries out processing of becoming a full member.
Wherein, described that Unionpay's mark in the bank card picture of upload is detected according to target detection model, also wrap
It includes:
Training objective detection model, specifically,
Mark several bank cards with Unionpay's mark as training set；
Cascade classifier is trained according to the training sample of label, to obtain target detection model.
Wherein, the bank card picture of described pair of upload carries out text detection, specifically:
According to the text detection model based on deep neural network training in server to the bank card picture of upload into
Row text detection.
Wherein, bank of the text detection model based on deep neural network training according in server to upload
Card picture carries out text detection, further includes:
The text detection model of training deep neural network training, specifically:
Image enhancement processing is carried out to several bank card pictures with bank's card number position mark；
Detection training is carried out according to text box of the improved full convolutional neural networks to bank card picture, to obtain depth mind
Text detection model through network training.
Wherein, the image to bank's card number field carries out Text region, to obtain bank's card number text, specifically:
According to the Text region model based on deep neural network training in server to the image of bank's card number field
Text region is carried out, to obtain bank's card number text.
Wherein, the Text region model based on deep neural network training according in server is to bank's card number region
The image in domain carries out Text region, further includes:
The Text region model of training deep neural network training, specifically:
Image enhancement processing is carried out to several bank's card number administrative division map pieces with card number text point mark；
Chinese character is carried out to bank's card number text box of input according to full convolutional neural networks and timing Classification Neural
Number identification training, to obtain Text region model.
To achieve the above object, second technical solution that the present invention uses are as follows: a kind of silver based on deep learning is provided
Row card number automatic recognition system, comprising:
Module is obtained, for obtaining the bank card picture uploaded；
Correction module, for carrying out processing of becoming a full member to the bank card picture of upload；
Text detection module, for carrying out text detection to the bank card picture of upload, to obtain bank's card number field
Image；
Text region module carries out Text region for the image to bank's card number field, to obtain bank's card number text；
Output module, for exporting bank's card number text.
To achieve the above object, the third technical solution that the present invention uses are as follows: a kind of computer equipment is provided, including is deposited
Reservoir, processor and storage on a memory and the computer program that can run on a processor, described in the processor execution
The step of above method is realized when computer program.
To achieve the above object, the 4th technical solution that the present invention uses are as follows: a kind of computer-readable storage medium is provided
The step of matter is stored thereon with computer program, and the computer program realizes above-mentioned method when being executed by processor.
Technical solution of the present invention first using the bank card picture uploaded is obtained, then indicates target detection mould using Unionpay
Type carries out processing of becoming a full member to the bank card picture of upload, and then carries out text detection to the bank card picture of upload, to obtain silver
The image of row card number field, and Text region is carried out to the image of bank's card number field, to obtain bank's card number text, finally
Export bank's card number text.Through the above steps, technical solution of the present invention can automatic identification bank card number, can guarantee silver
The accuracy and high efficiency of row card number identification, the typing especially suitable for bank's card number information.
Detailed description of the invention
Fig. 1 is the method flow diagram of bank card number automatic identifying method of the one embodiment of the invention based on deep learning；
Fig. 2 is the block diagram of bank card number automatic recognition system of the one embodiment of the invention based on deep learning；
Fig. 3 is the internal structure chart of one embodiment of the invention computer equipment.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiment is only a part of the embodiments of the present invention, instead of all the embodiments.Base
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts it is all its
His embodiment, shall fall within the protection scope of the present invention.
It is to be appreciated that the description of " first ", " second " involved in the present invention etc. is used for description purposes only, and should not be understood as
Its relative importance of indication or suggestion or the quantity for implicitly indicating indicated technical characteristic.Define as a result, " first ",
The feature of " second " can explicitly or implicitly include at least one of the features.In addition, the technical side between each embodiment
Case can be combined with each other, but must be based on can be realized by those of ordinary skill in the art, when the combination of technical solution
Conflicting or cannot achieve when occur will be understood that the combination of this technical solution is not present, also not the present invention claims guarantor
Within the scope of shield.
Fig. 1 is please referred to, Fig. 1 is the method for bank card number automatic identifying method of the one embodiment of the invention based on deep learning
Flow chart.In embodiments of the present invention, it is somebody's turn to do bank's card number automatic identifying method based on deep learning, comprising:
Step S10, the bank card picture uploaded is obtained；
Step S20, processing of becoming a full member is carried out to the bank card picture of upload；
Step S30, text detection is carried out to the bank card picture of upload, to obtain the image of bank's card number field；
Step S40, Text region is carried out to the image of bank's card number field, to obtain bank's card number text；
Step S50, bank's card number text is exported.
In the present embodiment, when obtaining the bank card picture of user terminal uploads, which is printed on Unionpay's mark
Side picture.In view of the shooting angle of the bank card picture of upload is different, lead to bank's card number and Unionpay mark position
Difference, in the present solution, needing to carry out processing of becoming a full member to bank card picture.Bank card picture after testing can pass through server
Text information thereon is continued to test, after text information detection confirmation, bank card area image is returned to by server, and pass through
Server carries out Text region to bank card area image and finally returns to bank's card number text to obtain bank's card number text.
Technical solution of the present invention first using the bank card picture uploaded is obtained, then carries out the bank card picture of upload
Become a full member processing, and then text detection is carried out to the bank card picture of upload, to obtain the image of bank's card number field, and to silver
The image of row card number field carries out Text region, to obtain bank's card number text, finally exports bank's card number text.By above-mentioned
Step, technical solution of the present invention can automatic identification bank card number, can guarantee bank's card number identification accuracy and efficiently
Property, the typing especially suitable for bank's card number information.
In a specific embodiment, the bank card picture of described pair of upload carries out processing of becoming a full member, comprising: is examined according to target
Model is surveyed to detect Unionpay's mark in the bank card picture of upload, if it is detected that the Unionpay in bank card picture identifies,
It then performs the next step rapid；If the Unionpay's mark being not detected in bank card picture, carries out processing of becoming a full member to bank card picture.
In processing of becoming a full member, first to bank card picture rotation certain angle, this programme is preferably 90 °, then detects bank
Card picture indicates with the presence or absence of Unionpay, if otherwise continuing to rotate above-mentioned angle, until finding Unionpay's mark.For what is detected
Unionpay's mark, then carry out text detection to bank card picture.Unionpay's mark is all not detected to having turned 360 degree, then maintains
Original image input carries out text detection.
In a specific embodiment, described that the Unionpay in the bank card picture of upload is identified according to target detection model
It is detected, further includes:
Training objective detection model, specifically,
Mark several bank cards with Unionpay's mark as training set；
Cascade classifier is trained according to the training sample of label, to obtain target detection model.
In the present embodiment, to Unionpay mark target detection model training, specifically:
1. a large amount of bank card pictures with Unionpay position mark are done image enhancement processing to Unionpay's sign image:
A) Unionpay's mark is carried out plus makes an uproar (white Gaussian noise)；
B) Unionpay is indicated and carries out Sloped rotating (- 3 ° to 3 °)；
C) adjustment Unionpay indicates the accounting (scaling) in bank card picture；
D) Unionpay is indicated and carries out at least one of above processing modes such as Fuzzy Processing (smoothing filters).
2. these Unionpay's sign images after treatment are replaced the more clear Unionpay mark on original bank card
Image, the accuracy to increase the diversity of Unionpay's mark target detection, with target detection.
3. being trained finally by cascade classifier to above-mentioned sample, target detection model is obtained.Through the above steps
The target detection model trained, detection speed is fast, precision is high, rapidly can be turned picture when picture is loaded into
Just, it can effectively avoid the problem that picture detects positional fault.
In a specific embodiment, the bank card picture of described pair of upload carries out text detection, specifically:
According to the text detection model based on deep neural network training in server to the bank card picture of upload into
Row text detection.
Specifically, silver of the text detection model based on deep neural network training according in server to upload
Row card picture carries out text detection, further includes:
The text detection model of training deep neural network training, specifically:
Image enhancement processing is carried out to several bank card pictures with bank's card number position mark；
Detection training is carried out according to text box of the improved full convolutional neural networks to bank card picture, to obtain depth mind
Text detection model through network training.
In the present embodiment, the image enhancement processing, specifically: samples pictures are carried out plus made an uproar using 50% probability is (high
This white noise), inclination (- 3 ° to 3 °), scaling (change picture size), at least one in the processing modes such as fuzzy (smoothing filter)
Kind, it so, it is possible the diversity of abundant sample；Secondly, being improved to traditional holostrome convolutional neural networks structure.The improvement
Include: the ratio of width to height of 1. adjustment text detection regional frames, can more accurately be suitable for bank card text detection model；2.
Multiple detection zones are generated for each pixel, and are returned repeatedly to authentic signature position, make it constantly close to true
Mark position；3. changing the convolution filter size and convolutional network depth of full convolutional neural networks, it is made to be more suitable for text inspection
It surveys；4. our neural network model can detecte inclined bank because having inclined sample in training sample
Card number text box, and adjusted text box to level according to tilt angle, conducive to the identification of Text region module；Finally, for
The neural network is trained end to end, obtains text detection model.
In a specific embodiment, the image to bank's card number field carries out Text region, to obtain bank card
Number text, specifically:
According to the Text region model based on deep neural network training in server to the image of bank's card number field
Text region is carried out, to obtain bank's card number text.
Specifically, the Text region model based on deep neural network training according in server is to bank's card number
The image in region carries out Text region, further includes:
The Text region model of training deep neural network training, specifically:
Image enhancement processing is carried out to several bank's card number administrative division map pieces with card number text point mark；
Chinese character is carried out to bank's card number text box of input according to full convolutional neural networks and timing Classification Neural
Number identification training, to obtain Text region model.
In the present embodiment, the image enhancement processing, the number of samples pictures is added including the probability using 50%,
It at least one of the processing modes such as deletes, tilt, obscuring, the diversity of sample can be enriched；Secondly, using full convolutional Neural
The structure of network added-time sequence Classification Neural (CTC) carries out letter symbol identification to bank's card number text box of input
Training；Finally, obtained Text region model, can learn well different colours, the digital picture with interference, distortion
Corresponding feature is practised, and carries out accurate Text region.
Referring to figure 2., Fig. 2 is the module of bank card number automatic recognition system of the one embodiment of the invention based on deep learning
Block diagram.In the embodiment of the present invention, it is somebody's turn to do bank's card number automatic recognition system based on deep learning, comprising:
Module 10 is obtained, for obtaining the bank card picture uploaded；
Correction module 20, for carrying out processing of becoming a full member to the bank card picture of upload；
Text detection module 30, for carrying out text detection to the bank card picture of upload, to obtain bank's card number field
Image；
Text region module 40 carries out Text region for the image to bank's card number field, to obtain bank's card number text
Word；
Output module 50, for exporting bank's card number text.
In the present embodiment, this system is by obtaining module 10, the bank card picture of available user terminal uploads, the silver
Row card picture is printed on the picture of the side of Unionpay's mark.In view of the shooting angle of the bank card picture of upload is different, lead to silver
Row card number and Unionpay mark position are different, in the present solution, can ajust the position of input picture by changing into module 20.Through
It crosses text information of the bank card of detection by the detection of text detection module 30 thereon and obtains silver after text information detection confirmation
Row card area image.The bank card area image carries out Text region to bank card area image by Text region module 40,
To obtain bank's card number text, finally by output module 50, bank's card number text is exported.
Specifically, text detection module 30 and Text region module 40 are realized by server.The server uses
Deep learning service arrangement scheme, specifically: using Tensorflow-Serving is trained text detection, identification model
Infrastructure service frame is provided, and Tensorflow-Serving service is packaged into a Docker mirror image；It will be packed
Docker mirror image is placed in the server for needing to provide service, and loads corresponding text detection, identification model, and what is used is light
The Web application framework Flask of magnitude develops api interface, and is externally provided by high performance Gunicorn http server
Service.Its advantage is as follows: 1. dynamically heat can update model algorithm using Tensorflow-Serving, not need to stop clothes
Business；2. using Tensorflow-Serving batch packing processing can be carried out to the picture that the short time uploads simultaneously, and return
Recognition result improves service performance；3. service is packaged in a Docker mirror image, the transplanting of service can be convenient, and
The container environment being relatively isolated improves the compatibility of deployment, accomplishes the effect of lightweight, rapid deployment；4. using Gunicon
Method of service, the quantity of process (workers), thread can be flexibly arranged according to the performance of server, recommendation
Workers quantity is current CPU several * 2+1.And have the function of can customize log content, facilitate inquiry and export；5.
All models all use image processor (GPU) operation to calculate, and increase the parallel speed of model.Further, text
When detection module 30 carries out text detection, picture acquired in external detection port is sent into and is wrapped up by Docker by Gunicorn
Tensorflow-Serving in, Tensorflow-Serving is according to the corresponding relationship of port and model name, by picture
It is sent into and is based on carrying out text detection in the trained text detection model of deep neural network.Text region module 40 carries out text
When identification, Gunicorn is wrapped up the feeding of bank's card number area image acquired in external identification port by Docker
In Tensorflow-Serving.Tensorflow-Serving is according to the corresponding relationship of port and model name, by bank card
Number area image is sent into based on carrying out Text region in the trained Text region model of deep neural network.
Referring to figure 3., Fig. 3 is the internal structure chart of one embodiment of the invention computer equipment.In one embodiment, the meter
Calculating machine equipment includes processor, memory and the network interface connected by system bus.Wherein, the processing of the computer equipment
Device is for providing calculating and control ability.The memory of the computer equipment includes non-volatile memory medium, built-in storage.It should
Non-volatile memory medium is stored with operating system, computer program and database.The built-in storage is non-volatile memories Jie
The operation of operating system and computer program in matter provides environment.The network interface of the computer equipment is used for and external end
End passes through network connection communication.To realize a kind of bank's card number based on deep learning when the computer program is executed by processor
Automatic identifying method.
It will be understood by those skilled in the art that structure shown in Fig. 3, 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 is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor are realized when executing computer program in above each embodiment of the method
The step of.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
The step in above each embodiment of the method is realized when machine program is executed by processor.
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..
The above description is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all at this
Under the inventive concept of invention, using equivalent structure transformation made by description of the invention and accompanying drawing content, or directly/use indirectly
It is included in other related technical areas in scope of patent protection of the invention.
Claims (10)
1. a kind of bank's card number automatic identifying method based on deep learning, which is characterized in that the silver based on deep learning
Row card number automatic identifying method includes:
Obtain the bank card picture uploaded；
Processing of becoming a full member is carried out to the bank card picture of upload；
Text detection is carried out to the bank card picture of upload, to obtain the image of bank's card number field；
Text region is carried out to the image of bank's card number field, to obtain bank's card number text；
Export bank's card number text.
2. bank's card number automatic identifying method based on deep learning as described in claim 1, which is characterized in that on described pair
The bank card picture of biography carries out processing of becoming a full member, comprising:
Unionpay's mark in the bank card picture of upload is detected according to target detection model, if it is detected that bank card picture
In Unionpay's mark, then perform the next step rapid；If the Unionpay's mark being not detected in bank card picture, to bank card picture
Carry out processing of becoming a full member.
3. bank's card number automatic identifying method based on deep learning as claimed in claim 2, which is characterized in that the basis
Target detection model detects Unionpay's mark in the bank card picture of upload, further includes:
Training objective detection model, specifically,
Mark several bank cards with Unionpay's mark as training set；
Cascade classifier is trained according to the training sample of label, to obtain target detection model.
4. bank's card number automatic identifying method based on deep learning as described in claim 1, which is characterized in that on described pair
The bank card picture of biography carries out text detection, specifically:
Text is carried out to the bank card picture of upload according to the text detection model based on deep neural network training in server
Word detection.
5. bank's card number automatic identifying method based on deep learning as claimed in claim 4, which is characterized in that the basis
The text detection model based on deep neural network training in server carries out text detection to the bank card picture of upload, also
Include:
The text detection model of training deep neural network training, specifically:
Image enhancement processing is carried out to several bank card pictures with bank's card number position mark；
Detection training is carried out according to text box of the improved full convolutional neural networks to bank card picture, to obtain depth nerve net
The text detection model of network training.
6. bank's card number automatic identifying method based on deep learning as described in claim 1, which is characterized in that described to silver
The image of row card number field carries out Text region, to obtain bank's card number text, specifically:
The image of bank's card number field is carried out according to the Text region model based on deep neural network training in server
Text region, to obtain bank's card number text.
7. bank's card number automatic identifying method based on deep learning as claimed in claim 6, which is characterized in that the basis
The Text region model based on deep neural network training in server carries out Text region to the image of bank's card number field,
Further include:
The Text region model of training deep neural network training, specifically:
Image enhancement processing is carried out to several bank's card number administrative division map pieces with card number text point mark；
Letter symbol knowledge is carried out to bank's card number text box of input according to full convolutional neural networks and timing Classification Neural
Other training, to obtain Text region model.
8. a kind of bank's card number automatic recognition system based on deep learning, which is characterized in that the silver based on deep learning
Row card number automatic recognition system includes:
Module is obtained, for obtaining the bank card picture uploaded；
Correction module, for carrying out processing of becoming a full member to the bank card picture of upload；
Text detection module, for carrying out text detection to the bank card picture of upload, to obtain the image of bank's card number field；
Text region module carries out Text region for the image to bank's card number field, to obtain bank's card number text；
Output module, for exporting bank's card number text.
9. 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 one of claims 1 to 7 institute when executing the computer program
The step of stating method.
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 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910409948.5A CN110147787A (en) | 2019-05-16 | 2019-05-16 | Bank's card number automatic identifying method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910409948.5A CN110147787A (en) | 2019-05-16 | 2019-05-16 | Bank's card number automatic identifying method and system based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110147787A true CN110147787A (en) | 2019-08-20 |
Family
ID=67595625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910409948.5A Pending CN110147787A (en) | 2019-05-16 | 2019-05-16 | Bank's card number automatic identifying method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110147787A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110751090A (en) * | 2019-10-18 | 2020-02-04 | 宁波博登智能科技有限责任公司 | Three-dimensional point cloud labeling method and device and electronic equipment |
| CN110909809A (en) * | 2019-11-27 | 2020-03-24 | 上海智臻智能网络科技股份有限公司 | Card image identification method based on deep learning |
| CN111027450A (en) * | 2019-12-04 | 2020-04-17 | 深圳市新国都金服技术有限公司 | Bank card information identification method and device, computer equipment and storage medium |
| CN113569850A (en) * | 2021-09-23 | 2021-10-29 | 湖南星汉数智科技有限公司 | Bank card number identification method and device, computer equipment and storage medium |
| CN113963339A (en) * | 2021-09-02 | 2022-01-21 | 泰康保险集团股份有限公司 | Information extraction method and device |
| CN114049646A (en) * | 2021-11-29 | 2022-02-15 | 中国平安人寿保险股份有限公司 | Bank card identification method and device, computer equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7433498B2 (en) * | 2003-09-09 | 2008-10-07 | Fujifilm Corporation | Apparatus, method and program for generating photo card data |
| CN107742120A (en) * | 2017-10-17 | 2018-02-27 | 北京小米移动软件有限公司 | The recognition methods of bank card number and device |
| CN109242047A (en) * | 2018-10-17 | 2019-01-18 | 福州大学 | Bank card number detection and recognition methods based on K-means++ cluster and residual error network class |
| CN104966097B (en) * | 2015-06-12 | 2019-01-18 | 成都数联铭品科技有限公司 | A kind of complex script recognition methods based on deep learning |
| CN109447080A (en) * | 2018-11-12 | 2019-03-08 | 北京奇艺世纪科技有限公司 | A kind of character identifying method and device |
-
2019
- 2019-05-16 CN CN201910409948.5A patent/CN110147787A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7433498B2 (en) * | 2003-09-09 | 2008-10-07 | Fujifilm Corporation | Apparatus, method and program for generating photo card data |
| CN104966097B (en) * | 2015-06-12 | 2019-01-18 | 成都数联铭品科技有限公司 | A kind of complex script recognition methods based on deep learning |
| CN107742120A (en) * | 2017-10-17 | 2018-02-27 | 北京小米移动软件有限公司 | The recognition methods of bank card number and device |
| CN109242047A (en) * | 2018-10-17 | 2019-01-18 | 福州大学 | Bank card number detection and recognition methods based on K-means++ cluster and residual error network class |
| CN109447080A (en) * | 2018-11-12 | 2019-03-08 | 北京奇艺世纪科技有限公司 | A kind of character identifying method and device |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110751090A (en) * | 2019-10-18 | 2020-02-04 | 宁波博登智能科技有限责任公司 | Three-dimensional point cloud labeling method and device and electronic equipment |
| CN110751090B (en) * | 2019-10-18 | 2022-09-20 | 宁波博登智能科技有限公司 | Three-dimensional point cloud labeling method and device and electronic equipment |
| CN110909809A (en) * | 2019-11-27 | 2020-03-24 | 上海智臻智能网络科技股份有限公司 | Card image identification method based on deep learning |
| CN110909809B (en) * | 2019-11-27 | 2023-09-05 | 上海智臻智能网络科技股份有限公司 | Card image recognition method based on deep learning |
| CN111027450A (en) * | 2019-12-04 | 2020-04-17 | 深圳市新国都金服技术有限公司 | Bank card information identification method and device, computer equipment and storage medium |
| CN113963339A (en) * | 2021-09-02 | 2022-01-21 | 泰康保险集团股份有限公司 | Information extraction method and device |
| CN113569850A (en) * | 2021-09-23 | 2021-10-29 | 湖南星汉数智科技有限公司 | Bank card number identification method and device, computer equipment and storage medium |
| CN114049646A (en) * | 2021-11-29 | 2022-02-15 | 中国平安人寿保险股份有限公司 | Bank card identification method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492643B (en) | Certificate identification method and device based on OCR, computer equipment and storage medium | |
| CN110147787A (en) | Bank's card number automatic identifying method and system based on deep learning | |
| CN109583445B (en) | Text image correction processing method, device, equipment and storage medium | |
| CN110059689B (en) | Sample set construction method, device, computer equipment and storage medium | |
| CN108960062A (en) | Correct method, apparatus, computer equipment and the storage medium of invoice image | |
| US10943107B2 (en) | Simulating image capture | |
| CN109255300B (en) | Bill information extraction method, bill information extraction device, computer equipment and storage medium | |
| CN109766778A (en) | Invoice information input method, device, equipment and storage medium based on OCR technique | |
| WO2021143088A1 (en) | Synchronous check method and apparatus for multiple certificate types, and computer device and storage medium | |
| CN110135346A (en) | Identity card automatic identifying method and system based on deep learning | |
| CN112085029A (en) | Invoice identification method, equipment and medium | |
| CN110516663A (en) | Test method, device, computer equipment and the storage medium of OCR recognition accuracy | |
| CN111931783A (en) | Training sample generation method, machine-readable code identification method and device | |
| CN112464925A (en) | Mobile terminal account opening data bank information automatic extraction method based on machine learning | |
| CN113111880B (en) | Certificate image correction method, device, electronic equipment and storage medium | |
| CN112861861A (en) | Method and device for identifying nixie tube text and electronic equipment | |
| CN115223183A (en) | Information extraction method and device and electronic equipment | |
| CN111553431A (en) | Picture definition detection method and device, computer equipment and storage medium | |
| CN111783541A (en) | Text recognition method and device | |
| CN113806613B (en) | Training image set generation method, training image set generation device, computer equipment and storage medium | |
| CN107122785B (en) | Text recognition model establishing method and device | |
| Pangestu et al. | Histogram equalization implementation in the preprocessing phase on optical character recognition | |
| CN105913024B (en) | The Android mobile phone endpoint detection methods of resistance Replay Attack based on LAP operator | |
| CN116524508A (en) | Correction method and device for table type image, storage medium and computer equipment | |
| CN114821618A (en) | Analysis method for OFD reading software display effect |
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: 20190820 |
|
| RJ01 | Rejection of invention patent application after publication |