CN110070045A - A kind of text recognition method of business license, system and associated component - Google Patents
A kind of text recognition method of business license, system and associated component Download PDFInfo
- Publication number
- CN110070045A CN110070045A CN201910329154.8A CN201910329154A CN110070045A CN 110070045 A CN110070045 A CN 110070045A CN 201910329154 A CN201910329154 A CN 201910329154A CN 110070045 A CN110070045 A CN 110070045A
- Authority
- CN
- China
- Prior art keywords
- text
- filed
- license
- content
- text filed
- 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
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/412—Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Character Discrimination (AREA)
Abstract
This application discloses a kind of text recognition method of business license, the text recognition method includes the license image for obtaining target business license, and executes text filed division operation to the license image, is obtained multiple text filed;Each text filed execution text identification is operated to obtain each text filed content of text;Each text filed corresponding information type is determined according to the content of text;The text identification result of the target business license is generated according to the content of text and corresponding information type.This method can carry out text identification operation to a variety of pattern business licenses, improve the accuracy of business license text identification result.Disclosed herein as well is a kind of text recognition system of business license, a kind of computer readable storage medium and a kind of electronic equipment, have the above beneficial effect.
Description
Technical field
The present invention relates to technical field of image processing, in particular to a kind of text recognition method of business license, system, one
Kind computer readable storage medium and a kind of electronic equipment.
Background technique
Text identification is a kind of technology using Computer Automatic Recognition character, and one for belonging to application of pattern recognition is important
Field.People will handle a large amount of text, report and text in production and life, and text recognition technique can mitigate people
Labour, improve treatment effeciency.Text information in automatic identification image can be applied to multiple fields, such as identification identity
Word content in card, bank card, and then extract key message.
Text identification is being carried out in the related technology to business license, is usually first determining pre-set region to be identified,
Identification region is treated again carries out relevant text identification operation.But when the modal shift of business license, above-mentioned related text
Recognition methods just fails.
Therefore, how text identification operation is carried out to a variety of pattern business licenses, improves business license text identification result
Accuracy be a technical problem that technical personnel in the field need to solve at present.
Summary of the invention
The purpose of the application is to provide a kind of text recognition method of business license, system, a kind of computer-readable storage
Medium and a kind of electronic equipment can carry out text identification operation to a variety of pattern business licenses, improve business license text and know
The accuracy of other result.
In order to solve the above technical problems, the application provides a kind of text recognition method of business license, text identification side
Method includes:
The license image of target business license is obtained, and text filed division operation is executed to the license image, is obtained
It is multiple text filed;
Each text filed execution text identification is operated to obtain each text filed content of text;
Each text filed corresponding information type is determined according to the content of text;
The text identification result of the target business license is generated according to the content of text and corresponding information type.
Optionally, text filed division operation is executed to the license image, obtain multiple text filed include:
Determine the location information of each textual character in the license image;
Text filed division operation is executed to license image according to the positional information, obtain it is multiple described text filed,
So that each text filed interior all textual character spacing are respectively less than preset value.
Optionally, include: to each text filed execution text identification operation
Each text filed execution text identification is operated using default Text region algorithm;Wherein, described default
Text region algorithm includes Densenet+ctc recognition methods.
Optionally, determine that each text filed corresponding information type includes: according to the content of text
The keyword of the content of text is extracted, and each text filed corresponding letter is determined according to the keyword
Cease type.
Optionally, the information type include number of registration, social credibility code, title, residence, legal representative, effectively
Any one of date appoints several combinations.
Optionally, it after determining each text filed corresponding information type according to the content of text, also wraps
It includes:
Record the corresponding relationship of each text filed regional center the point coordinate and information type;
Business license Text region template is generated according to the corresponding relationship.
Present invention also provides a kind of text recognition system of business license, text identifying system includes:
Region division module executes text for obtaining the license image of target business license, and to the license image
Region division operation, obtains multiple text filed;
Identification module, it is each described text filed for operating to obtain to each text filed execution text identification
Content of text;
Determination type module, for determining each text filed corresponding information type according to the content of text;
Result-generation module, for generating the target business license according to the content of text and corresponding information type
Text identification result.
Optionally, the region division module includes:
Position determination unit, for determining the location information of each textual character in the license image;
Division unit obtains multiple for executing text filed division operation to license image according to the positional information
It is described text filed, so that each text filed interior all textual character spacing are respectively less than preset value.
Present invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, the computer
Program realizes the step of text recognition method of above-mentioned business license executes when executing.
Present invention also provides a kind of electronic equipment, including memory and processor, calculating is stored in the memory
Machine program, the processor realize the text recognition method of above-mentioned business license when calling the computer program in the memory
The step of execution.
This application provides a kind of text recognition methods of business license, the license figure including obtaining target business license
Picture, and text filed division operation is executed to the license image, it obtains multiple text filed;It described text filed is held to each
Row text identification operates to obtain each text filed content of text;Each text is determined according to the content of text
The corresponding information type in region;The text of the target business license is generated according to the content of text and corresponding information type
Recognition result.
The application business license is divided into according to the text distribution situation in license image first it is multiple text filed, by
Text in business license is arranged according to certain rules, and the word content that a block text region is reflected belongs to specific
A kind of text information, such as title, type or residence, therefore determined according to each text filed middle word content should by the application
The information type in region, and then corresponding business license text is generated according to each text filed information type and Wen Nei content
Recognition result.The application can carry out text identification operation to a variety of pattern business licenses, improve business license text identification knot
The accuracy of fruit.The application additionally provides a kind of text recognition system of business license, a kind of computer-readable storage medium simultaneously
Matter and a kind of electronic equipment have above-mentioned beneficial effect, and details are not described herein.
Detailed description of the invention
In ord to more clearly illustrate embodiments of the present application, attached drawing needed in the embodiment will be done simply below
It introduces, it should be apparent that, the drawings in the following description are only some examples of the present application, for ordinary skill people
For member, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart of the text recognition method of business license provided by the embodiment of the present application;
Fig. 2 is the flow chart of the text recognition method of another kind business license provided by the embodiment of the present application;
Fig. 3 is license of the business corporation schematic diagram provided by the embodiments of the present application;
Fig. 4 is text filed division schematic diagram provided by the embodiments of the present application;
Fig. 5 is a kind of structural schematic diagram of the text recognition system of business license provided by the embodiment of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall in the protection scope of this application.
Below referring to Figure 1, Fig. 1 is a kind of stream of the text recognition method of business license provided by the embodiment of the present application
Cheng Tu.
Specific steps may include:
S101: obtaining the license image of target business license, and execute text filed division operation to the license image,
It obtains multiple text filed;
Wherein, the purpose of the present embodiment is that automatically extracting the text information to target business license, specifically, to target
The condition that the text identification result of business license should comply with are as follows: it is accurate that content of text identification is accurate, content of text type is sorted out,
There should not be the case where content of text and text type matching error.There may be receive text identification behaviour before this step
The instruction of work obtains the license image of target business license according to the instruction.It, can be preparatory as a kind of feasible embodiment
The license image of target business license has been shot before this step and has stored license image to specific memory space, is being held
License image directly is obtained from memory space when row S101.
It is understood that may include background area in business license and text filed, to license figure in the present embodiment
Business license will be divided into back as judgment basis with the presence or absence of content of text as the text filed division operation of execution is equivalent to
Scene area and character area, that is to say, that the region for not including content of text is background area, and the region including content of text is
It is text filed.The above-mentioned content of text being previously mentioned may include text, symbol, number etc..Further, the text in business license
This content is to arrange according to certain format, therefore there is specific certain content of text concentrations in business license and be present in
Some region of situation, such as: content of text corresponding to " title " is present in text filed interior a, " warp in business license
It is text filed interior that content of text corresponding to battalion's range " is present in one, and " title " is corresponding text filed and " manages model
Enclose " corresponding text filed spacing is greater than pre-determined distance.Specifically, can use retinanet frame carries out text detection
Determine it is text filed in license image, to complete text filed division operation.It determines text filed rear available each
Text filed location information (such as apex coordinate), to be held according to text filed location information to text filed in S102
The operation of row text identification.
Certainly, license photo can be divided into background area and multiple text filed, tool after the operation by S101
Body, it is text filed may include number of registration, social credibility code, title, residence, legal representative, corresponding to validity date
Content.It should be noted that the content of text on business license can be divided into two classes due to the call format of business license,
One kind be the information type for being used to indicate one's respective area content " item " and the information type corresponding to " content ".Therefore each
It is text filed to be divided into two sub-regions, therefore text filed can refer to number of registration item, number of registration content, social credibility code
Item, social credibility code content, name item, title content, residence item, residence content, legal representative, in legal representative
Hold, region corresponding to validity date and validity date content.
S102: each text filed execution text identification is operated to obtain in each text filed text
Hold;
Wherein, this step is established on the basis of having determined that text filed in license image, to each text area
Domain executes text identification and operates to obtain the content of text in text filed.The present embodiment does not limit the specific mistake of text identification operation
Journey can select text recognition algorithms appropriate to execute text identification operation, such as OCR Text region according to practical application scene
Algorithm, Densenet+ctc recognition methods etc..
S103: each text filed corresponding information type is determined according to the content of text;
Wherein, the purpose of this step is to determine text filed information type, in having obtained this article one's respective area
After content of text, content of text can be carried out determining information type based on the grammatical and semantic analysis of keyword.As one kind
Feasible embodiment can use trained text information type detection model and be analyzed accordingly content of text,
Obtain each text filed information type.
According to the discussion of front it is each it is text filed may include two sub-regions, therefore in this step determine
Information type can be the information type of the corresponding all texts in this article one's respective area, be also possible to every included by this article one's respective area
The set of the information type of one subregion text.Such as information type may include number of registration, social credibility code, title, live
Institute, legal representative, validity date are also possible to number of registration item, number of registration content, social credibility code entry, social credibility generation
Digital content, name item, title content, residence item, residence content, legal representative's item, legal representative's content, validity date
With validity date content, the present embodiment is not limited the division mode of information type specifically.
S104: the text identification knot of the target business license is generated according to the content of text and corresponding information type
Fruit.
It wherein, can be by after obtaining each text filed content of text and information type of target business license
Corresponding text identification result is generated according to content of text and the corresponding relationship of information type.As a kind of feasible embodiment,
The text identification result including each content of text and corresponding information type can be exported in the way of table.
The present embodiment business license is divided into according to the text distribution situation in license image first it is multiple text filed,
Since the text in business license is arranged according to certain rules, the word content that a block text region is reflected belongs to spy
Fixed a kind of text information, such as title, type or residence, therefore the present embodiment is true according to each text filed middle word content
The information type in the fixed region, and then corresponding business license is generated according to each text filed information type and Wen Nei content
Text identification result.The present embodiment can carry out text identification operation to a variety of pattern business licenses, improve business license text
The accuracy of recognition result.
Fig. 2 is referred to below, and Fig. 2 is the text recognition method of another kind business license provided by the embodiment of the present application
The specific steps of flow chart, the present embodiment may include:
S201: the license image of target business license is obtained, and determines the position of each textual character in the license image
Confidence breath;
Wherein, the textual character mentioned in this step i.e. text, number, the general name of symbol, different types of textual character
There are different location information methods of determination.For example, the location information of textual character is each Chinese when textual character is Chinese character
The geometric center of word;When textual character is the language that English etc. is made of letter, textual character is in the set of each single
The heart.Those skilled in the art will also be appreciated that the location information method of determination of other textual characters, herein without specific
Restriction.
S202: text filed division operation is executed to license image according to the positional information, obtains multiple texts
Region, so that each text filed interior all textual character spacing are respectively less than preset value.
Wherein, the purpose of this step is to carry out textual character in license image according to location distribution information text filed
It divides, all textual character spacing that text spacing can be less than to preset value are less than where all textual characters of preset value
Region is set as a text region.After division is text filed, obtained each text filed interior all texts are accorded with
Number spacing is respectively less than preset value, wantonly one or two it is different it is text filed in the distance between textual characters it is default more than or equal to this
Value.
S203: each text filed execution text identification is operated to obtain each institute using default Text region algorithm
State text filed content of text;
Wherein, the default Text region algorithm may include Densenet+ctc recognition methods.
S204: extracting the keyword of the content of text, and determined according to the keyword it is each described text filed right
The information type answered.
S205: the text identification knot of the target business license is generated according to the content of text and corresponding information type
Fruit.
As a kind of feasible embodiment, each text filed corresponding letter is being determined according to the content of text
After ceasing type, further includes following operation: recording pair of each text filed regional center the point coordinate and information type
It should be related to;Business license Text region template is generated according to the corresponding relationship.It, can be true after generating Text region template
Information type representated by the textual character of each position in fixed all business licenses corresponding with the text recognition template, with
Just according to the certain type of text filed position of regional center point coordinate, and then quick text identification is realized.
It is based on generic text recognition methods below by embodiment explanation in practical applications, for example uses Densenet+
Ctc carries out text identification.
Fig. 3 is referred to, Fig. 3 is license of the business corporation schematic diagram provided by the embodiments of the present application, inputs one first
Picture (such as Fig. 3) comprising business license complete information then carries out text detection, each available text area to picture
The coordinate (x1, y1, x2, y2) in domain, (x1, y1) are top left co-ordinate, and (x2, y2) is bottom right angular coordinate.Refer to Fig. 4, Fig. 4
For text filed division schematic diagram provided by the embodiments of the present application.To the text filed carry out text identification detected, can obtain
To text as shown in Table 1.Key message is extracted to text identification result, for example searches " registration in the information recognized
Number ", it finds number of registration and obtains the coordinate information (x1, y1, x2, y2) of number of registration text box.Believed according to the coordinate of the key message
Breath, is retrieved in all obtained text positions, finds the text information with the key message in same row, for example,
With number of registration with a line be a line number: 302xxxxxxxxxxx.Wherein, look for the method for same a line can be with are as follows: by each
The central point of the available each frame of the coordinate of a text box sees that the ordinate of which central point is fallen in such as " number of registration ", y1,
Between y2.And so on, so that it may find the key message on all business licenses.Finally to the key message on business license
It is integrated: obtaining corresponding relationship as shown in Table 2 and export.
The present embodiment carries out text detection from the picture comprising business license complete information, then carries out text identification,
It is matched according to text position information and the result of identification, obtains key message content on business license.
1 text identification result table of table
Number of registration |
3302XXXXXXXXXXX |
Social credibility code |
9974XXXXXXXXXXX |
Title |
XXXX Co., Ltd, the city XX |
Residence |
The city XX, the XX province road XXXX 121-1 |
Legal representative |
Mr. Li |
Validity date is extremely |
The year two thousand fifty August 21 days |
2 license information of table integrates table
Number of registration | 3302XXXXXXXXXXX |
Social credibility code | 9974XXXXXXXXXXX |
Title | XXXX Co., Ltd, the city XX |
Residence | The city XX, the XX province road XXXX 121-1 |
Legal representative | Mr. Li |
Validity date is extremely | The year two thousand fifty August 21 days |
Fig. 5 is referred to, Fig. 5 shows for a kind of structure of the text recognition system of business license provided by the embodiment of the present application
It is intended to;
The system may include:
Region division module 100 executes text for obtaining the license image of target business license, and to the license image
One's respective area division operation obtains multiple text filed;
Identification module 200, for operating to obtain each text area to each text filed execution text identification
The content of text in domain;
Determination type module 300, for determining each text filed corresponding info class according to the content of text
Type;
Result-generation module 400, for generating the target business according to the content of text and corresponding information type
The text identification result of license.
The present embodiment business license is divided into according to the text distribution situation in license image first it is multiple text filed,
Since the text in business license is arranged according to certain rules, the word content that a block text region is reflected belongs to spy
Fixed a kind of text information, such as title, type or residence, therefore the present embodiment is true according to each text filed middle word content
The information type in the fixed region, and then corresponding business license is generated according to each text filed information type and Wen Nei content
Text identification result.The present embodiment can carry out text identification operation to a variety of pattern business licenses, improve business license text
The accuracy of recognition result.
Further, the region division module 100 includes:
Position determination unit, for determining the location information of each textual character in the license image;
Division unit obtains multiple for executing text filed division operation to license image according to the positional information
It is described text filed, so that each text filed interior all textual character spacing are respectively less than preset value.
Further, identification module 200 is specially using default Text region algorithm to each text filed execution
Text identification operates to obtain the module of each text filed content of text;Wherein, the default Text region algorithm packet
Include Densenet+ctc recognizer.
Further, determination type module 300 is particularly for the keyword for extracting the content of text, and according to described
Keyword determines the module of each text filed corresponding information type.
Further, the information type includes number of registration, social credibility code, title, residence, legal representative, has
It imitates any one of date or appoints several combinations.
Further, further includes:
Logging modle, for according to the content of text determine each text filed corresponding information type it
Afterwards, the corresponding relationship of each text filed regional center the point coordinate and information type is recorded;
Last generation module, for generating business license Text region template according to the corresponding relationship.
Since the embodiment of components of system as directed is corresponded to each other with the embodiment of method part, the embodiment of components of system as directed is asked
Referring to the description of the embodiment of method part, wouldn't repeat here.
Present invention also provides a kind of computer readable storage mediums, have computer program thereon, the computer program
It is performed and step provided by above-described embodiment may be implemented.The storage medium may include: USB flash disk, mobile hard disk, read-only
Memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or
The various media that can store program code such as person's CD.
Present invention also provides a kind of electronic equipment, may include memory and processor, have meter in the memory
Calculation machine program may be implemented provided by above-described embodiment when the processor calls the computer program in the memory
Step.Certain electronic equipment can also include various network interfaces, the components such as power supply.
Each embodiment is described in a progressive manner in specification, the highlights of each of the examples are with other realities
The difference of example is applied, the same or similar parts in each embodiment may refer to each other.For system disclosed in embodiment
Speech, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is referring to method part illustration
?.It should be pointed out that for those skilled in the art, under the premise of not departing from the application principle, also
Can to the application, some improvement and modification can also be carried out, these improvement and modification also fall into the protection scope of the claim of this application
It is interior.
It should also be noted that, in the present specification, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.Under the situation not limited more, the element limited by sentence "including a ..." is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
Claims (10)
1. a kind of text recognition method of business license characterized by comprising
The license image of target business license is obtained, and text filed division operation is executed to the license image, is obtained multiple
It is text filed;
Each text filed execution text identification is operated to obtain each text filed content of text;
Each text filed corresponding information type is determined according to the content of text;
The text identification result of the target business license is generated according to the content of text and corresponding information type.
2. text recognition method according to claim 1, which is characterized in that execute text filed division to the license image
Operation, obtain multiple text filed include:
Determine the location information of each textual character in the license image;
Text filed division operation is executed to the license image according to the positional information, obtain it is multiple described text filed,
So that each text filed interior all textual character spacing are respectively less than preset value.
3. text recognition method according to claim 1, which is characterized in that each text filed execution text identification
Operation includes:
Each text filed execution text identification is operated using default Text region algorithm;Wherein, the default text
Recognizer includes Densenet+ctc recognition methods.
4. text recognition method according to claim 1, which is characterized in that determine each text according to the content of text
The corresponding information type in one's respective area includes:
The keyword of the content of text is extracted, and each text filed corresponding info class is determined according to the keyword
Type.
5. text recognition method according to claim 1, which is characterized in that the information type includes number of registration, society's letter
With any one of code, title, residence, legal representative, validity date or appoint several combinations.
6. according to claim 1 to any one of 5 text recognition methods, which is characterized in that true according to the content of text
After fixed each text filed corresponding information type, further includes:
Record the corresponding relationship of each text filed regional center the point coordinate and information type;
Business license Text region template is generated according to the corresponding relationship.
7. a kind of text recognition system of business license characterized by comprising
Region division module for obtaining the license image of target business license, and executes the license image text filed
Division operation obtains multiple text filed;
Identification module, for operating to obtain each text filed text to each text filed execution text identification
Content;
Determination type module, for determining each text filed corresponding information type according to the content of text;
Result-generation module, for generating the text of the target business license according to the content of text and corresponding information type
This recognition result.
8. text recognition system according to claim 7, which is characterized in that the region division module includes:
Position determination unit, for determining the location information of each textual character in the license image;
Division unit obtains multiple for executing text filed division operation to the license image according to the positional information
It is described text filed, so that each text filed interior all textual character spacing are respectively less than preset value.
9. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes that the text of the business license as described in any one of claim 1 to 6 is known when the computer program is executed by processor
The step of other method.
10. a kind of electronic equipment characterized by comprising
Memory, for storing computer program;
Processor realizes the text of the business license as described in any one of claim 1 to 6 when for executing the computer program
The step of recognition methods.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910329154.8A CN110070045A (en) | 2019-04-23 | 2019-04-23 | A kind of text recognition method of business license, system and associated component |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910329154.8A CN110070045A (en) | 2019-04-23 | 2019-04-23 | A kind of text recognition method of business license, system and associated component |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110070045A true CN110070045A (en) | 2019-07-30 |
Family
ID=67368571
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910329154.8A Pending CN110070045A (en) | 2019-04-23 | 2019-04-23 | A kind of text recognition method of business license, system and associated component |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110070045A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110889402A (en) * | 2019-11-04 | 2020-03-17 | 广州丰石科技有限公司 | Business license content identification method and system based on deep learning |
CN113569834A (en) * | 2021-08-05 | 2021-10-29 | 五八同城信息技术有限公司 | Business license identification method and device, electronic equipment and storage medium |
CN113723069A (en) * | 2021-09-03 | 2021-11-30 | 北京房江湖科技有限公司 | File detection method and system, machine-readable storage medium and electronic device |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106570500A (en) * | 2016-11-11 | 2017-04-19 | 北京三快在线科技有限公司 | Text line recognition method and device and calculation 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 |
CN107622255A (en) * | 2017-10-12 | 2018-01-23 | 江苏鸿信系统集成有限公司 | Bill images field localization method and system based on situation template and semantic template |
CN108399405A (en) * | 2017-02-07 | 2018-08-14 | 腾讯科技(上海)有限公司 | Business license recognition methods and device |
CN109086756A (en) * | 2018-06-15 | 2018-12-25 | 众安信息技术服务有限公司 | A kind of text detection analysis method, device and equipment based on deep neural network |
CN109241904A (en) * | 2018-08-31 | 2019-01-18 | 平安科技(深圳)有限公司 | Text region model training, character recognition method, device, equipment and medium |
-
2019
- 2019-04-23 CN CN201910329154.8A patent/CN110070045A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106570500A (en) * | 2016-11-11 | 2017-04-19 | 北京三快在线科技有限公司 | Text line recognition method and device and calculation 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 |
CN107622255A (en) * | 2017-10-12 | 2018-01-23 | 江苏鸿信系统集成有限公司 | Bill images field localization method and system based on situation template and semantic template |
CN109086756A (en) * | 2018-06-15 | 2018-12-25 | 众安信息技术服务有限公司 | A kind of text detection analysis method, device and equipment based on deep neural network |
CN109241904A (en) * | 2018-08-31 | 2019-01-18 | 平安科技(深圳)有限公司 | Text region model training, character recognition method, device, equipment and medium |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110889402A (en) * | 2019-11-04 | 2020-03-17 | 广州丰石科技有限公司 | Business license content identification method and system based on deep learning |
CN113569834A (en) * | 2021-08-05 | 2021-10-29 | 五八同城信息技术有限公司 | Business license identification method and device, electronic equipment and storage medium |
CN113723069A (en) * | 2021-09-03 | 2021-11-30 | 北京房江湖科技有限公司 | File detection method and system, machine-readable storage medium and electronic device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105930159A (en) | Image-based interface code generation method and system | |
CN108053545B (en) | Certificate verification method and device, server and storage medium | |
CN106599240A (en) | Multi-source data processing method and system | |
CN111753767A (en) | Method and device for automatically correcting operation, electronic equipment and storage medium | |
CN110070045A (en) | A kind of text recognition method of business license, system and associated component | |
CN107274281A (en) | A kind of Accounting network system | |
CN106951832A (en) | A kind of verification method and device based on Handwritten Digits Recognition | |
CN110674396B (en) | Text information processing method and device, electronic equipment and readable storage medium | |
JP2004139484A (en) | Form processing device, program for implementing it, and program for creating form format | |
CN111191652A (en) | Certificate image identification method and device, electronic equipment and storage medium | |
CN105930836A (en) | Identification method and device of video text | |
Sang et al. | Robust movie character identification and the sensitivity analysis | |
CN112766255A (en) | Optical character recognition method, device, equipment and storage medium | |
CN111753120A (en) | Method and device for searching questions, electronic equipment and storage medium | |
CN110059647A (en) | A kind of file classification method, system and associated component | |
CN114118053A (en) | Contract information extraction method and device | |
CN106372216A (en) | Method and device for improving subject finding accuracy | |
CN112508000B (en) | Method and equipment for generating OCR image recognition model training data | |
CN104408403A (en) | Arbitration method and apparatus for inconsistent phenomenon of two pieces of entry information | |
CN114021556A (en) | Log sensitive data detection method and system based on natural language processing technology | |
CN112949523A (en) | Method and system for extracting key information from identity card image picture | |
CN104299000A (en) | Handwriting recognition method based on local fragment distribution characteristics | |
US20150199582A1 (en) | Character recognition apparatus and method | |
CN112541505B (en) | Text recognition method, text recognition device and computer-readable storage medium | |
CN110147516A (en) | The intelligent identification Method and relevant device of front-end code in Pages Design |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190730 |