CN104462044A - Recognizing and editing method and device of tabular images - Google Patents
Recognizing and editing method and device of tabular images Download PDFInfo
- Publication number
- CN104462044A CN104462044A CN201410773904.8A CN201410773904A CN104462044A CN 104462044 A CN104462044 A CN 104462044A CN 201410773904 A CN201410773904 A CN 201410773904A CN 104462044 A CN104462044 A CN 104462044A
- Authority
- CN
- China
- Prior art keywords
- lines
- edit cell
- edit
- drawing picture
- tabular drawing
- 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
- Image Analysis (AREA)
- Character Input (AREA)
Abstract
The invention discloses a recognizing and editing method of tabular images. The method includes: acquiring a tabular image containing a table; according to lines of the table, dividing the tabular image into multiple editing units, each which is bordered by the lines of the table and each which contain no lines of the table; performing single or multiple editing operations to the image parts in the single or multiple editing units, and generating a new tabular image according to editing operation results. The invention further discloses a device implementing the method. By the application of the recognizing and editing method and device according to the technical scheme, text recognizing and editing for the tabular images is facilitated for users, and the tabular images can be processed efficiently and simply.
Description
Technical field
The present invention relates to a kind of image processing method, especially a kind of form image recognition edit methods.The invention still further relates to a kind of image processing apparatus, especially a kind of form image recognition editing device.
Background technology
Now, people have more and more used electronic document to replace paper document.Such as, user can take the image of paper document with smart mobile phone, is then sent to by image others to complete the transmission of information.But, all store with picture format to take or to scan the electronic document obtained, therefore word be above difficult to edit.Now, along with the development of OCR technology, existing a lot of software can identify the word on these images, carries out text editing for user, but use really not very convenient, especially for the file including form, due to the diversity of form, the form in image not only can not be identified, and sometimes can also cause the mistake of Text region, affect discrimination, bring very large inconvenience to the use of user.In addition, if find that filling in of form exists mistake, user modifies also pretty troublesome to image.
Summary of the invention
Technical matters to be solved by this invention is to provide a kind of form image recognition edit methods, and realize the form image recognition editing device that this form image recognition edit methods adopts, Text region and editor can be carried out by his-and-hers watches table images easily, the his-and-hers watches table images of user's high-efficient simple is processed.
For solving the problems of the technologies described above, the technical scheme of form image recognition edit methods of the present invention comprises the following steps:
Step one, obtains described tabular drawing picture, and described tabular drawing picture includes form;
Step 2, according to the lines of described form, is divided into multiple edit cell by described tabular drawing picture, and each edit cell for border, and no longer includes the lines of described form with the lines of described form in each edit cell;
Step 3, carries out the editing operation of one or many to the image in one or more edit cell, and according to the result of editing operation, generates new tabular drawing picture.
The invention also discloses a kind of form image recognition editing device realizing above table image recognition edit methods and adopt, its technical scheme is, based on computer system, comprising:
Form image acquisition component, obtains described tabular drawing picture, and described tabular drawing picture includes form;
Divided parts, according to the lines of described form, is divided into multiple edit cell by described tabular drawing picture, and each edit cell for border, and no longer includes the lines of described form with the lines of described form in each edit cell;
Editor's parts, carry out the editing operation of one or many to the image in one or more edit cell, and according to the result of editing operation, generate new tabular drawing picture.
The present invention by adopting technique scheme, can make user easily his-and-hers watches table images carry out Text region and editing operation, thus the his-and-hers watches table images of high-efficient simple processes.
Accompanying drawing explanation
Below in conjunction with drawings and Examples, the present invention is further detailed explanation:
Fig. 1 and Fig. 2 is the schematic diagram of form image recognition edit methods embodiment of the present invention;
Fig. 3 is the schematic diagram of form image recognition editing device of the present invention.
Embodiment
The invention discloses a kind of form image recognition edit methods, comprise the following steps:
Step one, obtains described tabular drawing picture, and described tabular drawing picture includes form;
Step 2, according to the lines of described form, is divided into multiple edit cell by described tabular drawing picture, and each edit cell for border, and no longer includes the lines of described form with the lines of described form in each edit cell;
Step 3, carries out the editing operation of one or many to the image in one or more edit cell, and according to the result of editing operation, generates new tabular drawing picture.
As depicted in figs. 1 and 2, user obtains tabular drawing picture, and the mode obtaining tabular drawing picture can be shooting tabular drawing picture, also can be open the picture file including tabular drawing picture.This tabular drawing picture there is form ABCD as shown in Figure 1.Due to the angle problem of shooting, the form of rectangle can be shown as a quadrilateral ABCD as shown in Figure 1 on image originally.In order to reduce this distortion, after acquisition tabular drawing picture, form image recognition edit methods of the present invention also comprises and carries out image processing step to described tabular drawing picture, and described image procossing comprises at least one in following two kinds:
1. his-and-hers watches table images stretches, and the shape making the form after stretching is rectangle.
2. the lines of pair form process, and the direction angle with horizontal reference being less than the lines of a certain preset range fits to horizontal direction, and the direction angle with vertical reference being less than the lines of a certain preset range fits to vertical direction.
After carrying out above-mentioned image procossing, quadrilateral form ABCD in Fig. 1 will be adjusted to the rectangle tables ABCD in Fig. 2, such as, and the lines in form, lines EF and lines GK are also adjusted to horizontal direction and vertical direction, thus eliminate the distortion of taking and causing table shape.
According to the lines of described form, such as lines EF and lines GK, be divided into multiple edit cell by described tabular drawing picture, and each edit cell for border, and no longer includes the lines of described form with the lines of described form in each edit cell; As depicted in figs. 1 and 2, form ABCD is divided into edit cell AGHE, GBFH, EHKD and HFCK.
Then, editing operation is carried out to the image in described edit cell, this editing operation can be the image in described edit cell is modified, image-editing operations that replacement etc. is traditional, also can be following several at least one:
1. the word in pair described edit cell carries out OCR identification, and to identifying that the text obtained carries out text editing operations, such as, have in the edit cell EHKD of Fig. 1 " word 2 " of handwritten form, OCR identification is carried out to the word of this edit cell, obtain " word 2 " as the block letter in Fig. 2 inediting unit EHKC, if recognition result is wrong, user can carry out manual modification.
2. using not comprising the edit cell of word as copy editor region, in described copy editor region, carrying out text editing operations by user, such as, in the edit cell GBFH of Fig. 1 and Fig. 2, carrying out text editing operations wherein by user.
3. adjust the position of the lines of form described in one or more, the edit cell being border with controlled lines repartitions region according to the reposition of these lines, such as lines EF or GK in Fig. 1 and Fig. 2 is adjusted, to repartition each edit cell.
4. delete the lines of form described in one or more, merged with multiple edit cells that controlled lines are border, if such as delete the lines HK in Fig. 1 and Fig. 2, then edit cell EHKD and edit cell HFCK is just merged into edit cell EFCD.
5. increase the lines of form described in one or more, the edit cell that these lines pass is with these lines edit cell new for border is divided into.
In technology in the past, if user needs the form document Electronically transmitting paper, need, after shooting form document, form Image to be sent.If what send is the form needing to fill in, user also wants to be filled in by form in advance, and the form sent so is also that user is hand-written to be filled in, in addition, if find that there is mistake in form also cannot modify, adopt the softwares for editing such as OFFICE to re-start editing and composing to form, inconvenience very except non-user.But, after employing form image recognition edit methods of the present invention, user can carry out edit-modify by his-and-hers watches table images easily, the hand-written form filled in of such as user, the block letter of standard can be become after identifying, if find that paper form exists mistake, can be convenient to use the present invention after photographing and modify, user can also use the present invention's fill substance on the form of electronic version after shooting blank form.
The invention also discloses a kind of form image recognition editing device realizing above table image recognition edit methods and adopt, as shown in Figure 3, based on computer system, described computer system can comprise the system that PC, smart mobile phone, panel computer etc. have computer hardware and corresponding function software.
Form image recognition editing device of the present invention comprises:
Form image acquisition component, obtains described tabular drawing picture, and described tabular drawing picture includes form;
Divided parts, according to the lines of described form, is divided into multiple edit cell by described tabular drawing picture, and each edit cell for border, and no longer includes the lines of described form with the lines of described form in each edit cell;
Editor's parts, carry out the editing operation of one or many to the image in one or more edit cell, and according to the result of editing operation, generate new tabular drawing picture.
Form image recognition editing device of the present invention also comprises form image processing section, carries out image procossing to described tabular drawing picture, and described image procossing comprises at least one in following two kinds:
His-and-hers watches table images stretches, and the shape making the form after stretching is rectangle;
Process the lines of form, the direction angle with horizontal reference being less than the lines of a certain preset range fits to horizontal direction, and the direction angle with vertical reference being less than the lines of a certain preset range fits to vertical direction.
The present invention by adopting technique scheme, can make user easily his-and-hers watches table images carry out Text region and editing operation, thus the his-and-hers watches table images of high-efficient simple processes.
The foregoing is only preferred embodiment of the present invention, and be not used to limit substantial technological context of the present invention, substantial technological content of the present invention be broad sense be defined in the right of application, any technology entities that other people complete or method, if with application right define identical, also or a kind of change of equivalence, be all covered by being regarded as among this right.
Claims (5)
1. a form image recognition edit methods, is characterized in that, comprises the following steps:
Step one, obtains described tabular drawing picture, and described tabular drawing picture includes form;
Step 2, according to the lines of described form, is divided into multiple edit cell by described tabular drawing picture, and each edit cell for border, and no longer includes the lines of described form with the lines of described form in each edit cell;
Step 3, carries out the editing operation of one or many to the image in one or more edit cell, and according to the result of editing operation, generates new tabular drawing picture.
2. form image recognition edit methods according to claim 1, is characterized in that, after described step one, also comprise and carry out image processing step to described tabular drawing picture, described image procossing comprises at least one in following two kinds:
His-and-hers watches table images stretches, and the shape making the form after stretching is rectangle;
Process the lines of form, the direction angle with horizontal reference being less than the lines of a certain preset range fits to horizontal direction, and the direction angle with vertical reference being less than the lines of a certain preset range fits to vertical direction.
3. form image recognition edit methods according to claim 1, is characterized in that, described editing operation comprise following several at least one:
OCR identification is carried out to the word in described edit cell, and to identifying that the text obtained carries out text editing operations;
Using not comprising the edit cell of word as copy editor region, in described copy editor region, carry out text editing operations by user;
Adjust the position of the lines of form described in one or more, the edit cell being border with controlled lines repartitions region according to the reposition of these lines;
Delete the lines of form described in one or more, merged with multiple edit cells that controlled lines are border;
Increase the lines of form described in one or more, the edit cell that these lines pass is with these lines edit cell new for border is divided into.
4. realize as the form image recognition edit methods in claim 1-3 as described in any one the form image recognition editing device that adopts, it is characterized in that, based on computer system, comprising:
Form image acquisition component, obtains described tabular drawing picture, and described tabular drawing picture includes form;
Divided parts, according to the lines of described form, is divided into multiple edit cell by described tabular drawing picture, and each edit cell for border, and no longer includes the lines of described form with the lines of described form in each edit cell;
Editor's parts, carry out the editing operation of one or many to the image in one or more edit cell, and according to the result of editing operation, generate new tabular drawing picture.
5. form image recognition editing device according to claim 4, is characterized in that, also comprise form image processing section, carries out image procossing to described tabular drawing picture, and described image procossing comprises at least one in following two kinds:
His-and-hers watches table images stretches, and the shape making the form after stretching is rectangle;
Process the lines of form, the direction angle with horizontal reference being less than the lines of a certain preset range fits to horizontal direction, and the direction angle with vertical reference being less than the lines of a certain preset range fits to vertical direction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410773904.8A CN104462044A (en) | 2014-12-16 | 2014-12-16 | Recognizing and editing method and device of tabular images |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410773904.8A CN104462044A (en) | 2014-12-16 | 2014-12-16 | Recognizing and editing method and device of tabular images |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104462044A true CN104462044A (en) | 2015-03-25 |
Family
ID=52908116
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410773904.8A Pending CN104462044A (en) | 2014-12-16 | 2014-12-16 | Recognizing and editing method and device of tabular images |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104462044A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105373791A (en) * | 2015-11-12 | 2016-03-02 | 中国建设银行股份有限公司 | Information processing method and information processing device |
CN107679024A (en) * | 2017-09-11 | 2018-02-09 | 畅捷通信息技术股份有限公司 | The method of identification form, system, computer equipment, readable storage medium storing program for executing |
CN109461111A (en) * | 2018-10-26 | 2019-03-12 | 连尚(新昌)网络科技有限公司 | Image editing method, device, terminal device and medium |
CN110163030A (en) * | 2018-02-11 | 2019-08-23 | 鼎复数据科技(北京)有限公司 | A kind of PDF based on image information has frame table abstracting method |
WO2020140698A1 (en) * | 2019-01-04 | 2020-07-09 | 阿里巴巴集团控股有限公司 | Table data acquisition method and apparatus, and server |
CN111859874A (en) * | 2019-04-17 | 2020-10-30 | 百度在线网络技术(北京)有限公司 | Table generating method and system, video playing device and computer readable medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7505167B2 (en) * | 2003-08-07 | 2009-03-17 | Ricoh Company, Limited | Information processing apparatus, method, and computer product, for file naming |
CN101676930A (en) * | 2008-09-17 | 2010-03-24 | 北大方正集团有限公司 | Method and device for recognizing table cells in scanned image |
CN101702242A (en) * | 2009-11-23 | 2010-05-05 | 中兴通讯股份有限公司 | Method and terminal for automatically filling in document with fixed format |
CN101908136A (en) * | 2009-06-08 | 2010-12-08 | 比亚迪股份有限公司 | Table identifying and processing method and system |
CN102508823A (en) * | 2011-11-24 | 2012-06-20 | 杨盛 | Method and system for making tables |
-
2014
- 2014-12-16 CN CN201410773904.8A patent/CN104462044A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7505167B2 (en) * | 2003-08-07 | 2009-03-17 | Ricoh Company, Limited | Information processing apparatus, method, and computer product, for file naming |
CN101676930A (en) * | 2008-09-17 | 2010-03-24 | 北大方正集团有限公司 | Method and device for recognizing table cells in scanned image |
CN101908136A (en) * | 2009-06-08 | 2010-12-08 | 比亚迪股份有限公司 | Table identifying and processing method and system |
CN101702242A (en) * | 2009-11-23 | 2010-05-05 | 中兴通讯股份有限公司 | Method and terminal for automatically filling in document with fixed format |
CN102508823A (en) * | 2011-11-24 | 2012-06-20 | 杨盛 | Method and system for making tables |
Non-Patent Citations (1)
Title |
---|
刘昱: "印刷体表格识别的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105373791A (en) * | 2015-11-12 | 2016-03-02 | 中国建设银行股份有限公司 | Information processing method and information processing device |
CN105373791B (en) * | 2015-11-12 | 2018-12-14 | 中国建设银行股份有限公司 | Information processing method and information processing unit |
CN107679024A (en) * | 2017-09-11 | 2018-02-09 | 畅捷通信息技术股份有限公司 | The method of identification form, system, computer equipment, readable storage medium storing program for executing |
CN110163030A (en) * | 2018-02-11 | 2019-08-23 | 鼎复数据科技(北京)有限公司 | A kind of PDF based on image information has frame table abstracting method |
CN110163030B (en) * | 2018-02-11 | 2021-04-23 | 鼎复数据科技(北京)有限公司 | PDF framed table extraction method based on image information |
CN109461111A (en) * | 2018-10-26 | 2019-03-12 | 连尚(新昌)网络科技有限公司 | Image editing method, device, terminal device and medium |
WO2020140698A1 (en) * | 2019-01-04 | 2020-07-09 | 阿里巴巴集团控股有限公司 | Table data acquisition method and apparatus, and server |
CN111859874A (en) * | 2019-04-17 | 2020-10-30 | 百度在线网络技术(北京)有限公司 | Table generating method and system, video playing device and computer readable medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104462044A (en) | Recognizing and editing method and device of tabular images | |
US11631050B2 (en) | Syncing physical and electronic document | |
US8855413B2 (en) | Image reflow at word boundaries | |
CN101859225B (en) | Method for implementing words and tables rapidly inputting by digital red drawing | |
CN105260996B (en) | Electronic document generating system and electronic document generation device | |
CN105005980B (en) | Image processing method and device | |
CA3065062A1 (en) | Simulating image capture | |
CN101702242B (en) | Method and terminal for automatically filling in document with fixed format | |
WO2014086287A1 (en) | Text image automatic dividing method and device, method for automatically dividing handwriting entries | |
US9460089B1 (en) | Flow rendering of annotation characters | |
US20170286415A1 (en) | Intelligently identifying and presenting digital documents | |
CN103810485A (en) | Recognition device, character recognition system and method | |
CN105786784A (en) | PowerPoint template replacing method and device | |
CN103399696A (en) | Method and device for adsorbing straight lines/ line segments, and method and device for structuring polygon | |
CN111695518B (en) | Method and device for labeling structured document information and electronic equipment | |
WO2022089170A1 (en) | Caption area identification method and apparatus, and device and storage medium | |
KR20150059989A (en) | Apparatus and Method for recognition a documentation with text and image | |
CN106530219A (en) | Image splicing method and device | |
KR20160138930A (en) | A method of aligning the images cut of a cartoon contents | |
CN103400387A (en) | Method and device for adsorbing line segment in image, as well as method and device for constructing polygon | |
KR20160059358A (en) | Method of processing images, Computer readable storage medium of recording the method and an electronic apparatus | |
US20170310920A1 (en) | Method and system for rendering documents with depth camera for telepresence | |
US20150302246A1 (en) | Forming scanned composite document with optical character recognition function | |
US20170041494A1 (en) | Digital content access using a machine -readable link | |
KR101517829B1 (en) | Book scanning system using smart device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 200436 building A, No. 1268, Wanrong Road, Jingan District, Shanghai Applicant after: Shanghai Hehe Information Technology Development Co., Ltd. Address before: 7, No. 200433, building 335, building 3, National Road, Yangpu District, Shanghai, B Applicant before: Shanghai Hehe Information Technology Development Co., Ltd. |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150325 |