CN108171239A - The extracting method of certificate pictograph, apparatus and system, computer storage media - Google Patents
The extracting method of certificate pictograph, apparatus and system, computer storage media Download PDFInfo
- Publication number
- CN108171239A CN108171239A CN201810104851.9A CN201810104851A CN108171239A CN 108171239 A CN108171239 A CN 108171239A CN 201810104851 A CN201810104851 A CN 201810104851A CN 108171239 A CN108171239 A CN 108171239A
- Authority
- CN
- China
- Prior art keywords
- certificate
- image
- character
- text message
- pictograph
- 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
- G06V30/28—Character recognition specially adapted to the type of the alphabet, e.g. Latin alphabet
- G06V30/287—Character recognition specially adapted to the type of the alphabet, e.g. Latin alphabet of Kanji, Hiragana or Katakana characters
Abstract
The present invention provides a kind of extracting method of certificate pictograph, apparatus and system, computer storage media, wherein, method includes：Certificate type is determined according to certificate image；The reference certificate text message of same type is transferred from far-end server according to the certificate type；Extract the character format with reference to certificate text message；Slit mode is determined according to the character format；The certificate image, which is cut, using the slit mode obtains character picture and non-character image.The present invention can effectively cut the character of different fonts form in certificate image, and character identification rate and reliability are high.
Description
Technical field
The present invention relates to technical field of image processing more particularly to it is a kind of extract certificate image Chinese word method, specifically
For be exactly a kind of extracting method of certificate pictograph, apparatus and system, computer storage media.
Background technology
With increasingly dependence of the people to computer technology and network communication, need to calculate a large amount of papery data typing
Machine for example, during movable property and real estate sales/purchase, lease, is scanned certificate, material, qualifications, to historical document,
Books carry out electronic disposal.In order to preferably preserve, retrieving, check word class paper material, people develop word knowledge again
Other technology, automatic identification, extraction picture or photo in text information.
So-called Text region is exactly the technology using Computer Automatic Recognition character, is a weight of application of pattern recognition
Want field.Particularly as being using a large amount of character sample, by complicated neural network learning, corresponding model file is generated,
So as to achieve the purpose that identify character in picture or photo.Wherein, OCR (optical character recognition) texts
Word identification is the representative of character recognition technology.OCR technique mainly identifies the character in shooting, scanned picture, it is necessary first to will scheme
Character string cutting as in is opened, and forms the small picture for including single word, then the word after cutting is identified.Existing text
Character segmentation is sciagraphy into common method, is by after pictograph binary conversion treatment, two are found by vertical projection method
Character segmentation is come according to line of demarcation in line of demarcation between a word.
However, for the certificates such as diploma, business license, between the character in the certificate image of scanning or shooting
Difference is very big, for example, the font of character, character boundary, character color and luster difference are very big in certificate image, and in certificate image
There is adhesion, existing projecting method is difficult the character preferably in cutting certificate image, while cutting quality is good between character
Bad to directly influence OCR Text region effects, correct text information can not be extracted from certificate image by eventually leading to.
Therefore, those skilled in the art improve OCR texts there is an urgent need for researching and developing a kind of method of character in effective cutting certificate image
The accuracy of word identification.
Invention content
In view of this, the technical problem to be solved in the present invention is to provide a kind of extracting method of certificate pictograph, dress
It puts and system, computer storage media, certificate image character segmentation can not be adapted to by solving conventional images word cutting mode,
The problem of causing OCR technique that can not correctly identify character in certificate image.
In order to solve the above-mentioned technical problem, specific embodiment of the invention provides a kind of extraction side of certificate pictograph
Method, including：Certificate type is determined according to certificate image；The ginseng of same type is transferred from far-end server according to the certificate type
Investigate book text message；Extract the character format with reference to certificate text message；Cutting side is determined according to the character format
Formula；The certificate image, which is cut, using the slit mode obtains character picture and non-character image.
The specific embodiment of the present invention also provides a kind of extraction element of certificate pictograph, including：First determines list
Member, for determining certificate type according to certificate image；Unit is transferred, for being transferred according to the certificate type from far-end server
The reference certificate text message of same type；Extraction unit, for extracting the character format with reference to certificate text message；The
Two determination units, for determining slit mode according to the character format；Cutting unit, for being cut using the slit mode
The certificate image obtains character picture and non-character image.
The specific embodiment of the present invention also provides a kind of extraction system of certificate pictograph, including：Multiple extraction dresses
The far-end server put and connect with the extraction element.Wherein, the extraction element is used for true according to the certificate image
Determine certificate type；The far-end server is used to be provided to the offer device according to the certificate type of the certificate image
Reference certificate text message；The extraction element is additionally operable to extract the character format with reference to certificate text message, and root
Slit mode is determined according to the character format, to cut the certificate image using the slit mode.
The specific embodiment of the present invention also provides a kind of computer storage media for including computer executed instructions, described
When computer executed instructions are handled via data processing equipment, which performs the extraction side of certificate pictograph
Method.
Above-mentioned specific embodiment according to the present invention is it is found that the extracting method of certificate pictograph, apparatus and system, meter
Calculation machine storage medium at least has the advantages that：Certificate type is determined according to certificate image first, further according to certificate type
Text message (Chinese, English, number etc.) of the same type with reference to certificate image is transferred from far-end server, extracts text message
Character format, slit mode is then determined according to character format, slit mode is recycled to carry out cutting to certificate image, finally
Identify the character picture after cutting.The present invention can effectively cut the character of different fonts form in certificate image, and be not required to
Complicated neural network model is constructed, character identification rate and reliability are high, adapt to the needs of OCR character recognition technologies.
It is to be understood that above-mentioned general description and detailed description below are merely illustrative and illustrative, not
It can the limitation range of the invention to be advocated.
Description of the drawings
Following appended attached drawing is the part of specification of the present invention, depicts example embodiments of the present invention, institute
Attached drawing is used for illustrating the principle of the present invention together with the description of specification.
Fig. 1 is the stream of the embodiment one of the extracting method of a kind of certificate pictograph that the specific embodiment of the invention provides
Cheng Tu.
Fig. 2 is the stream of the embodiment two of the extracting method of a kind of certificate pictograph that the specific embodiment of the invention provides
Cheng Tu.
Fig. 3 is the stream of the embodiment three of the extracting method of a kind of certificate pictograph that the specific embodiment of the invention provides
Cheng Tu.
Fig. 4 is the stream of the example IV of the extracting method of a kind of certificate pictograph that the specific embodiment of the invention provides
Cheng Tu.
Fig. 5 is the knot of the embodiment one of the extraction element of a kind of certificate pictograph that the specific embodiment of the invention provides
Structure schematic diagram.
Fig. 6 is the knot of the embodiment two of the extraction element of a kind of certificate pictograph that the specific embodiment of the invention provides
Structure schematic diagram.
Fig. 7 is the knot of the embodiment three of the extraction element of a kind of certificate pictograph that the specific embodiment of the invention provides
Structure schematic diagram.
Fig. 8 is the knot of the example IV of the extraction element of a kind of certificate pictograph that the specific embodiment of the invention provides
Structure schematic diagram.
Fig. 9 is the application schematic diagram of the extraction system of a kind of certificate pictograph that the specific embodiment of the invention provides.
Specific embodiment
Purpose, technical scheme and advantage to make the embodiment of the present invention are more clearly understood, below will with attached drawing and in detail
Narration clearly illustrates the spirit of disclosed content, and any skilled artisan is understanding the content of present invention
After embodiment, when the technology that can be taught by the content of present invention, it is changed and modifies, without departing from the essence of the content of present invention
God and range.
The illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but not as a limitation of the invention.
In addition, element/component of the same or like label used in drawings and the embodiments is for representing same or like portion
Point.
About " first " used herein, " second " ... etc., not especially censure the meaning of order or cis-position,
It is non-to limit the present invention, only for distinguishing the element described with same technique term or operation.
About direction term used herein, such as：Upper and lower, left and right, front or rear etc. are only the sides of refer to the attached drawing
To.Therefore, the direction term used is intended to be illustrative and not intended to limit this creation.
It is open term, i.e., about "comprising" used herein, " comprising ", " having ", " containing " etc.
Mean including but not limited to.
About it is used herein " and/or ", including any of the things or all combination.
Include " two " and " two or more " about " multiple " herein；Include " two groups " about " multigroup " herein
And " more than two ".
About term used herein " substantially ", " about " etc., to modify it is any can be with the quantity or mistake of microvariations
Difference, but this slight variations or error can't change its essence.In general, microvariations that such term is modified or error
Range in some embodiments can be 20%, in some embodiments can be 10%, can be in some embodiments 5% or its
His numerical value.It will be understood by those skilled in the art that the aforementioned numerical value referred to can be adjusted according to actual demand, it is not limited thereto.
It is certain to describe the word of the application by lower or discuss in the other places of this specification, to provide art technology
Personnel's guiding additional in relation to the description of the present application.
Fig. 1 is the stream of the embodiment one of the extracting method of a kind of certificate pictograph that the specific embodiment of the invention provides
Cheng Tu as shown in Figure 1, transferring the reference certificate text message of same type from far-end server according to certificate type, and is extracted
With reference to the character format of certificate text message, slit mode is determined further according to character format, is finally cut and demonstrate,proved using slit mode
Book image.
In the specific embodiment shown in the drawings, the extracting method of certificate pictograph includes：
Step 101：Certificate type is determined according to certificate image.In specific embodiments of the present invention, certificate can be graduation
Card, marriage certificate, business license, honorary certificate etc.；Certificate image is the scanned copy of above-mentioned certificate or shooting photo.Certificate type
For specific certificate issued department provide particular certificate, for example, certain colleges and universities provide diploma.
Step 102：The reference certificate text message of same type is transferred from far-end server according to the certificate type.This
In the specific embodiment of invention, far-end server can be cloud server, server cluster etc..With reference to certificate text message just
Refer to that the text on certificate image can be edited.
Step 103：Extract the character format with reference to certificate text message.In specific embodiments of the present invention, reference
The character format of certificate text message is with specific reference to character boundary, character font, font color of certificate text message etc..
Step 104：Slit mode is determined according to the character format.In specific embodiments of the present invention, by corresponding
Slit mode can be just rationally separated by the character in certificate image, convenient for later stage OCR Text region.
Step 105：The certificate image, which is cut, using the slit mode obtains character picture and non-character image.This hair
In bright specific embodiment, character picture refers in image as a character (such as Chinese character, number, English word), non-character figure
As referring in image as mark (e.g., figure, insignia, personage etc.).
Referring to Fig. 1, the reference certificate text of same type is transferred from far-end server according to the certificate type of certificate image
Information, slit mode is determined using with reference to the character format of certificate text message, and certificate image is cut using slit mode, can be with
Slit mode is rationally determined with reference to the form of certificate image context sheet, so as to which the character in certificate image is rationally separated,
Improve the accuracy and discrimination of OCR Text regions.
Fig. 2 is the stream of the embodiment two of the extracting method of a kind of certificate pictograph that the specific embodiment of the invention provides
Cheng Tu, as shown in Fig. 2, after cutting certificate image using slit mode, identification character picture obtains editable digital certificate text
This information.
In the specific embodiment shown in the drawings, after step 105, the extracting method of certificate pictograph further includes：
Step 106：Identify that the character picture obtains editable digital certificate text message.Specifically, it can utilize
OCR character recognition technologies identify character picture, and obtained editable digital certificate text message does not have any special form, text
Information can be edited, be deleted.
Referring to Fig. 2, editable digital certificate text message is obtained using OCR character recognition technologies identification character picture, side
Just user edits, and user experience is good.
Fig. 3 is the stream of the embodiment three of the extracting method of a kind of certificate pictograph that the specific embodiment of the invention provides
Cheng Tu, as shown in figure 3, after identification character picture obtains editable digital certificate text message, using character format, editor can
Digital certificate text message is edited, certificate graphs are restored according to non-character image and edited editable digital certificate text message
Picture.
In the specific embodiment shown in the drawings, after step 106, the extracting method of certificate pictograph further includes：
Step 107：Utilize editable digital certificate text message described in the character format editor.The specific reality of the present invention
It applies in example, after character format editor's editable digital certificate text message, the form and card of digital certificate text message
The form of book image context sheet is identical.
Step 108：Contained according to the non-character image and the edited editable digital certificate text message recovery
There is the certificate image of the editable digital certificate text message.In specific embodiments of the present invention, by non-character image
It is punctured into edited editable digital certificate text message, the final space of a whole page for restoring certificate image.
Referring to Fig. 3, restore certificate image, card using non-character image and edited editable digital certificate text message
Text message can be edited in book image, facilitate editor and the storage of certificate image, meet the particular demands of user.
Fig. 4 is the stream of the example IV of the extracting method of a kind of certificate pictograph that the specific embodiment of the invention provides
Cheng Tu, as shown in figure 4, determining certificate type according to certificate image.
In the specific embodiment shown in the drawings, step 101 specifically includes：
Step 1011：Extract the main feature of the certificate image.In specific embodiments of the present invention, the master of certificate image
Feature is wanted to include：Realizing text information, identification information, layout information etc. in certificate image.For example, in marriage certificate image
" marriage certificate " three words, the layout information of marriage certificate is the main feature of certificate image.
Step 1012：The certificate type is determined according to the main feature.In specific embodiments of the present invention, according to card
One or more main features of book image determine certificate type.
Referring to Fig. 4, certificate type is determined according to certificate image like clockwork, so as to according to certificate type from remote service
Device accurately transfers the reference certificate text message of same type.
Fig. 5 is the knot of the embodiment one of the extraction element of a kind of certificate pictograph that the specific embodiment of the invention provides
Structure schematic diagram, device as shown in Figure 5 can be applied in Fig. 1~method shown in Fig. 4, according to certificate type from remote service
Device transfers the reference certificate text message of same type, and extracts the character format with reference to certificate text message, further according to character
Form determines slit mode, finally cuts certificate image using slit mode.
In the specific embodiment shown in the drawings, the extraction element of certificate pictograph includes：First determination unit 1,
Transfer unit 2, extraction unit 3, the second determination unit 4 and cutting unit 5.Wherein, the first determination unit 1 is used for according to certificate graphs
As determining certificate type；It transfers unit 2 and is demonstrate,proved for transferring the reference of same type from far-end server according to the certificate type
Book text message；Extraction unit 3 is used to extract the character format with reference to certificate text message；Second determination unit 4 is used for
Slit mode is determined according to the character format；Cutting unit 5 is used to obtain using the slit mode cutting certificate image
To character picture and non-character image.
Referring to Fig. 5, the reference certificate text of same type is transferred from far-end server according to the certificate type of certificate image
Information, slit mode is determined using with reference to the character format of certificate text message, and certificate image is cut using slit mode, can be with
Slit mode is rationally determined with reference to the form of certificate image context sheet, so as to which the character in certificate image is rationally separated,
Improve the accuracy and discrimination of OCR Text regions.
Fig. 6 is the knot of the embodiment two of the extraction element of a kind of certificate pictograph that the specific embodiment of the invention provides
Structure schematic diagram, as shown in fig. 6, after cutting certificate image using slit mode, identification character picture obtains editable number card
Book text message.
In the specific embodiment shown in the drawings, the extraction element of certificate pictograph further includes recognition unit 6.Its
In, recognition unit 6 is used to identify that the character picture obtains editable digital certificate text message.
Referring to Fig. 6, editable digital certificate text message is obtained using OCR character recognition technologies identification character picture, side
Just user edits, and user experience is good.
Fig. 7 is the knot of the embodiment three of the extraction element of a kind of certificate pictograph that the specific embodiment of the invention provides
Structure schematic diagram as shown in fig. 7, after identification character picture obtains editable digital certificate text message, is compiled using character format
Editable digital certificate text message is collected, card is restored according to non-character image and edited editable digital certificate text message
Book image.
In the specific embodiment shown in the drawings, the extraction element of certificate pictograph further includes：Edit cell 7 and extensive
Multiple unit 8.Wherein, edit cell 7 is used to utilize editable digital certificate text message described in the character format editor；Restore
Unit 8 is used for can containing described according to the non-character image and the edited editable digital certificate text message recovery
Edit the certificate image of digital certificate text message.
Referring to Fig. 7, restore certificate image, card using non-character image and edited editable digital certificate text message
Text message can be edited in book image, facilitate editor and the storage of certificate image, meet the particular demands of user.
Fig. 8 is the knot of the example IV of the extraction element of a kind of certificate pictograph that the specific embodiment of the invention provides
Structure schematic diagram, as shown in figure 8, the first determination unit specifically includes the extraction module of the main feature of extraction certificate image and determines
The determining module of certificate type.
In the specific embodiment shown in the drawings, the first determination unit 1 specifically includes extraction module 11 and determining module
12.Wherein, first determination unit 1 specifically includes：Extraction module 11 is used to extract the main feature of the certificate image；Really
Cover half block 12 is used to determine the certificate type according to the main feature.
Referring to Fig. 8, certificate type is determined according to certificate image like clockwork, so as to according to certificate type from remote service
Device accurately transfers the reference certificate text message of same type
Fig. 9 is the application schematic diagram of the extraction system of a kind of certificate pictograph that the specific embodiment of the invention provides,
As shown in figure 9, the system includes：Multiple extraction elements 100 and the far-end server being connect with the extraction element 100
200.Wherein, the extraction element 100 is used to determine certificate type according to the certificate image；The far-end server 200 is used
In the reference certificate text message that the certificate type according to the certificate image is provided to the offer device 100；It is described
Extraction element 100 is additionally operable to extract the character format with reference to certificate text message, and determine to cut according to the character format
The mode of dividing, to cut the certificate image using the slit mode.
Referring to Fig. 9, the character of different fonts form in certificate image can be effectively cut, and not need to construction complexity
Neural network model, character identification rate and reliability are high, adapt to the needs of OCR character recognition technologies.
The specific embodiment of the invention provides a kind of computer storage media for including computer executed instructions, the computer
When execute instruction is handled via data processing equipment, which performs the extracting method of certificate pictograph.Method
Include the following steps：
Step 101：Certificate type is determined according to certificate image.
Step 102：The reference certificate text message of same type is transferred from far-end server according to the certificate type.
Step 103：Extract the character format with reference to certificate text message.
Step 104：Slit mode is determined according to the character format.
Step 105：The certificate image, which is cut, using the slit mode obtains character picture and non-character image.
The specific embodiment of the invention also provides a kind of computer storage media for including computer executed instructions, the calculating
When machine execute instruction is handled via data processing equipment, which performs the extracting method of certificate pictograph.Side
Method includes the following steps：
Step 101：Certificate type is determined according to certificate image.
Step 102：The reference certificate text message of same type is transferred from far-end server according to the certificate type.
Step 103：Extract the character format with reference to certificate text message.
Step 104：Slit mode is determined according to the character format.
Step 105：The certificate image, which is cut, using the slit mode obtains character picture and non-character image.
Step 106：Identify that the character picture obtains editable digital certificate text message.
The specific embodiment of the invention also provides a kind of computer storage media for including computer executed instructions, the calculating
When machine execute instruction is handled via data processing equipment, which performs the extracting method of certificate pictograph.Side
Method includes the following steps：
Step 101：Certificate type is determined according to certificate image.
Step 102：The reference certificate text message of same type is transferred from far-end server according to the certificate type.
Step 103：Extract the character format with reference to certificate text message.
Step 104：Slit mode is determined according to the character format.
Step 105：The certificate image, which is cut, using the slit mode obtains character picture and non-character image.
Step 106：Identify that the character picture obtains editable digital certificate text message.
Step 107：Utilize editable digital certificate text message described in the character format editor.
Step 108：Contained according to the non-character image and the edited editable digital certificate text message recovery
There is the certificate image of the editable digital certificate text message.
The specific embodiment of the invention provides a kind of computer storage media for including computer executed instructions, the computer
When execute instruction is handled via data processing equipment, which performs the extracting method of certificate pictograph.Method
Include the following steps：
Step 1011：Extract the main feature of the certificate image.
Step 1012：The certificate type is determined according to the main feature.
Step 102：The reference certificate text message of same type is transferred from far-end server according to the certificate type.
Step 103：Extract the character format with reference to certificate text message.
Step 104：Slit mode is determined according to the character format.
Step 105：The certificate image, which is cut, using the slit mode obtains character picture and non-character image.
The specific embodiment of the invention provides a kind of extracting method of certificate pictograph, apparatus and system, computer storage
Medium determines certificate type according to certificate image first, and same type reference is transferred from far-end server further according to certificate type
The text message (Chinese, English, number etc.) of certificate image extracts the character format of text message, then according to character format
It determines slit mode, slit mode is recycled to carry out cutting to certificate image, finally identify the character picture after cutting.The present invention
The character of different fonts form in certificate image can be effectively cut, and not need to the complicated neural network model of construction, word
It accords with discrimination and reliability is high, adapt to the needs of OCR character recognition technologies.
The above-mentioned embodiment of the present invention can be implemented in various hardware, Software Coding or both combination.For example, this hair
Bright embodiment, which is alternatively in data signal processor (Digital Signal Processor, DSP), performs the above method
Program code.The present invention can also refer to computer processor, digital signal processor, microprocessor or field-programmable gate array
Arrange the multiple functions that (Field Programmable Gate Array, FPGA) is performed.Can above-mentioned processing be configured according to the present invention
Device performs particular task, and the machine-readable software code of ad hoc approach or the firmware generation that the present invention discloses are defined by performing
Code is completed.Software code or firmware code can be developed into different program languages and different forms or form.Or
Different target platform composing software codes.However, in generation, is configured according to the software code of execution task of the present invention and other types
Different code pattern, type and the language of code do not depart from spirit and scope of the invention.
The foregoing is merely the schematical specific embodiment of the present invention, before the design of the present invention and principle is not departed from
It puts, the equivalent variations and modification that any those skilled in the art is made should all belong to the scope of protection of the invention.
Claims (10)
1. a kind of extracting method of certificate pictograph, which is characterized in that this method includes：
Certificate type is determined according to certificate image；
The reference certificate text message of same type is transferred from far-end server according to the certificate type；
Extract the character format with reference to certificate text message；
Slit mode is determined according to the character format；And
The certificate image, which is cut, using the slit mode obtains character picture and non-character image.
2. the extracting method of certificate pictograph as described in claim 1, which is characterized in that cut using the slit mode
After the step of certificate image, this method further includes：
Identify that the character picture obtains editable digital certificate text message.
3. the extracting method of certificate pictograph as claimed in claim 2, which is characterized in that identify that the character picture obtains
After the step of editable digital certificate text message, this method further includes：
Utilize editable digital certificate text message described in the character format editor；And
Restore to contain the editable according to the non-character image and the edited editable digital certificate text message
The certificate image of digital certificate text message.
4. the extracting method of certificate pictograph as described in claim 1, which is characterized in that certificate is determined according to certificate image
The step of type, specifically includes：
Extract the main feature of the certificate image；And
The certificate type is determined according to the main feature.
5. a kind of extraction element of certificate pictograph, which is characterized in that the device includes：
First determination unit, for determining certificate type according to certificate image；
Unit is transferred, for transferring the reference certificate text message of same type from far-end server according to the certificate type；
Extraction unit, for extracting the character format with reference to certificate text message；
Second determination unit, for determining slit mode according to the character format；And
Cutting unit obtains character picture and non-character image for cutting the certificate image using the slit mode.
6. the extraction element of certificate pictograph as claimed in claim 5, which is characterized in that the device further includes：
Recognition unit, for identifying that the character picture obtains editable digital certificate text message.
7. the extraction element of certificate pictograph as claimed in claim 6, which is characterized in that the device further includes：
Edit cell, for utilizing editable digital certificate text message described in the character format editor；And
Recovery unit, for being contained according to the non-character image and the edited editable digital certificate text message recovery
There is the certificate image of the editable digital certificate text message.
8. the extraction element of certificate pictograph as claimed in claim 5, which is characterized in that first determination unit is specific
Including：
Extraction module, for extracting the main feature of the certificate image；And
Determining module, for determining the certificate type according to the main feature.
9. a kind of extraction system of certificate pictograph, which is characterized in that the system includes：Multiple such as claims 5~8 are any
The extraction element and the far-end server being connect with the extraction element, wherein,
The extraction element is used to determine certificate type according to the certificate image；
The far-end server is used for the reference provided according to the certificate type of the certificate image to the offer device
Certificate text message；
The extraction element is additionally operable to extract the character format with reference to certificate text message, and true according to the character format
Slit mode is determined, to cut the certificate image using the slit mode.
10. a kind of computer storage media for including computer executed instructions, the computer executed instructions are via data processing
During equipment processing, the extracting method of 1~4 any certificate pictograph of data processing equipment perform claim requirement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810104851.9A CN108171239A (en) | 2018-02-02 | 2018-02-02 | The extracting method of certificate pictograph, apparatus and system, computer storage media |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810104851.9A CN108171239A (en) | 2018-02-02 | 2018-02-02 | The extracting method of certificate pictograph, apparatus and system, computer storage media |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108171239A true CN108171239A (en) | 2018-06-15 |
Family
ID=62513061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810104851.9A Pending CN108171239A (en) | 2018-02-02 | 2018-02-02 | The extracting method of certificate pictograph, apparatus and system, computer storage media |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108171239A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110442744A (en) * | 2019-08-09 | 2019-11-12 | 泰康保险集团股份有限公司 | Extract method, apparatus, electronic equipment and the readable medium of target information in image |
| CN111160395A (en) * | 2019-12-05 | 2020-05-15 | 北京三快在线科技有限公司 | Image recognition method and device, electronic equipment and storage medium |
| WO2020113561A1 (en) * | 2018-12-07 | 2020-06-11 | 华为技术有限公司 | Method for extracting structural data from image, apparatus and device |
| CN111405191A (en) * | 2020-04-24 | 2020-07-10 | Oppo（重庆）智能科技有限公司 | Image management method, device, terminal and storage medium |
| CN112686237A (en) * | 2020-12-21 | 2021-04-20 | 福建新大陆软件工程有限公司 | Certificate OCR recognition method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10272874A (en) * | 1997-03-31 | 1998-10-13 | Toppan Forms Co Ltd | Cut form with variable information and method for forming the information |
| CN102402684A (en) * | 2010-09-15 | 2012-04-04 | 富士通株式会社 | Method and device for determining type of certificate and method and device for translating certificate |
| CN103885723A (en) * | 2014-03-04 | 2014-06-25 | 广东数字证书认证中心有限公司 | Digital certificate storage method, digital certificate storage system, digital certificate reading method and digital certificate reading system |
| US20140219561A1 (en) * | 2013-02-06 | 2014-08-07 | Nidec Sankyo Corporation | Character segmentation device and character segmentation method |
| CN104079587A (en) * | 2014-07-21 | 2014-10-01 | 深圳天祥质量技术服务有限公司 | Certificate identification device and certificate check system |
| CN106886776A (en) * | 2017-02-23 | 2017-06-23 | 山东浪潮云服务信息科技有限公司 | The application model of license electronization is realized in a kind of utilization image recognition |
-
2018
- 2018-02-02 CN CN201810104851.9A patent/CN108171239A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10272874A (en) * | 1997-03-31 | 1998-10-13 | Toppan Forms Co Ltd | Cut form with variable information and method for forming the information |
| CN102402684A (en) * | 2010-09-15 | 2012-04-04 | 富士通株式会社 | Method and device for determining type of certificate and method and device for translating certificate |
| US20140219561A1 (en) * | 2013-02-06 | 2014-08-07 | Nidec Sankyo Corporation | Character segmentation device and character segmentation method |
| CN103885723A (en) * | 2014-03-04 | 2014-06-25 | 广东数字证书认证中心有限公司 | Digital certificate storage method, digital certificate storage system, digital certificate reading method and digital certificate reading system |
| CN104079587A (en) * | 2014-07-21 | 2014-10-01 | 深圳天祥质量技术服务有限公司 | Certificate identification device and certificate check system |
| CN106886776A (en) * | 2017-02-23 | 2017-06-23 | 山东浪潮云服务信息科技有限公司 | The application model of license electronization is realized in a kind of utilization image recognition |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020113561A1 (en) * | 2018-12-07 | 2020-06-11 | 华为技术有限公司 | Method for extracting structural data from image, apparatus and device |
| CN111615702A (en) * | 2018-12-07 | 2020-09-01 | 华为技术有限公司 | Method, device and equipment for extracting structured data from image |
| CN111615702B (en) * | 2018-12-07 | 2023-10-17 | 华为云计算技术有限公司 | Method, device and equipment for extracting structured data from image |
| CN110442744A (en) * | 2019-08-09 | 2019-11-12 | 泰康保险集团股份有限公司 | Extract method, apparatus, electronic equipment and the readable medium of target information in image |
| CN110442744B (en) * | 2019-08-09 | 2022-11-04 | 泰康保险集团股份有限公司 | Method and device for extracting target information in image, electronic equipment and readable medium |
| CN111160395A (en) * | 2019-12-05 | 2020-05-15 | 北京三快在线科技有限公司 | Image recognition method and device, electronic equipment and storage medium |
| WO2021110174A1 (en) * | 2019-12-05 | 2021-06-10 | 北京三快在线科技有限公司 | Image recognition method and device, electronic device, and storage medium |
| CN111405191A (en) * | 2020-04-24 | 2020-07-10 | Oppo（重庆）智能科技有限公司 | Image management method, device, terminal and storage medium |
| CN112686237A (en) * | 2020-12-21 | 2021-04-20 | 福建新大陆软件工程有限公司 | Certificate OCR recognition method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108171239A (en) | The extracting method of certificate pictograph, apparatus and system, computer storage media | |
| CN109308476B (en) | Billing information processing method, system and computer readable storage medium | |
| CN111046784A (en) | Document layout analysis and identification method and device, electronic equipment and storage medium | |
| CN110442744A (en) | Extract method, apparatus, electronic equipment and the readable medium of target information in image | |
| JP4993319B2 (en) | Apparatus and method for supporting verification of software internationalization | |
| CN114299528B (en) | Information extraction and structuring method for scanned document | |
| CN108090445A (en) | The electronics of a kind of papery operation or paper corrects method | |
| CN108090400A (en) | A kind of method and apparatus of image text identification | |
| CN111652232A (en) | Bill identification method and device, electronic equipment and computer readable storage medium | |
| CN112508011A (en) | OCR (optical character recognition) method and device based on neural network | |
| CN111062791A (en) | Method, device and equipment for reimbursing and filling bill | |
| CN106980857B (en) | Chinese calligraphy segmentation and recognition method based on copybook | |
| CN110516664A (en) | Bank slip recognition method, apparatus, electronic equipment and storage medium | |
| CN109271951A (en) | A kind of method and system promoting book keeping operation review efficiency | |
| CN110210470A (en) | Merchandise news image identification system | |
| CN110458014A (en) | Answering card reading method, device and computer readable storage medium | |
| JP2019079347A (en) | Character estimation system, character estimation method, and character estimation program | |
| CN109992752A (en) | Label labeling method, device, computer installation and the storage medium of contract documents | |
| CN112668580A (en) | Text recognition method, text recognition device and terminal equipment | |
| CN109726369A (en) | A kind of intelligent template questions record Implementation Technology based on normative document | |
| Elanwar et al. | Extracting text from scanned Arabic books: a large-scale benchmark dataset and a fine-tuned Faster-R-CNN model | |
| CN111144445A (en) | Error detection method and system for printing book and periodical writing format and electronic equipment | |
| CN115130437B (en) | Intelligent document filling method and device and storage medium | |
| CN115690819A (en) | Big data-based identification method and system | |
| Kumar et al. | Line based robust script identification for indianlanguages |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 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: 20180615 |