CN105809157A - Answer sheet modeling method and device - Google Patents
Answer sheet modeling method and device Download PDFInfo
- Publication number
- CN105809157A CN105809157A CN201410838311.5A CN201410838311A CN105809157A CN 105809157 A CN105809157 A CN 105809157A CN 201410838311 A CN201410838311 A CN 201410838311A CN 105809157 A CN105809157 A CN 105809157A
- Authority
- CN
- China
- Prior art keywords
- answering card
- card
- region
- user
- answering
- 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
Landscapes
- Character Discrimination (AREA)
- Character Input (AREA)
Abstract
The invention provides an answer sheet modeling method, comprising the steps of pre-establishing a feature database storing each region feature of an answer sheet; scanning the user answer sheet to obtain an electronic image of the user answer sheet; performing OCR (Optical Character Recognition) character recognition and graphic symbol recognition on the electronic image; judging the position of each region of the user answer sheet according to the recognition results and the region features in the feature database; and establishing an electronic model of the answer sheet according to the position of each region. The invention further provides an answer sheet modeling device, comprising a feature database, a scan module, a recognition module, a judgment module and a modeling module. The method and the device can recognize multiple answer sheets by establishing electronic models.
Description
Technical field
The invention belongs to teaching information equipment technical field, more specifically, particularly to a kind of answering card modeling method and device.
Background technology
Answering card is the carrier of optical character reader (OCR) input information, is the general name of the various Data Enter forms of supporting optical character reader (OCR).The information that user needs is converted into selectable option by answering card, scribbles for user.Optical character reader (OCR) according to the painting of information point be not coated with and formatted file is arranged information reverting.The style of answering card, the information according to input computer the form required by the design specification of optical character reader (OCR) is needed to design, namely the pattern of answering card compares and is limited to, optical character reader (OCR) of the prior art often only can recognise that a kind of standard answer card, when the pattern typesetting of answering card changes, then optical character reader (OCR) None-identified.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of answering card modeling method and device, in order to solve above-mentioned technical problem.
For this, the invention provides a kind of answering card modeling method, including step:
Step A, pre-builds that storage has the property data base of answering card regional feature；
Step B, scans user's answering card, obtains the electronic image of user's answering card；
Step C, carries out OCR Text region and graphic symbol recognition to described electronic image；
Step D, according to recognition result and the provincial characteristics in described property data base, it is judged that each regional location of user's answering card；
Step E, according to each regional location, sets up answering card electronic model.
Wherein, described electronic image is carried out by described step C graphic symbol recognition to include carrying out rectangle identification and bracket identification.
Wherein, described step D is according to recognition result and the provincial characteristics in property data base, it is judged that each regional location of user's answering card includes step:
Identify and in a bigger rectangle, have the region being connected more than 4 less rectangle frames, then judge that this bigger rectangular area is as admission card for entrance examination region.
Wherein, described step D is according to recognition result and the provincial characteristics in property data base, it is judged that each regional location of user's answering card includes step:
If by Distance Judgment, identifying and have horizontal tetrad, three graphical symbols in a rectangle apart from identical, and have the many groups of set of pixels chalaza meeting this rule, then judge that this rectangular area is as multiple-choice question answer region.
Wherein, according to each regional location in described step E, set up answering card electronic model and include step:
" [] " that go out at admission card for entrance examination region recognition is longitudinally inserted successively numeral 0-9.
Wherein, according to each regional location in described step E, set up answering card electronic model and include step:
" [] " that four is one group at multiple-choice question answer region recognition is laterally sequentially filled letter A, B, C, D.
Wherein, according to each regional location in described step E, set up answering card electronic model and include step:
The handwriting area that will identify that and name region are directly replicated as the handwriting area in electric answer card model and name region.
Wherein, setting up storage in described step A has the property data base of answering card regional feature, has the property data base of name region characteristic of field, admission card for entrance examination provincial characteristics, answer provincial characteristics and borderline region feature including setting up storage.
Wherein, after described step B, before step C, further comprise the steps of:
Described electronic image is carried out binary conversion treatment.
The present invention also provides for a kind of answering card model building device, including property data base, scan module, identification module, judge module and MBM；
Described property data base, is used for storing answering card regional feature；
Described scan module, is used for scanning user's answering card, obtains the electronic image of user's answering card；
Described identification module, for carrying out OCR Text region and graphic symbol recognition to described electronic image；
Described judge module, for according to recognition result and the provincial characteristics in described property data base, it is judged that each regional location of user's answering card；
Described MBM, for according to each regional location, setting up answering card electronic model.
The invention provides a kind of answering card modeling method and device, by gathering the electrical image data of user's answering card, by each provincial characteristics and image recognition technology, judge the position in this each region of user's answering card, and then each region content is correspondingly placed in electric answer card model, setting up one can by the standard electronic answering card model of optical character reader (OCR) identification, so, the answering card of plurality of specifications and typesetting, by the modeling method of this present invention and device, all can be exchanged into general electric answer card model, so just the technical problem that only can recognise that a kind of answering card in prior art is solved.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, the accompanying drawing used required in embodiment or description of the prior art will be briefly described below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the premise not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
The schematic flow sheet of a kind of answering card modeling method that Fig. 1 provides for the embodiment of the present invention；
The structural representation of a kind of answering card model building device that Fig. 2 provides for the embodiment of the present invention.
Detailed description of the invention
For making the object, technical solutions and advantages of the present invention clearly understand, below in conjunction with specific embodiment, and with reference to accompanying drawing, the present invention is described in more detail.
In order to make those skilled in the art be more fully understood that the present invention, below in conjunction with the drawings and specific embodiments, the present invention is described in further detail.
Embodiments provide a kind of answering card modeling method, shown in Figure 1, comprise the steps:
Step S110, pre-builds that storage has the property data base of answering card regional feature.
Feature according to each region of various answering cards, for instance: multiple-choice question answer choice is all ABCD tetra-, and admission card for entrance examination number will be higher than 4, and the frame in each region is obvious rectangle frame etc., adds up these features and sets up a property data base.
As a kind of embodiment, property data base should comprise name region characteristic of field, admission card for entrance examination provincial characteristics, answer provincial characteristics and borderline region feature etc..
Step S111, scans user's answering card, obtains the electronic image of user's answering card.
By user's answering card data that high photographing instrument gathers, first image binaryzation being processed, first temporarily draw an electronic model, electronic model now also cannot be identified.
Step S112, carries out OCR Text region and graphic symbol recognition to described electronic image；
In embodiments of the present invention, answering card identification comprises OCR Text region and rectangle frame and multiple-choice question option identification.
Multiple answering card is all made up of rectangle frame miscellaneous (including frame solid, hollow, big and little frame), character area, multiple-choice question answer choice identifier " [] ", and mostly using rectangle frame as demarcation line.So identify and reformed into identification rectangle, OCR Text region and " [] " identification.Wherein rectangular characteristic clearly and is very regular figure, and therefore more easy to identify, algorithm complex is low.Even if the unidentified success of some part of rectangle, such as rectangle has lacked one jiao, it is also possible to by algorithm, scarce foot is coupled together.
Multiple-choice question option includes the multiple implementation such as square brackets, round parentheses, it is not limited only to square brackets " [] " when namely identifying, can also is that round parentheses " () " etc., namely for " (A) (B) (C) (D) " this type of answering card, the technology design provided according to the embodiment of the present invention also can recognise that.
The shape in the actual region on user's answering card is likely and irregular rectangle, now can be processed by relevant image recognition algorithm, processes the rectangle into rule.
Preferably, identify complete after, be corrected.
OCR (OpticalCharacterRecognition) Text region is prior art, and the embodiment of the present invention repeats no more.
Step S113, according to recognition result and the provincial characteristics in described property data base, it is judged that each regional location of user's answering card.
Identify and in a bigger rectangle, have the region being connected more than 4 less rectangle frames, then judge that this bigger rectangular area is as admission card for entrance examination region.
For the figure place of admission card for entrance examination, then the figure place obtained can be passed to common variable.
If by Distance Judgment, identifying and have horizontal tetrad, three graphical symbols in a rectangle apart from identical, and have the many groups of set of pixels chalaza meeting this rule, then judge that this rectangular area is as multiple-choice question answer region.
When setting up model, answering card then can be divided into four parts: name region, admission card for entrance examination region, text region, borderline region, different answering card Probability Areas is inconsistent, but the aspect ratio of these four parts is more apparent, this four subregion of labelling in embodiments of the present invention, zones of different adopts different feature recognition algorithms, can reduce algorithm degree of being responsible for.Simultaneously by this tetrameric position judgment, also the card can distinguished under camera lens is the discernible answering card of standard.
Step S114, according to each regional location, sets up answering card electronic model.
After carrying out OCR Text region and graphic symbol recognition, it is possible to the feature according to admission card for entrance examination region and multiple-choice question answer region, it is determined that the particular location in each region in user's answering card.After position is determined, admission card for entrance examination region and multiple-choice question answer region need the answer information entrained by user's answering card electronic image and number information, carry out data exchange, change into the number information in admission card for entrance examination region corresponding in electric answer card model and multiple-choice question answer region and answer information.
Such as some answering card is [A], band letter in [B], if analyzed, [] has word, then need not judge that concrete letter is how many, from left to right, directly fill with A, B, C, D, formed [A] [B] [C] [D], be about to " [] " that four is one group at multiple-choice question answer region recognition and be laterally sequentially filled letter A, B, C, D；In some answering card bracket and without word, but every one letter " A " of string subscript, such Direct Recognition is [].
Ibid, wherein comprise numeral, as long as judging that [] has content, directly longitudinally inserting numeral 0-9 successively, forming [0], [1], [2], [3] ....
Admission card for entrance examination region and the two region, multiple-choice question answer region need data to exchange, so needing to read specifically what data.And to other regions such as name region or hand-written answers, then according to the area size in original subscriber's answering card and shape, directly replicate and place in model.
The embodiment of the present invention also provides for a kind of answering card model building device, shown in Figure 2, including property data base, scan module, identification module, judge module and MBM.
Property data base, is used for storing answering card regional feature.
Scan module, is used for scanning user's answering card, obtains the electronic image of user's answering card.
Identification module, for carrying out OCR Text region and graphic symbol recognition to described electronic image.
Judge module, for according to recognition result and the provincial characteristics in described property data base, it is judged that each regional location of user's answering card.
MBM, for according to each regional location, setting up answering card electronic model.
All there is a defect in answer sheet recognition device of the prior art, can only identify specific answering card, thus causes the limitation of software.The technical scheme that the embodiment of the present invention provides, gather user by high photographing instrument and require the electronic image of the answering card supported, by 2D modeling pattern, software can automatically according to existing answering card profile, it is converted into electronic edition answering card, automatically identifies and automatically set up corresponding electronic model, in order to software can support rapidly this answering card, and support this answering card to print, so can realize multiple answering card and identify simultaneously.
Described above to the disclosed embodiments, makes professional and technical personnel in the field be capable of or uses invention.The multiple amendment of these embodiments be will be apparent from for those skilled in the art, and generic principles defined herein can without departing from the spirit or scope of the present invention, realize in other embodiments.Therefore, the present invention is not intended to be limited to the embodiments shown herein, and is to fit to the widest scope consistent with principles disclosed herein and features of novelty.
Claims (10)
1. an answering card modeling method, it is characterised in that include step:
Step A, pre-builds that storage has the property data base of answering card regional feature；
Step B, scans user's answering card, obtains the electronic image of user's answering card；
Step C, carries out OCR Text region and graphic symbol recognition to described electronic image；
Step D, according to recognition result and the provincial characteristics in described property data base, it is judged that each regional location of user's answering card；
Step E, according to each regional location, sets up answering card electronic model.
2. answering card modeling method according to claim 1, it is characterised in that in described step C, described electronic image is carried out graphic symbol recognition and includes carrying out rectangle identification and bracket identification.
3. answering card modeling method according to claim 2, it is characterised in that described step D is according to recognition result and the provincial characteristics in property data base, it is judged that each regional location of user's answering card includes step:
Identify and in a bigger rectangle, have the region being connected more than 4 less rectangle frames, then judge that this bigger rectangular area is as admission card for entrance examination region.
4. answering card modeling method according to claim 2, it is characterised in that described step D is according to recognition result and the provincial characteristics in property data base, it is judged that each regional location of user's answering card includes step:
If by Distance Judgment, identifying and have horizontal tetrad, three graphical symbols in a rectangle apart from identical, and have the many groups of set of pixels chalaza meeting this rule, then judge that this rectangular area is as multiple-choice question answer region.
5. answering card modeling method according to claim 3, it is characterised in that according to each regional location in described step E, sets up answering card electronic model and includes step:
" [] " that go out at admission card for entrance examination region recognition is longitudinally inserted successively numeral 0-9.
6. answering card modeling method according to claim 4, it is characterised in that according to each regional location in described step E, sets up answering card electronic model and includes step:
" [] " that four is one group at multiple-choice question answer region recognition is laterally sequentially filled letter A, B, C, D.
7. answering card modeling method according to claim 1, it is characterised in that according to each regional location in described step E, sets up answering card electronic model and includes step:
The handwriting area that will identify that and name region are directly replicated as the handwriting area in electric answer card model and name region.
8. answering card modeling method according to claim 1, it is characterized in that, described step A sets up storage and has the property data base of answering card regional feature, have the property data base of name region characteristic of field, admission card for entrance examination provincial characteristics, answer provincial characteristics and borderline region feature including setting up storage.
9. answering card modeling method according to claim 1, it is characterised in that after described step B, before step C, further comprise the steps of:
Described electronic image is carried out binary conversion treatment.
10. an answering card model building device, it is characterised in that include property data base, scan module, identification module, judge module and MBM；
Described property data base, is used for storing answering card regional feature；
Described scan module, is used for scanning user's answering card, obtains the electronic image of user's answering card；
Described identification module, for carrying out OCR Text region and graphic symbol recognition to described electronic image；
Described judge module, for according to recognition result and the provincial characteristics in described property data base, it is judged that each regional location of user's answering card；
Described MBM, for according to each regional location, setting up answering card electronic model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410838311.5A CN105809157A (en) | 2014-12-29 | 2014-12-29 | Answer sheet modeling method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410838311.5A CN105809157A (en) | 2014-12-29 | 2014-12-29 | Answer sheet modeling method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105809157A true CN105809157A (en) | 2016-07-27 |
Family
ID=56979880
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410838311.5A Pending CN105809157A (en) | 2014-12-29 | 2014-12-29 | Answer sheet modeling method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105809157A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451581A (en) * | 2017-07-11 | 2017-12-08 | 济宁九点连线信息技术有限公司 | A kind of method of batch Automatic Read Overmarginalia answering card |
| CN107480667A (en) * | 2017-08-15 | 2017-12-15 | 成都准星云学科技有限公司 | The method and its system of intelligent topic image acquisition and processing based on template |
| CN108171297A (en) * | 2018-01-24 | 2018-06-15 | 谢德刚 | A kind of answer card identification method and device |
| CN109509378A (en) * | 2019-02-13 | 2019-03-22 | 湖南强视信息科技有限公司 | A kind of online testing method for supporting handwriting input |
| CN112507758A (en) * | 2019-09-16 | 2021-03-16 | 深圳中兴网信科技有限公司 | Answer sheet character string identification method, answer sheet character string identification device, terminal and computer storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1256900A1 (en) * | 2001-05-09 | 2002-11-13 | Requisite Technology Inc. | Database entry system and method employing optical character recognition |
| CN1619580A (en) * | 2004-09-03 | 2005-05-25 | 深圳市海云天科技有限公司 | Information identification method of full-filling information card |
| CN101908136A (en) * | 2009-06-08 | 2010-12-08 | 比亚迪股份有限公司 | Table identifying and processing method and system |
| CN301877865S (en) * | 2011-10-21 | 2012-04-04 | 中国人民解放军专业技术干部考试中心 | answer sheet |
| CN102567711A (en) * | 2010-12-29 | 2012-07-11 | 方正国际软件(北京)有限公司 | Method and system for making and using scanning recognition template |
| CN103208004A (en) * | 2013-03-15 | 2013-07-17 | 北京英迈杰科技有限公司 | Automatic recognition and extraction method and device for bill information area |
| CN103488608A (en) * | 2013-09-27 | 2014-01-01 | 杨昕吉 | Method and system for quickly creating visual-style electronic business card |
| CN103577837A (en) * | 2013-10-25 | 2014-02-12 | 江苏经贸职业技术学院 | Answer sheet image judging and reading statistical analysis system |
-
2014
- 2014-12-29 CN CN201410838311.5A patent/CN105809157A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1256900A1 (en) * | 2001-05-09 | 2002-11-13 | Requisite Technology Inc. | Database entry system and method employing optical character recognition |
| CN1619580A (en) * | 2004-09-03 | 2005-05-25 | 深圳市海云天科技有限公司 | Information identification method of full-filling information card |
| CN101908136A (en) * | 2009-06-08 | 2010-12-08 | 比亚迪股份有限公司 | Table identifying and processing method and system |
| CN102567711A (en) * | 2010-12-29 | 2012-07-11 | 方正国际软件(北京)有限公司 | Method and system for making and using scanning recognition template |
| CN301877865S (en) * | 2011-10-21 | 2012-04-04 | 中国人民解放军专业技术干部考试中心 | answer sheet |
| CN103208004A (en) * | 2013-03-15 | 2013-07-17 | 北京英迈杰科技有限公司 | Automatic recognition and extraction method and device for bill information area |
| CN103488608A (en) * | 2013-09-27 | 2014-01-01 | 杨昕吉 | Method and system for quickly creating visual-style electronic business card |
| CN103577837A (en) * | 2013-10-25 | 2014-02-12 | 江苏经贸职业技术学院 | Answer sheet image judging and reading statistical analysis system |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451581A (en) * | 2017-07-11 | 2017-12-08 | 济宁九点连线信息技术有限公司 | A kind of method of batch Automatic Read Overmarginalia answering card |
| CN107480667A (en) * | 2017-08-15 | 2017-12-15 | 成都准星云学科技有限公司 | The method and its system of intelligent topic image acquisition and processing based on template |
| CN108171297A (en) * | 2018-01-24 | 2018-06-15 | 谢德刚 | A kind of answer card identification method and device |
| CN108171297B (en) * | 2018-01-24 | 2022-01-14 | 谢德刚 | Answer sheet identification method |
| CN109509378A (en) * | 2019-02-13 | 2019-03-22 | 湖南强视信息科技有限公司 | A kind of online testing method for supporting handwriting input |
| CN112507758A (en) * | 2019-09-16 | 2021-03-16 | 深圳中兴网信科技有限公司 | Answer sheet character string identification method, answer sheet character string identification device, terminal and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109993112B (en) | Method and device for identifying table in picture | |
| CN109815932B (en) | Test paper correcting method and device, electronic equipment and storage medium | |
| CN105809157A (en) | Answer sheet modeling method and device | |
| US20210020059A1 (en) | Answer evaluation method, answer evaluation system, electronic device, and medium | |
| CN108701234A (en) | Licence plate recognition method and cloud system | |
| CN107798321A (en) | A kind of examination paper analysis method and computing device | |
| CN106203454B (en) | The method and device of certificate format analysis | |
| CN104820835A (en) | Automatic examination paper marking method for examination papers | |
| CN105590101A (en) | Hand-written answer sheet automatic processing and marking method and system based on mobile phone photographing | |
| CN101196994A (en) | Image content recognizing method and recognition system | |
| CN102567300A (en) | Picture document processing method and device | |
| CN105427320A (en) | Image segmentation and extraction method | |
| CN109753953A (en) | The method, apparatus of localization of text, electronic equipment and storage medium in image | |
| CN104915667B (en) | A kind of answering card identifying and analyzing method and system based on mobile terminal | |
| CN107038438A (en) | It is a kind of that method is read and appraised based on image recognition | |
| CN110110714A (en) | Method and system are corrected automatically on a kind of line of papery operation | |
| CN103065146A (en) | Character recognition method for power communication machine room dumb equipment signboards | |
| CN108304562B (en) | Question searching method and device and intelligent terminal | |
| CN112434699A (en) | Automatic extraction and intelligent scoring system for handwritten Chinese characters or components and strokes | |
| CN112036259A (en) | Form correction and recognition method based on combination of image processing and deep learning | |
| CN106446885A (en) | Paper-based Braille recognition method and system | |
| CN110321837A (en) | A kind of recognition methods, device, terminal and the storage medium of examination question score | |
| CN113822907B (en) | Image processing method and device | |
| CN113159014A (en) | Objective question reading method, device, equipment and storage medium based on handwritten question numbers | |
| CN114463770A (en) | Intelligent question-cutting method for general test paper questions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 100086 Beijing Haidian District information on Road No. 11, room 407, floor 405 West Fourth Applicant after: Beijing hitevision Intelligent System Co. Ltd. Address before: 100086 Beijing Haidian District information on Road No. 11, room 407, floor 405 West Fourth Applicant before: BEIJING HONGHE INTELLIGENT SYSTEMS CO., LTD. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160727 |
|
| RJ01 | Rejection of invention patent application after publication |