CN110135431A - The automatic identifying method and system of business license - Google Patents
The automatic identifying method and system of business license Download PDFInfo
- Publication number
- CN110135431A CN110135431A CN201910409918.4A CN201910409918A CN110135431A CN 110135431 A CN110135431 A CN 110135431A CN 201910409918 A CN201910409918 A CN 201910409918A CN 110135431 A CN110135431 A CN 110135431A
- Authority
- CN
- China
- Prior art keywords
- text
- business license
- identification
- digital
- digital alphabet
- 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
- 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
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- 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
Abstract
The invention discloses a kind of automatic identifying method of business license and systems, wherein this method comprises: detect to the text in business license picture and determining all text regions when receiving business license picture to be identified；Text region is carried out to all text regions, obtains the Text region result of all fields；The character area of the unified social credibility code or number of registration in Text region result is selected according to specified conditions；To the character area of unified social credibility code or number of registration, digital alphabet identification is carried out using special digital Letter identification network, obtains digital alphabet data；The Chinese Fields data of identification and digital alphabet data are merged, obtain business license recognition result.Technical solution of the present invention can automatically identify complete business license field, and can be improved the accuracy rate and recognition efficiency of business license identification.
Description
Technical field
The present invention relates to image processing techniques more particularly to a kind of automatic identifying methods of business license, system, computer
Equipment and storage medium.
Background technique
With the continuous development of image processing techniques, character recognition technology has been applied to identify various certificates.Existing skill
Character recognition technology in art based on deep learning is mostly identified just for character a kind of in text and number, if knowing simultaneously
Other text and number often will appear leakage identification, reduce the accuracy rate problem of business license identification.
In view of this, it is necessary to which current business license recognition methods 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 automatic identification side of industry license
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 automatic knowledge of business license is provided
Other method, comprising:
When receiving business license picture to be identified, the text in business license picture detect and determines institute
There is text region；
Text region is carried out to all text regions, obtains the Text region result of all fields；
The character area of the unified social credibility code or number of registration in Text region result is selected according to specified conditions；
To the character area of unified social credibility code or number of registration, number is carried out using special digital Letter identification network
Letter identification obtains digital alphabet data；
The Chinese Fields data of identification and digital alphabet data are merged, obtain business license recognition result.
Wherein, described pair of all text regions carry out Text region, specifically include:
All text regions are cut, textbox is obtained；
All fields in textbox are identified according to Text region network.
Wherein, described that digital alphabet identification is carried out to text region using digital alphabet identification network, it specifically includes:
Number or alphabetical starting position are found out in text region according to CTC algorithm；
The text region cut is cut again according to number or alphabetical starting position, obtains digital alphabet
Textbox；
The digital alphabet in digital alphabetic literal frame is identified using digital alphabet identification network.
Wherein, the number of characters of the judgement digital alphabet, further includes:
Judge the number of characters of digital alphabet and the size of setting word threshold,
Digital alphabet number of characters be greater than setting word threshold when, continue determine digital alphabet where literal line in be
It is no containing specified field keys, the field keys include unified social credibility code or number of registration；
When in the literal line where digital alphabet containing specified field keys, continue according to unified social credibility generation
Code coding rule or number of registration establishment rules verify original recognition result,
It is obstructed out-of-date verifying, this character area is judged as that unified society's letter is contained in target area, the target area
With code or the character area of number of registration；
If this character area is otherwise determined as nontarget area.
Wherein, described to merge the Chinese Fields data of identification and digital alphabet data, show that business license identifies
As a result after, further includes:
All recognition results are cleaned, the business for obtaining standard executes field.
To achieve the above object, second technical solution that the present invention uses are as follows: a kind of automatic knowledge of business license is provided
Other system, comprising:
Text detection module, for when receiving business license picture to be identified, to the text in business license picture
Word detect and determines all text regions；
Text region module, for carrying out Text region to all text regions, the text for obtaining all fields is known
Other result；
Judgment module, for selecting unified social credibility code or number of registration in Text region result according to specified conditions
Character area；
Digital identification module, for the character area to unified social credibility code or number of registration, using special digital word
Mother's identification network carries out digital alphabet identification, obtains digital alphabet data；
Cleaning module obtains business license for merging the Chinese Fields data of identification and digital alphabet data
Recognition result.
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
Matter is stored thereon with computer program, which is characterized in that the computer program realizes above-mentioned method when being executed by processor
The step of.
Technical solution of the present invention is used when receiving business license picture to be identified, first in business license picture
Text detected, all text regions are determined by testing result, then to text region carry out for the first time
Identification, i.e. Text region, obtain the Text region result of all fields according to Text region；Text is selected further according to specified conditions
The character area of unified social credibility code or number of registration in recognition result；Then to unified social credibility code or number of registration
Text region carries out second and identifies, i.e., digital alphabet identifies, obtains digital alphabet number according to digital alphabet recognition result
According to；The Chinese Fields data of identification and digital alphabet data are merged, obtain business license recognition result, can be known automatically
Other business license information, can be improved recognition efficiency.In addition, meeting specific item to business license using digital alphabet identification network
The unified social credibility code or number of registration character area of part are further identified, can be improved the identification of business license entirety
Accuracy.
Detailed description of the invention
Fig. 1 is the method flow diagram of the automatic identifying method of one embodiment of the invention business license；
Fig. 2 is the block diagram of the automatic recognition system of one embodiment of the invention business license；
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 flow diagram of the automatic identifying method of one embodiment of the invention business license.At this
In inventive embodiments, the automatic identifying method of the business license, comprising:
Step S10, when receiving business license picture to be identified, the text in business license picture is detected
And determine all text regions；
Step S20, Text region is carried out to all text regions, obtains the Text region result of all fields；
Step S30, the text of the unified social credibility code or number of registration in Text region result is selected according to specified conditions
Block domain；
Step S40, to the character area of unified social credibility code or number of registration, using special digital Letter identification network
Digital alphabet identification is carried out, digital alphabet data are obtained；
Step S50, the Chinese Fields data of identification and digital alphabet data are merged, obtains business license identification knot
Fruit.
In the present embodiment, automatic identification business license information can be realized by above-mentioned method.Specifically, receiving
When the business license photo or picture to be identified of input, first passes through text detection network and detect all texts in picture, and
Determine all text regions.Above-mentioned all texts include Chinese character and digital alphabet.Text region is carried out
It identifies for the first time, Text region is carried out to all text regions using trained network.Text is selected according to specified conditions
The character area of unified social credibility code or number of registration in recognition result.The specified conditions need to meet simultaneously three items
Part judges the number of characters of digital alphabet and the size of setting word threshold, is greater than setting character threshold in the number of characters of digital alphabet
When value, whether continue to determine in the literal line where digital alphabet containing specified field keys, the field keys packet
Contain unified social credibility code or number of registration；When in the literal line where digital alphabet containing specified field keys,
Continue to verify original recognition result according to unified social credibility code coding rule or number of registration establishment rules, verify
It is obstructed out-of-date, this character area is judged as that unified social credibility code or number of registration are contained in target area, the target area
Character area；If this character area is otherwise determined as nontarget area.It need to be noted that, one not in three conditions
When meeting, this character area is determined as nontarget area.Above-mentioned unified social credibility code coding rule be specially " legal person and
Its hetero-organization unifies social credibility code coding rule ", above-mentioned number of registration establishment rules are specially " industrial and commercial administration market
Main body number of registration establishment rules ".Then to the character area of unified social credibility code or number of registration, using special digital letter
It identifies that network carries out digital alphabet identification, obtains digital alphabet data.Finally Chinese Fields and digital alphabet are merged, and
The field that is formatted according to the matched mode of canonical as a result, and export the confidence level of each field, finally according to confidence level
Output field can be realized automatic identification business license field.
Technical solution of the present invention is used when receiving business license picture to be identified, first in business license picture
Text detected, all text regions are determined by testing result, then to text region carry out for the first time
Identification, i.e. Text region, obtain the Text region result Chinese Fields data of all fields according to Text region；Further according to specific
Condition selects the character area of unified social credibility code or number of registration in Text region result；Then to unified social credibility
The text region of code or number of registration carries out second and identifies, i.e., digital alphabet identifies, according to digital alphabet recognition result
Obtain digital alphabet data；The Chinese Fields data of identification and digital alphabet data are merged, show that business license identifies
As a result, it is possible to which automatic identification business license field, can be improved recognition efficiency.In addition, using digital alphabet identification network to battalion
Industry license meets the unified social credibility code of specified conditions or number of registration character area is further identified, can be improved battalion
The identification accuracy of industry license entirety.
In a specific embodiment, described pair of all text regions carry out Text region, specifically include:
All text regions are cut, textbox is obtained；
According to Text region network in textbox Chinese Fields and alphanumeric characters number identify.
In the present embodiment, by all text regions are cut multiple character areas can be cut into it is several
A textbox, according to Text region network in textbox Chinese Fields and alphanumeric characters number identify.Above-mentioned
Text region network uses densenet+CTC model, and the textbox of multiple cuttings can be inputted in Text region model with batch,
To improve recognition efficiency.
It is described that numeric word is carried out to text region using digital alphabet identification network in a specific embodiment
Mother's identification, specifically includes:
Number or alphabetical starting position are found out in text region according to CTC algorithm；
The text region cut is cut again according to number or alphabetical starting position, obtains digital alphabet
Textbox；
The digital alphabet in digital alphabetic literal frame is identified using digital alphabet identification network.
In the present embodiment, CTC algorithm is well known algorithm.Here main to utilize according to CTC algorithm in text region
Number or alphabetical starting position are found out, after finding word start position, this section of text is number and/or alphabet data.Then
The text region cut is cut again according to number or alphabetical starting position, by above-mentioned cutting, can be incited somebody to action
Single number or letter is separately in independent textbox, to facilitate the identification of subsequent number and letter.
It is described to merge the Chinese Fields data of identification and digital alphabet data in a specific embodiment,
After obtaining business license recognition result, further includes:
All recognition results are cleaned, the business for obtaining standard executes field.
In the present embodiment, all recognition results include Chinese Fields and alphanumeric information, available after over cleaning
The business of standard executes field.It can finally show that the business of standard executes field.
Referring to figure 2., Fig. 2 is the block diagram of the automatic recognition system of one embodiment of the invention business license.This hair
In bright embodiment, the automatic recognition system of the business license, comprising:
Text detection module 10, for when receiving business license picture to be identified, in business license picture
Text detect and determines all text regions；
Text region module 20 obtains the text of all fields for carrying out Text region to all text regions
Recognition result；
Judgment module 30, for selecting unified social credibility code or registration in Text region result according to specified conditions
Number character area；
Digital identification module 40, for the character area to unified social credibility code or number of registration, using special digital
Letter identification network carries out digital alphabet identification, obtains digital alphabet data；；
Cleaning module 50 show that business is held for merging the Chinese Fields data of identification and digital alphabet data
According to recognition result.
In the present embodiment, this system first passes through text in the business license photo or picture to be identified for receiving input
Word detection module 10 detects all texts in picture according to text detection network, and determines all text regions.It is above-mentioned
All texts include Chinese character and digital alphabet.By Text region module 20, text region is carried out for the first time
Identification carries out Text region to all text regions using trained network.Judgment module 30 is selected according to specified conditions
The character area of unified social credibility code or number of registration in Text region result.The specified conditions need to meet three simultaneously
A condition judges the number of characters of digital alphabet and the size of setting word threshold, is greater than setting word in the number of characters of digital alphabet
When according with threshold value, continue to determine in the literal line where digital alphabet that the field is crucial whether containing specified field keys
Word includes unified social credibility code or number of registration；Contain specified field keys in the literal line where digital alphabet
When, continue to verify original recognition result according to unified social credibility code coding rule or number of registration establishment rules,
It is obstructed out-of-date to verify, this character area is judged as that unified social credibility code or note are contained in target area, the target area
The character area of volume number；If this character area is otherwise determined as nontarget area.It need to be noted that, one in three conditions
A when being unsatisfactory for, this character area is determined as nontarget area.Then by digital identification module 40, to unified social credibility generation
The character area of code or number of registration carries out digital alphabet identification using special digital Letter identification network, obtains digital alphabet number
According to；Finally by cleaning module 50, Chinese Fields and digital alphabet are merged, and lattice are obtained according to the matched mode of canonical
The field of formula is as a result, and exporting the confidence level of each field and can be realized automatic identification finally according to confidence level output field
Business license field.
In a specific embodiment, the Text region module 20 is specifically used for:
All text regions are cut, textbox is obtained；
According to Text region network in textbox Chinese Fields and alphanumeric characters number identify.
In a specific embodiment, the number identification module 40 is specifically used for: identifying network using digital alphabet
Digital alphabet identification is carried out to text region.
In a specific embodiment, the number identification module 40 is also used to:
Number or alphabetical starting position are found out in text region according to CTC algorithm；
The text region cut is cut again according to number or alphabetical starting position, obtains digital alphabet
Textbox；
The digital alphabet in digital alphabetic literal frame is identified using digital alphabet identification network.
In a specific embodiment, the judgment module 30 is also used to:
The character area of the unified social credibility code or number of registration in Text region result is selected according to specified conditions.It should
Specified conditions need to meet simultaneously three conditions, the number of characters of digital alphabet and the size of setting word threshold are judged, in number
When the number of characters of letter is greater than setting word threshold, whether continue to determine in the literal line where digital alphabet containing specified word
Section keyword, the field keys include unified social credibility code or number of registration；In the literal line where digital alphabet
In containing specified field keys when, continue according to unified social credibility code coding rule or number of registration establishment rules to original
Beginning recognition result is verified, obstructed out-of-date verifying, this character area is judged as that target area, the target area are contained
The character area of unified social credibility code or number of registration；If this character area is otherwise determined as nontarget area.
In a specific embodiment, further includes cleaning module 50, is used for,
All recognition results are cleaned, the business for obtaining standard executes field.
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.A kind of automatic identification side of business license is realized when the computer program is executed by processor
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 integrating 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 (8)
1. a kind of automatic identifying method of business license, which is characterized in that the automatic identifying method of the business license, comprising:
When receiving business license picture to be identified, the text in business license picture detect and determines all texts
Word region；
Text region is carried out to all text regions, obtains the Text region result of all fields；
The character area of the unified social credibility code or number of registration in Text region result is selected according to specified conditions；
To the character area of unified social credibility code or number of registration, digital alphabet is carried out using special digital Letter identification network
Identification, obtains digital alphabet data；
The Chinese Fields data of identification and digital alphabet data are merged, obtain business license recognition result.
2. the automatic identifying method of business license as described in claim 1, which is characterized in that described pair of all text location
Domain carries out Text region, specifically includes:
All text regions are cut, textbox is obtained；
All character fields in textbox are identified according to Text region network.
3. the automatic identifying method of business license as claimed in claim 2, which is characterized in that described using special digital letter
It identifies that network carries out digital alphabet identification, specifically includes:
Number or alphabetical starting position are found out in text region according to CTC algorithm；
The text region cut is cut again according to number or alphabetical starting position, obtains digital alphabet text
Frame；
The digital alphabet in digital alphabetic literal frame is identified using digital alphabet identification network.
4. the automatic identifying method of business license as claimed in claim 3, which is characterized in that described to be selected according to specified conditions
The character area of unified social credibility code or number of registration in Text region result, specifically includes:
Judge the number of characters of digital alphabet and the size of setting word threshold,
Digital alphabet number of characters be greater than setting word threshold when, continue determine digital alphabet where literal line in whether contain
There are specified field keys, the field keys include unified social credibility code or number of registration；
When in the literal line where digital alphabet containing specified field keys, continue to be compiled according to unified social credibility code
Code rule or number of registration establishment rules verify original recognition result, obstructed out-of-date verifying, this character area is judged
For target area, the character area of unified social credibility code or number of registration is contained in the target area；
If this character area is otherwise determined as nontarget area.
5. the automatic identifying method of business license as described in claim 1, which is characterized in that the Chinese Fields by identification
Data and digital alphabet data merge, after obtaining business license recognition result, further includes:
All recognition results are cleaned, the business for obtaining standard executes field.
6. a kind of automatic recognition system of business license, which is characterized in that the automatic recognition system of the business license, comprising:
Text detection module, for when receiving business license picture to be identified, to the text in business license picture into
Row detects and determines all text regions；
Text region module obtains the Text region knot of all fields for carrying out Text region to all text regions
Fruit；
Judgment module, for selecting the text of unified social credibility code or number of registration in Text region result according to specified conditions
Block domain；
Digital identification module is known for the character area to unified social credibility code or number of registration using special digital letter
Other network carries out digital alphabet identification, obtains digital alphabet data；
Cleaning module show that business license identifies for merging the Chinese Fields data of identification and digital alphabet data
As a result.
7. 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 5 institute when executing the computer program
The step of stating method.
8. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program quilt
The step of processor realizes method described in any one of claims 1 to 5 when executing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910409918.4A CN110135431A (en) | 2019-05-16 | 2019-05-16 | The automatic identifying method and system of business license |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910409918.4A CN110135431A (en) | 2019-05-16 | 2019-05-16 | The automatic identifying method and system of business license |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110135431A true CN110135431A (en) | 2019-08-16 |
Family
ID=67574735
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910409918.4A Pending CN110135431A (en) | 2019-05-16 | 2019-05-16 | The automatic identifying method and system of business license |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110135431A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111507813A (en) * | 2020-04-21 | 2020-08-07 | 江西省机电设备招标有限公司 | Bidder identity confirming method and bidding method |
| CN113642556A (en) * | 2021-08-04 | 2021-11-12 | 五八有限公司 | Image processing method and device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1750036A (en) * | 2004-09-07 | 2006-03-22 | 韩国超级票据株式会社 | System and method for mnaging, exchanging and purchasing medium of electronic bill and electronic check |
| CN106611174A (en) * | 2016-12-29 | 2017-05-03 | 成都数联铭品科技有限公司 | OCR recognition method for unusual fonts |
| CN106815561A (en) * | 2016-12-22 | 2017-06-09 | 北京五八信息技术有限公司 | Business license printed page analysis method and device |
| CN106846011A (en) * | 2016-12-30 | 2017-06-13 | 金蝶软件（中国）有限公司 | Business license recognition methods and device |
| CN108399405A (en) * | 2017-02-07 | 2018-08-14 | 腾讯科技（上海）有限公司 | Business license recognition methods and device |
| CN108898131A (en) * | 2018-05-23 | 2018-11-27 | 郑州金惠计算机系统工程有限公司 | It is a kind of complexity natural scene under digital instrument recognition methods |
| CN108921166A (en) * | 2018-06-22 | 2018-11-30 | 深源恒际科技有限公司 | Medical bill class text detection recognition method and system based on deep neural network |
| CN109241894A (en) * | 2018-08-28 | 2019-01-18 | 南京安链数据科技有限公司 | A kind of specific aim ticket contents identifying system and method based on form locating and deep learning |
-
2019
- 2019-05-16 CN CN201910409918.4A patent/CN110135431A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1750036A (en) * | 2004-09-07 | 2006-03-22 | 韩国超级票据株式会社 | System and method for mnaging, exchanging and purchasing medium of electronic bill and electronic check |
| CN106815561A (en) * | 2016-12-22 | 2017-06-09 | 北京五八信息技术有限公司 | Business license printed page analysis method and device |
| CN106611174A (en) * | 2016-12-29 | 2017-05-03 | 成都数联铭品科技有限公司 | OCR recognition method for unusual fonts |
| CN106846011A (en) * | 2016-12-30 | 2017-06-13 | 金蝶软件（中国）有限公司 | Business license recognition methods and device |
| CN108399405A (en) * | 2017-02-07 | 2018-08-14 | 腾讯科技（上海）有限公司 | Business license recognition methods and device |
| CN108898131A (en) * | 2018-05-23 | 2018-11-27 | 郑州金惠计算机系统工程有限公司 | It is a kind of complexity natural scene under digital instrument recognition methods |
| CN108921166A (en) * | 2018-06-22 | 2018-11-30 | 深源恒际科技有限公司 | Medical bill class text detection recognition method and system based on deep neural network |
| CN109241894A (en) * | 2018-08-28 | 2019-01-18 | 南京安链数据科技有限公司 | A kind of specific aim ticket contents identifying system and method based on form locating and deep learning |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111507813A (en) * | 2020-04-21 | 2020-08-07 | 江西省机电设备招标有限公司 | Bidder identity confirming method and bidding method |
| CN111507813B (en) * | 2020-04-21 | 2023-05-12 | 江西省机电设备招标有限公司 | Bidder identity identification method and bidding method |
| CN113642556A (en) * | 2021-08-04 | 2021-11-12 | 五八有限公司 | Image processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110489415B (en) | Data updating method and related equipment | |
| CN110765770A (en) | Automatic contract generation method and device | |
| CN106056114A (en) | Business card content identification method and business card content identification device | |
| CN103019937A (en) | Human-machine interaction interface traverse test method | |
| US11776248B2 (en) | Systems and methods for automated document image orientation correction | |
| CN103488460B (en) | The system and method for automatic mark source code | |
| CN110135431A (en) | The automatic identifying method and system of business license | |
| CN104462068A (en) | Character conversion system and method | |
| CN111583180A (en) | Image tampering identification method and device, computer equipment and storage medium | |
| CN107315989A (en) | For the text recognition method and device of medical information picture | |
| CN110929110B (en) | Electronic document detection method, device, equipment and storage medium | |
| CN111382570A (en) | Text entity recognition method and device, computer equipment and storage medium | |
| CN111754352A (en) | Method, device, equipment and storage medium for judging correctness of viewpoint statement | |
| CN110489416B (en) | Information storage method based on data processing and related equipment | |
| CN103778210B (en) | Method and device for judging specific file type of file to be analyzed | |
| EP2390793B1 (en) | Method for determining similarity of text portions | |
| CN111368061B (en) | Short text filtering method, device, medium and computer equipment | |
| CN109992778A (en) | Resume document method of discrimination and device based on machine learning | |
| CN115017871B (en) | Replacement display method and display system for file archive contents | |
| US20190205320A1 (en) | Sentence scoring apparatus and program | |
| CN109657929A (en) | Appraisal procedure, device and the computer equipment of trade mark registration percent of pass | |
| CN113792017A (en) | Method and system for checking template content imported into excel | |
| CN113849644A (en) | Text classification model configuration method and device, computer equipment and storage medium | |
| CN112784540A (en) | Document number proofreading method and device | |
| CN117114142B (en) | AI-based data rule expression generation method, apparatus, device and 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: 20190816 |
|
| RJ01 | Rejection of invention patent application after publication |