CN106815561A - Business license printed page analysis method and device - Google Patents
Business license printed page analysis method and device Download PDFInfo
- Publication number
- CN106815561A CN106815561A CN201611200465.7A CN201611200465A CN106815561A CN 106815561 A CN106815561 A CN 106815561A CN 201611200465 A CN201611200465 A CN 201611200465A CN 106815561 A CN106815561 A CN 106815561A
- Authority
- CN
- China
- Prior art keywords
- boundary rectangle
- business license
- character
- connected domain
- locating shaft
- 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
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/414—Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Character Input (AREA)
Abstract
The application provides a kind of business license printed page analysis method and device, by determining at least one of business license connected domain, for each connected domain, determine the boundary rectangle of the connected domain, so as to obtain at least one boundary rectangle, then according at least one boundary rectangle, determine the locating shaft of preset characters, character in business license includes preset characters, the content of business license is split finally according to locating shaft, by the content segmentation of business license at least one character, and at least one character obtained according to segmentation, printed page analysis is carried out to business license.During being somebody's turn to do, by extracting the connected domain of business license, the purpose to business license printed page analysis is realized.
Description
Technical field
The invention relates to image analysis technology, more particularly to a kind of business license printed page analysis method and device.
Background technology
Business license is the voucher of enterprise or tissue lawful operation power, economic strength, money for proving enterprise or tissue
Matter and prestige etc..It is general to be filed an application to the administrative agency for industry and commerce from enterprise or organize, it is complicated formality by one, by work
Business administrative management organization issues.Because the application process of business license is complicated, and applicant has to comply with certain condition, because
This, many lawless persons carry out illegal operation by forging business license.
To prevent lawless person from forging business license, it is necessary to carry out printed page analysis to business license, so as to business license
Audited.However, software for discerning characters on the market is only for conventional portable document format (Portable at present
Document Format, PDF) or document carry out structural analysis, the method for not carrying out printed page analysis for business license.
Software for discerning characters according to analysis PDF or document is analyzed to business license, then analyze accuracy rate low.
The content of the invention
The embodiment of the present application provides a kind of business license printed page analysis method and device, by the connection for extracting business license
Domain, realizes the purpose to business license printed page analysis.
In a first aspect, the embodiment of the present application provides a kind of business license printed page analysis method, including：
Determine at least one of business license connected domain；
The boundary rectangle of each connected domain at least one connected domain is determined, to obtain at least one boundary rectangle；
According at least one boundary rectangle, the locating shaft of preset characters is determined, the character bag in the business license
Include the preset characters；
According to the locating shaft, split the content of the business license, by the content segmentation of the business license at least
One character；
According at least one character, printed page analysis is carried out to the business license.
In a kind of feasible implementation, before at least one of described determination business license connected domain, also include：
Obtain the binary image of the business license；
At least one of determination business license connected domain, including：
Determine at least one of binary image connected domain.
It is described according at least one boundary rectangle in a kind of feasible implementation, determine determining for preset characters
Before the axle of position, also include：
At least one boundary rectangle is filtered, to obtain qualified external square at least one boundary rectangle
Shape.
In a kind of feasible implementation, the qualified boundary rectangle includes：Pixel quantity is less than the first threshold
The boundary rectangle of value, transverse and longitudinal are outer less than the 3rd threshold value than the number of the boundary rectangle less than Second Threshold, the connected domain for including
Connect rectangle.
It is described according at least one boundary rectangle in a kind of feasible implementation, determine determining for preset characters
Position axle, including：Characteristics of image is extracted to each boundary rectangle at least one boundary rectangle, to obtain characteristics of image
Collection；Extract the characteristics of image of the preset characters；Determined from described image feature set special with the image of the preset characters
Levy immediate characteristics of image, using the corresponding boundary rectangle of the immediate image as the preset characters locating shaft.
It is described according to the locating shaft in a kind of feasible implementation, split the content of the business license, by institute
The content segmentation of business license is stated at least one character, including：According to the locating shaft, by the content of the business license point
It is cut at least one character string；By in each character string maps at least one character string to the business license, with
Obtain the business license after mapping character strings；At least one is extracted from the business license after the mapping character strings with behavior unit
Individual line character string；Each line character string at least one line character string is split, to obtain described at least one
Character.
Second aspect, the embodiment of the present application provides a kind of business license printed page analysis device, including：
Processing module, for determining at least one of business license connected domain；
Boundary rectangle determining module, the boundary rectangle for determining each connected domain at least one connected domain, with
Obtain at least one boundary rectangle；
Locating shaft determining module, it is described for according at least one boundary rectangle, determining the locating shaft of preset characters
Character in business license includes the preset characters；
Segmentation module, for according to the locating shaft, splitting the content of the business license, by the business license
Appearance is divided at least one character；
Analysis module, for according at least one character, printed page analysis being carried out to the business license.
In a kind of feasible implementation, the processing module, the binary image for obtaining the business license,
Determine at least one of binary image connected domain.
In a kind of feasible implementation, the boundary rectangle determining module is additionally operable to determine mould in the locating shaft
Root tuber before determining the locating shaft of preset characters, filters at least one boundary rectangle according at least one boundary rectangle,
To obtain qualified boundary rectangle at least one boundary rectangle.
In a kind of feasible implementation, the qualified boundary rectangle includes：Pixel quantity is less than the first threshold
The boundary rectangle of value, transverse and longitudinal are outer less than the 3rd threshold value than the number of the boundary rectangle less than Second Threshold, the connected domain for including
Connect rectangle.
In a kind of feasible implementation, the locating shaft determining module, specifically for external to described at least one
Each boundary rectangle in rectangle extracts characteristics of image, to obtain set of image characteristics；Extract the characteristics of image of the preset characters；
Determined from described image feature set with the immediate characteristics of image of the characteristics of image of the preset characters, will be described closest
The corresponding boundary rectangle of image as the preset characters locating shaft.
In a kind of feasible implementation, the segmentation module, specifically for according to the locating shaft, by the business
The content segmentation of license is at least one character string；By each character string maps at least one character string to the battalion
In industry license, to obtain the business license after mapping character strings；With business license of the behavior unit from after the mapping character strings
At least one line character string of middle extraction；Each line character string at least one line character string is split, to obtain
At least one character.
The business license printed page analysis method and device that the embodiment of the present application is provided, by determining in business license at least
One connected domain, for each connected domain, determines the boundary rectangle of the connected domain, so as to obtain at least one boundary rectangle,
Then according at least one boundary rectangle, the locating shaft of preset characters is determined, the character in business license includes preset characters, most
The content of business license is split according to locating shaft afterwards, by the content segmentation of business license at least one character, and root
According at least one character that segmentation is obtained, printed page analysis is carried out to business license.During being somebody's turn to do, by the company for extracting business license
Logical domain, realizes the purpose to business license printed page analysis.
Brief description of the drawings
Fig. 1 is the flow chart of the application business license printed page analysis embodiment of the method one；
Fig. 2 is the flow chart of preprocessing process in the application business license printed page analysis method；
Fig. 3 is the schematic diagram of binary image in the application business license printed page analysis method；
Fig. 4 is the schematic diagram of the boundary rectangle of connected domain in the application business license printed page analysis method；
Fig. 5 is the flow chart of preprocessing process in the application business license printed page analysis method；
Fig. 6 is the structural representation of the application business license printed page analysis device.
Specific embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In accompanying drawing, the technical scheme in the embodiment of the present application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, rather than whole embodiments.Based on the embodiment in the application, those skilled in the art are not having
There is the every other embodiment made and being obtained under the premise of creative work, belong to the scope of the application protection.Herein below
It is with reference to accompanying drawing and preferred embodiment, to the specific embodiment according to the application, structure, feature and its effect specifically
It is bright.
Fig. 1 is the flow chart of the application business license printed page analysis embodiment of the method one, including：
101st, at least one of business license connected domain is determined.
There is the information such as national emblem, title, content, seal, Quick Response Code on the business license space of a whole page, wherein, title includes registration
Number, title, type, residence, legal representative, registered capital, Date of Incorporation etc., accordingly, content include specific number of registration,
Specific title, particular type (such as partnership or restricted), specific address, the name of legal representative, registered capital
The amount of money, exact date etc. for setting up.In those information, interconnected multiple points constitute a region, and the region is referred to as
Connected domain.For example, " name " of title constitutes a connected domain, four words of business license respectively constitute four connected domains.This step
In, connected domain is determined from the business license space of a whole page by software algorithm.During determining connected domain, adjacent characteristic point quilt
Same region is divided into so as to form connected domain.
102nd, the boundary rectangle of each connected domain at least one connected domain is determined, to obtain at least one external square
Shape.
After connected domain on the business license space of a whole page is determined, for each connected domain, the external of the connected domain is asked for
Rectangle, so as to obtain the boundary rectangle of each connected domain.
103rd, according at least one boundary rectangle, the locating shaft of preset characters, the word in the business license are determined
Symbol includes the preset characters.
In this step, preset characters are pre-set, the image of the characteristics of image of preset characters and each boundary rectangle is special
Levy and compare, the external square of degree of approach highest with the characteristics of image of preset characters is determined from least one boundary rectangle
Shape, using the boundary rectangle as preset characters locating shaft.
104th, according to the locating shaft, split the content of the business license, by the content segmentation of the business license into
At least one character.
After locating shaft is determined, a series of segmentation is carried out to the content in business license, so as to by business license
Content segmentation is into character one by one.
105th, according at least one character, printed page analysis is carried out to the business license.
By the content segmentation on the business license space of a whole page into after character one by one, business license space of a whole page auditor according to
Those characters, the space of a whole page to business license is analyzed.During analysis, business license space of a whole page auditor obtain according to segmentation
At least one character, business license entire content is checked, then by content item classification (point title, type, residence),
Each single item is audited.
The business license printed page analysis method that the embodiment of the present application is provided, by determining at least one of business license even
Logical domain, for each connected domain, determines the boundary rectangle of the connected domain, so as to obtain at least one boundary rectangle, Ran Hougen
According at least one boundary rectangle, the locating shaft of preset characters is determined, the character in business license includes preset characters, finally according to
Locating shaft is split to the content of business license, by the content segmentation of business license at least one character, and according to segmentation
At least one character for obtaining, printed page analysis is carried out to business license.During being somebody's turn to do, by extracting the connected domain of business license,
Realize the purpose to business license printed page analysis.
In the embodiment of the present application, three processes are roughly divided into business license printed page analysis, below, to three processes point
It is not described in detail.
First, the first process：Preprocessing process.
Specifically, reference can be made to Fig. 2, Fig. 2 be the application business license printed page analysis method in preprocessing process flow chart,
Including：
201st, marginal information is filtered.
In this step, for a specific business license, it is normalized according to original scale to by business license, is led to
Image processing algorithm is crossed to filter out the marginal information of normalized business license.Wherein, image processing algorithm is, for example, longitudinal direction
Projection and transverse projection；Marginal information is, for example, the business license left and right sides with the white space of upper and lower both sides etc..
202nd, the binary image of business license is obtained.
In this step, binaryzation is carried out to the business license for filtering out marginal information using methods such as LMM binaryzations, so that
Obtain the binary image of business license.Specifically, Fig. 3 can be participated in, Fig. 3 is two in the application business license printed page analysis method
The schematic diagram of value image.
Fig. 3 is refer to, the image on the left side is original business license, and the image on the right is the two-value obtained by binaryzation
Change image.Wherein, the business license for filtering out marginal information is eliminated.
203rd, determine at least one of binary image connected domain, determine each connected domain at least one connected domain
Boundary rectangle, to obtain at least one boundary rectangle.
In this step, the connected domain in binary image is asked for, and draw the boundary rectangle of all connected domains.Wherein, outward
Connect the boundary rectangle of boundary rectangle and non-legible connected domain of the rectangle including word connected domain.Specifically, reference can be made to Fig. 4, Fig. 4
It is the schematic diagram of the boundary rectangle of connected domain in the application business license printed page analysis method.
Fig. 4 is refer to, the connected domain in binary image is multiple, accordingly, the boundary rectangle of connected domain is multiple.
204th, at least one boundary rectangle is filtered, to obtain qualified boundary rectangle at least one boundary rectangle.
In this step, according to a large amount of text-processing experiences, by comprising very few boundary rectangle, the transverse and longitudinal of pixel than excessive
Boundary rectangle, filtered out comprising the boundary rectangle that connected domain is excessive and other are ineligible, it is only remaining qualified
Boundary rectangle.Wherein, the pixel that pixel is crossed in oligodactyly boundary rectangle is less than first threshold, and first threshold is, for example, 6；It is horizontal
The vertical length-width ratio than excessive finger boundary rectangle is more than Second Threshold, and Second Threshold is, for example, 4；Comprising connected domain excessively refer to it is external
The quantity of the connected domain included in rectangle is more than the 3rd threshold value, and the 3rd threshold value is, for example, 4.In addition, ineligible is external
Rectangle can also be the transverse and longitudinal ratio of boundary rectangle less than the 4th threshold value, such as 0.3 boundary rectangle, the embodiment of the present application not with
This is limitation.
In this step, boundary rectangle, the angle of the angle of rectangle, as literal line are obtained by connected domain.
Secondly, the second process：Cutting procedure.
Specifically, reference can be made to Fig. 5, Fig. 5 be the application business license printed page analysis method in preprocessing process flow chart,
Including：
301st, according at least one boundary rectangle, the locating shaft of preset characters is determined, the character in business license includes pre-
If character.
In this step, according to the boundary rectangle of each connected domain, the locating shaft of preset characters is found using knn algorithms etc..
Under normal circumstances, preset characters are the character that business license includes.Specifically, several characters that desk of doing business is included
As preset characters, characteristics of image, such as histograms of oriented gradients (Histogram of Oriented are extracted to preset characters
Gradient, HOG) feature, characteristics of image, such as HOG features are extracted to each boundary rectangle at least one boundary rectangle, with
Obtain set of image characteristics.Then, each characteristics of image is concentrated to compare the characteristics of image of preset characters and characteristics of image, from
Characteristics of image concentrates the degree of approach highest characteristics of image determined with the characteristics of image of preset characters, by characteristics of image correspondence
Boundary rectangle as preset characters locating shaft.
302nd, according to locating shaft, by the content segmentation of business license at least one character string.
In this step, according to business license Chinese space between words gap, the width of the boundary rectangle to meeting word requirement,
Height etc. is counted, and combines the position of locating shaft, and by business license, title, the macroplate of content two are separated.So
Afterwards, in plate carry out word respectively between axial clearance, the statistics of lateral clearance, and combine the battalion after being normalized during first
Industry license, by intraplate content segmentation into the character string of behavior unit.
303rd, by each character string maps at least one character string to business license, after obtaining mapping character strings
Business license.
In this step, the business license before the character string maps to normalization for obtaining, i.e., original business license will be split
In.
304th, at least one line character string is extracted from the business license after mapping character strings with behavior unit, at least one
Each line character string in individual line character string is split, to obtain at least one character.
In this step, according to the relative position of text character block, by projects title in business license, content is successfully divided
Isolate.Specifically, carrying out background extracting again with behavior unit, and horizontal partition is carried out with reference to global text size, finally
It is Chinese character one by one by string segmentation.
305th, the Chinese character that segmentation is obtained is processed.
In this step, the Chinese character after segmentation is processed, the non-textual content of priori conditions is not met to filter out.Example
Such as, it is generally the case that the transverse and longitudinal ratio of Chinese character is 1:1, the transverse and longitudinal ratio of numeral is 1:2.By filtering, will be horizontal at least one character
Vertical ratio is not 1:1 or 1:2 character filtering falls.Wherein, transverse and longitudinal ratio is 1:1 or 1:2 are priori conditions.
Finally, the 3rd process：Printed page analysis process.
During being somebody's turn to do, according to Chinese character after treatment etc., the space of a whole page to business license is analyzed.During analysis, business
At least one character that license space of a whole page auditor obtains according to segmentation, checks to business license entire content, then will be interior
Hold classification of the items (point title, type, residence), each single item is audited.Should during, if desired optical character identification
(Optical Character Recognition, OCR), then can directly invoke each character that segmentation is obtained.
Fig. 6 is the structural representation of the application business license printed page analysis device, including：
Processing module 11, for determining at least one of business license connected domain；
Boundary rectangle determining module 12, the boundary rectangle for determining each connected domain at least one connected domain,
To obtain at least one boundary rectangle；
Locating shaft determining module 13, for according at least one boundary rectangle, determining the locating shaft of preset characters, institute
The character stated in business license includes the preset characters；
Segmentation module 14, for according to the locating shaft, splitting the content of the business license, by the business license
Content segmentation is at least one character；
Analysis module 15, for according at least one character, printed page analysis being carried out to the business license.
The business license printed page analysis device that the embodiment of the present application is provided, by determining at least one of business license even
Logical domain, for each connected domain, determines the boundary rectangle of the connected domain, so as to obtain at least one boundary rectangle, Ran Hougen
According at least one boundary rectangle, the locating shaft of preset characters is determined, the character in business license includes preset characters, finally according to
Locating shaft is split to the content of business license, by the content segmentation of business license at least one character, and according to segmentation
At least one character for obtaining, printed page analysis is carried out to business license.During being somebody's turn to do, by extracting the connected domain of business license,
Realize the purpose to business license printed page analysis.
Optionally, in the embodiment of the application one, the processing module 11, the binaryzation for obtaining the business license
Image, determines at least one of binary image connected domain.
Optionally, in the embodiment of the application one, the boundary rectangle determining module 12 is additionally operable to true in the locating shaft
Cover half block 13 before determining the locating shaft of preset characters, is filtered outside described at least one according at least one boundary rectangle
Rectangle is connect, to obtain qualified boundary rectangle at least one boundary rectangle.
Optionally, in the embodiment of the application one, the qualified boundary rectangle includes：Pixel quantity is less than first
The boundary rectangle of threshold value, transverse and longitudinal are less than the 3rd threshold value than the number of the boundary rectangle less than Second Threshold, the connected domain for including
Boundary rectangle.
Optionally, in the embodiment of the application one, the locating shaft determining module 13, specifically for described at least one
Each boundary rectangle in boundary rectangle extracts characteristics of image, to obtain set of image characteristics；Extract the image of the preset characters
Feature；Determined from described image feature set with the immediate characteristics of image of the characteristics of image of the preset characters, will be described
The corresponding boundary rectangle of immediate image as the preset characters locating shaft.
Optionally, in the embodiment of the application one, the segmentation module 14, specifically for according to the locating shaft, by institute
State the content segmentation of business license at least one character string；Each character string maps at least one character string are arrived
In the business license, to obtain the business license after mapping character strings；With battalion of the behavior unit from after the mapping character strings
At least one line character string is extracted in industry license；Each line character string at least one line character string is split,
To obtain at least one character.
One of ordinary skill in the art will appreciate that：Realizing all or part of step of above-mentioned each method embodiment can lead to
The related hardware of programmed instruction is crossed to complete.Foregoing program can be stored in a computer read/write memory medium.The journey
Sequence upon execution, performs the step of including above-mentioned each method embodiment；And foregoing storage medium includes：ROM, RAM, magnetic disc or
Person's CD etc. is various can be with the medium of store program codes.
Finally it should be noted that：Various embodiments above is only used to illustrate the technical scheme of the application, rather than its limitations；To the greatest extent
Pipe has been described in detail with reference to foregoing embodiments to the application, it will be understood by those within the art that：Its according to
The technical scheme described in foregoing embodiments can so be modified, or which part or all technical characteristic are entered
Row equivalent；And these modifications or replacement, the essence of appropriate technical solution is departed from each embodiment technology of the application
The scope of scheme.
Claims (10)
1. a kind of business license printed page analysis method, it is characterised in that including：
Determine at least one of business license connected domain；
The boundary rectangle of each connected domain at least one connected domain is determined, to obtain at least one boundary rectangle；
According at least one boundary rectangle, the locating shaft of preset characters is determined, the character in the business license includes institute
State preset characters；
According to the locating shaft, split the content of the business license, by the content segmentation of the business license at least one
Character；
According at least one character, printed page analysis is carried out to the business license.
2. method according to claim 1, it is characterised in that at least one of described determination business license connected domain it
Before, also include：
Obtain the binary image of the business license；
At least one of determination business license connected domain, including：
Determine at least one of binary image connected domain.
3. method according to claim 1, it is characterised in that described according at least one boundary rectangle, it is determined that in advance
If before the locating shaft of character, also including：
At least one boundary rectangle is filtered, to obtain qualified boundary rectangle at least one boundary rectangle.
4. method according to claim 3, it is characterised in that the qualified boundary rectangle includes：Pixel quantity
Boundary rectangle, transverse and longitudinal less than first threshold than the boundary rectangle less than Second Threshold, the connected domain for including number less than the
The boundary rectangle of three threshold values.
5. the method according to any one of Claims 1 to 4, it is characterised in that described according to described at least one external square
Shape, determines the locating shaft of preset characters, including：
Characteristics of image is extracted to each boundary rectangle at least one boundary rectangle, to obtain set of image characteristics；
Extract the characteristics of image of the preset characters；
Determined from described image feature set with the immediate characteristics of image of the characteristics of image of the preset characters, will described in most
The corresponding boundary rectangle of close image as the preset characters locating shaft.
6. the method according to any one of Claims 1 to 4, it is characterised in that described according to the locating shaft, segmentation is described
The content of business license, by the content segmentation of the business license at least one character, including：
According to the locating shaft, by the content segmentation of the business license at least one character string；
By in each character string maps at least one character string to the business license, after obtaining mapping character strings
Business license；
At least one line character string is extracted from the business license after the mapping character strings with behavior unit；
Each line character string at least one line character string is split, to obtain at least one character.
7. a kind of business license printed page analysis device, it is characterised in that including：
Processing module, for determining at least one of business license connected domain；
Boundary rectangle determining module, the boundary rectangle for determining each connected domain at least one connected domain, to obtain
At least one boundary rectangle；
Locating shaft determining module, for according at least one boundary rectangle, determining the locating shaft of preset characters, the business
Character in license includes the preset characters；
Segmentation module, for according to the locating shaft, splitting the content of the business license, by the content of the business license point
It is cut at least one character；
Analysis module, for according at least one character, printed page analysis being carried out to the business license.
8. device according to claim 7, it is characterised in that
The processing module, the binary image for obtaining the business license is determined in the binary image at least
One connected domain.
9. device according to claim 7, it is characterised in that
The boundary rectangle determining module, is additionally operable in the locating shaft determining module according at least one boundary rectangle,
Before determining the locating shaft of preset characters, at least one boundary rectangle is filtered, to obtain at least one boundary rectangle
In qualified boundary rectangle.
10. device according to claim 9, it is characterised in that the qualified boundary rectangle includes：Pixel quantity
Boundary rectangle, transverse and longitudinal less than first threshold than the boundary rectangle less than Second Threshold, the connected domain for including number less than the
The boundary rectangle of three threshold values.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611200465.7A CN106815561A (en) | 2016-12-22 | 2016-12-22 | Business license printed page analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611200465.7A CN106815561A (en) | 2016-12-22 | 2016-12-22 | Business license printed page analysis method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106815561A true CN106815561A (en) | 2017-06-09 |
Family
ID=59110398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611200465.7A Pending CN106815561A (en) | 2016-12-22 | 2016-12-22 | Business license printed page analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106815561A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108460385A (en) * | 2018-03-02 | 2018-08-28 | 山东超越数控电子股份有限公司 | A kind of Document Segmentation method and apparatus |
| CN110135431A (en) * | 2019-05-16 | 2019-08-16 | 深圳市信联征信有限公司 | The automatic identifying method and system of business license |
| 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 |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101339618A (en) * | 2007-07-06 | 2009-01-07 | 上海思必得通讯技术有限公司 | Mobile phones name card recognition device |
| CN101408937A (en) * | 2008-11-07 | 2009-04-15 | 东莞市微模式软件有限公司 | Method and apparatus for locating character row |
| CN102955941A (en) * | 2011-08-31 | 2013-03-06 | 汉王科技股份有限公司 | Identity information recording method and device |
| CN103839058A (en) * | 2012-11-21 | 2014-06-04 | 方正国际软件(北京)有限公司 | Information locating method for document image based on standard template |
| CN104200209A (en) * | 2014-08-29 | 2014-12-10 | 南京烽火星空通信发展有限公司 | Image text detecting method |
| CN105117706A (en) * | 2015-08-28 | 2015-12-02 | 小米科技有限责任公司 | Image processing method and apparatus and character recognition method and apparatus |
| CN105261110A (en) * | 2015-10-26 | 2016-01-20 | 江苏国光信息产业股份有限公司 | Efficient DSP banknote serial number recognizing method |
| CN105701488A (en) * | 2016-01-01 | 2016-06-22 | 广州恒巨信息科技有限公司 | Identity card identification method |
| CN106056114A (en) * | 2016-05-24 | 2016-10-26 | 腾讯科技（深圳）有限公司 | Business card content identification method and business card content identification device |
| CN106156767A (en) * | 2016-03-02 | 2016-11-23 | 平安科技（深圳）有限公司 | Driving license effect duration extraction method, server and terminal |
-
2016
- 2016-12-22 CN CN201611200465.7A patent/CN106815561A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101339618A (en) * | 2007-07-06 | 2009-01-07 | 上海思必得通讯技术有限公司 | Mobile phones name card recognition device |
| CN101408937A (en) * | 2008-11-07 | 2009-04-15 | 东莞市微模式软件有限公司 | Method and apparatus for locating character row |
| CN102955941A (en) * | 2011-08-31 | 2013-03-06 | 汉王科技股份有限公司 | Identity information recording method and device |
| CN103839058A (en) * | 2012-11-21 | 2014-06-04 | 方正国际软件(北京)有限公司 | Information locating method for document image based on standard template |
| CN104200209A (en) * | 2014-08-29 | 2014-12-10 | 南京烽火星空通信发展有限公司 | Image text detecting method |
| CN105117706A (en) * | 2015-08-28 | 2015-12-02 | 小米科技有限责任公司 | Image processing method and apparatus and character recognition method and apparatus |
| CN105261110A (en) * | 2015-10-26 | 2016-01-20 | 江苏国光信息产业股份有限公司 | Efficient DSP banknote serial number recognizing method |
| CN105701488A (en) * | 2016-01-01 | 2016-06-22 | 广州恒巨信息科技有限公司 | Identity card identification method |
| CN106156767A (en) * | 2016-03-02 | 2016-11-23 | 平安科技（深圳）有限公司 | Driving license effect duration extraction method, server and terminal |
| CN106056114A (en) * | 2016-05-24 | 2016-10-26 | 腾讯科技（深圳）有限公司 | Business card content identification method and business card content identification device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108460385A (en) * | 2018-03-02 | 2018-08-28 | 山东超越数控电子股份有限公司 | A kind of Document Segmentation method and apparatus |
| CN110135431A (en) * | 2019-05-16 | 2019-08-16 | 深圳市信联征信有限公司 | The automatic identifying method and system of business license |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2020200251B2 (en) | Label and field identification without optical character recognition (OCR) | |
| CA2900818C (en) | Systems and methods for tax data capture and use | |
| CN103995904B (en) | A kind of identifying system of image file electronic bits of data | |
| US20200184210A1 (en) | Multi-modal document feature extraction | |
| CA3117374C (en) | Sensitive data detection and replacement | |
| CN111353491B (en) | Text direction determining method, device, equipment and storage medium | |
| CN111695453B (en) | Drawing recognition method and device and robot | |
| CN104182722B (en) | Method for text detection and device and text message extracting method and system | |
| CN108154132A (en) | A kind of identity card text extraction method, system and equipment and storage medium | |
| CN106815561A (en) | Business license printed page analysis method and device | |
| Abramova et al. | Detecting copy–move forgeries in scanned text documents | |
| Baechler et al. | Text line extraction using DMLP classifiers for historical manuscripts | |
| CN114463767A (en) | Credit card identification method, device, computer equipment and storage medium | |
| CN110197140A (en) | Material checking method and equipment based on Text region | |
| WO2017069741A1 (en) | Digitized document classification | |
| CN104182744A (en) | Text detection method and device, and text message extraction method and system | |
| CN113033562A (en) | Image processing method, device, equipment and storage medium | |
| CN114005131A (en) | Certificate character recognition method and device | |
| CN205670326U (en) | There is the bank note inspection pseudo-device of pseudo-coinage type statistics function | |
| CN111931229B (en) | Data identification method, device and storage medium | |
| JP6896260B1 (en) | Layout analysis device, its analysis program and its analysis method | |
| CN113111882A (en) | Card identification method and device, electronic equipment and storage medium | |
| Vasilopoulos et al. | Automatic text extraction from arabic newspapers | |
| Chithra et al. | A Survey on Various Leaf Identification Techniques for Medicinal Plants | |
| JP2022108130A (en) | Information processor and computer program |
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: 20170609 |
|
| RJ01 | Rejection of invention patent application after publication |