CN1848109A - Method and system for editing optical character identification result - Google Patents
Method and system for editing optical character identification result Download PDFInfo
- Publication number
- CN1848109A CN1848109A CN 200510064987 CN200510064987A CN1848109A CN 1848109 A CN1848109 A CN 1848109A CN 200510064987 CN200510064987 CN 200510064987 CN 200510064987 A CN200510064987 A CN 200510064987A CN 1848109 A CN1848109 A CN 1848109A
- Authority
- CN
- China
- Prior art keywords
- display screen
- document image
- text
- ocr
- user
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000003287 optical effect Effects 0.000 title claims description 9
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 238000009434 installation Methods 0.000 claims description 16
- 239000012634 fragment Substances 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 3
- 238000012015 optical character recognition Methods 0.000 abstract 4
- 238000010586 diagram Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 206010009696 Clumsiness Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000001915 proofreading effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Landscapes
- Character Input (AREA)
- Character Discrimination (AREA)
Abstract
The present invention relates to a method for displaying file image and optical character recognition (OCR) result on a display screen and its system. Said invention can be used for editing OCR result. Said method includes the following steps: on first portion of said display screen displaying file image including a test area, the displaying text information that can be edited by user of said device on second portion of said display screen. The file image on first portion of said display screen and test information on second portion of said display screen can be simultaneously displayed, and the text information can be obtained from at least one text area of file image by means of OCR analysis.
Description
Technical field
The present invention generally speaking (but not exclusively) relates in hand-hold electronic device inediting optical character identification (OCR) result, relates in particular to the method and system that is used to show the OCR result that can be edited by the user of electronic installation.
Background technology
Optical character identification (OCR) can be defined as text image data is converted to the character code form that can be read by word-processing application of ASCII for example.In the urtext view data, text character is made of according to the mode identical with the view data (for example picture or lines) of other types each pixel.After converting the character code form to, the original image of text character usually no longer can be used for helping editing with the calibration shift result in mistake.Therefore OCR handles the quite high-quality image that needs each character, so that image transitions is become specific character code.Yet high quality graphic is very big often, high-resolution image.Handling high-definition picture needs a large amount of storage and processor resource usually, and may increase the required time of execution character identification greatly.
For the image analysis engine that is embedded in the hand-hold electronic device, handling high-definition picture may especially be a problem.Many hand-held devices, for example mobile phone, PDA(Personal Digital Assistant) and digital camera, or the combination of these devices all comprise the OCR parts of the text that is used for recognition image.For example, mobile phone can comprise digital camera, and it makes the user can catch the image of business card, analyzes this image with the text in the recognition image, then relevant name and address is stored in the contact files of phone automatically.But the limited storage of mobile phone and processor resource may cause containing a large amount of mistakes from the OCR processing of business card identification name and address.In addition, for example positions different on the business card is arranged or be arranged in to the file of business card often with for example criteria field such as name, address and phone number field with different orders, and this also may cause the OCR mistake, need proofread and correct by editing and processing.
There is the small-size text editing machine, is used for proofreading and correct the OCR result's of hand-hold electronic device mistake; Yet this prior art editing machine usually is difficult to usefulness, because they need key in each character on keypad.And this editing machine needs the user with reference to source document when carrying out the OCR error recovery usually.This usually is very inconvenient, because forget when the user attempts to edit OCR where business card has been placed on and has often can not find as a result the time probably.
Summary of the invention
According to an aspect of the present invention, the present invention is a kind of method that is used for showing optical character identification (OCR) result that can be edited by the user of electronic installation on display screen.This method comprises: show to comprise the document image that at least one is text filed in the first of display screen.On the second portion of display screen, show the text message that to edit by the user of device then.Text message on document image in the first of screen and the second portion at screen shows simultaneously, and described text message obtains from least one the text filed OCR analysis to described document image.Because document image reproduces in editing process, therefore do not need the user to use original hardcopy file such as business card.In fact, contrast the text filed of document image, can easily check the result that OCR handles.
According to a further aspect in the invention, as mentioned above simultaneously after display file image and the text message, can select one of described document image text filed.The text filed first that is replicated and pastes display screen of the selection of document image then.Use the OCR engine to handle to produce editor's text output then to the selection of document image is text filed.At last, the output of editor's text shows in the first of display screen.Droplet operation easy to use proofreaies and correct handling the text message that obtains from OCR between document image that can show simultaneously in first and second parts of screen and the text message.
In accordance with a further aspect of the present invention, the present invention is a kind of system that is used to show optical character identification (OCR) result that can be edited by the user.This system comprises the display screen of electronic installation.Show in the first of display screen to comprise the document image that at least one is text filed, and with the first of display screen on document image demonstration simultaneously, on the second portion of display screen, show the text message that can edit by the user of device.Described text message is analyzed from least one the text filed OCR to described document image and is obtained.
Description of drawings
For the present invention is understood easily, and produce actual effect, will with reference to the accompanying drawings the example embodiment that illustrates be described, wherein identical reference number refers to components identical, wherein:
Fig. 1 is the synoptic diagram that illustrates according to first embodiment of the display screen of the hand-hold electronic device of the embodiment of the invention;
Fig. 2 is the synoptic diagram that illustrates according to second embodiment of the display screen of the hand-hold electronic device of the embodiment of the invention;
Fig. 3 is the synoptic diagram that illustrates according to the 3rd embodiment of the display screen of the hand-hold electronic device of the embodiment of the invention;
Fig. 4 is the synoptic diagram that illustrates according to the 4th embodiment of the display screen of the hand-hold electronic device of the embodiment of the invention;
Fig. 5 is the synoptic diagram that illustrates according to the 5th embodiment of the display screen of the hand-hold electronic device of the embodiment of the invention;
Fig. 6 is the synoptic diagram that illustrates according to the 6th embodiment of the display screen of the hand-hold electronic device of the embodiment of the invention;
Fig. 7 is the process flow diagram that illustrates according to the method for the embodiment of the invention.
Embodiment
With reference to figure 1, the synoptic diagram according to the display screen 100 of the hand-hold electronic device of the embodiment of the invention is shown.Screen 100 comprises the first 105 of display file image 110, and document image 110 for example is the topography of business card, comprise at least one text filed 115.Screen 100 further comprises the second portion 120 of videotex information 125.As shown in Figure 1, the text message on document image 110 in the first 105 of screen 100 and the second portion 120 at screen 100 shows simultaneously.Text message 125 obtains by at least one optical character identification of text filed 115 (OCR) analysis to document image 110.Therefore split screen 100 of the present invention by demonstration can be used in check OCR as a result the document image 110 of accuracy make it possible on hand-held device more effective and edit OCR result more easily.
According to one embodiment of present invention, for example the single file text message 125 of name obtains from single file text filed 115 usually.Analyzed text filed 115 can on document image 110, the representing of document image 110 of identification with witness marking by OCR.For example, text filed 115 usefulness names black surround on every side shown in Figure 1 is represented.OCR in the second portion 120 of editing files image 110 is as a result the time, and witness marking may be useful.For example, if having only the part of line of text to handle by OCR in document image 110, the witness marking indication is identified, if perhaps indicate OCR to handle to have omitted fully the delegation's text in the document image 110 by not having witness marking, the user can take steps to edit and proofread and correct the text message 125 in the second portion 120 of display screen 100 so.Witness marking can be a various forms, for example forms the lines (shown in Fig. 1 to 4) around text filed 115 rectangle.Other marks can comprise the color change of emphasis point and text filed 115.For example, on colorful display screen 100, the background paper image 110 in the first 105 of screen 100 can be rendered as black and white, can be rendered as redness by text filed 115 of OCR processing and identification.
Fig. 2 is the synoptic diagram that display screen same as shown in Figure 1 100 is shown; But, in the first 105 of screen 100, document image 110 demonstrations move to the left side.According to one embodiment of present invention, this feature makes that user of the present invention can be with respect to the small screen 100 of hand-held device move image 110 in any direction, so that check a plurality of fragments of big image.
Fig. 3 and Fig. 4 have shown another feature of the embodiment of the invention, and wherein first and second parts 105,120 of display screen 100 can relative to each other be adjusted.This feature has also increased on small display 100 the easy and convenient of editor OCR result, only shows on screen 100 aspect those of the current document image of being edited 110 and relevant OCR result because the user has been given very big dirigibility.
Therefore the present invention can be used for various types of electronic installations with small display 100.This device comprises for example mobile phone, personal digital assistant, digital camera and some kneetop computers.Using this device editing text file may be the process of a clumsiness sometimes, because these devices are not connected to full size keyboard or mouse usually.Therefore editor usually needs to use keypad or touch-screen parts, and they are operated with finger or stylus.The present invention can help to minimize the quantity to keyboard or touch-screen input, and these inputs are that editor OCR result is needed on this device, have therefore saved the user's of device time and efforts.
For example, embodiments of the invention can be included in the mobile phone that is combined with digital camera.The user of this phone may for example receive a new business card, and attempts the information on the business card is input in the personal electric address book of storing in the storer on the his or her phone.According to the present invention, the user can use this phone that this business card is taken a picture simply, starts OCR on the phone then and handles and discern text filed 115 of the image 110 that obtains.Because document image 110 comprises the full picture of original business card, so this user does not need to preserve original business card.This user then can be according to the present invention at him or she when an opportunity arises by only editing OCR result with reference to the document image 110 that is stored on the phone.
Except can be at editor OCR as a result the time the document image 110 with reference to source document, embodiments of the invention make that also the user can be among document image 110 will text filedly copy to the row of the text message 125 of demonstration the second portion 120 of display screen 100.This ability can significantly reduce the required time of editor.For example, if the text message 125 in the second portion 120 of screen 100 is incorrect, if perhaps text message 125 has been omitted from the second portion 120 of screen 100 fully, the user can select to select and duplicate relevant text filedly from the first 105 of screen 100 so, and it is pasted the appropriate location of the second portion 120 of screen 100." drag and drop " program that this copy and paste process can use those skilled in the art to be familiar with is carried out.Electronic installation uses the text filed 115 of OCR engine processing selecting then, to produce text output, shows in the second portion 120 of screen 100 as new text message 125.Therefore drag and drop are handled and are impelled this device to use OCR to text filed 115 reanalysing that document image 110 incorrect analyzed, and perhaps text filed 115 can impel this device to carry out the analysis first time to text filed 115 when being omitted during initial OCR handles.
The present invention can use various types of OCR of the electronic installation that is suitable for reducing size to handle and system.As is known to persons skilled in the art, this OCR system can comprise the OCR technology of matrix coupling, feature extraction and other types.
With reference to figure 5, provide another synoptic diagram according to the display screen 100 of the electronic installation of the embodiment of the invention.Here screen 100 only comprises the second portion 120 of Fig. 1 to screen 100 shown in Figure 4.Therefore, after the user had checked OCR result by the document image 110 in the first 105 of looking back display screen 100, the user can switch to the full-screen form of second portion 120, a videotex information 125.Drop-down menu 500 also can be used for increasing the facility of editor such as standardized text such as business card titles.Drop-down menu 500 can comprise the default fields title, and for example " name ", " unit " during business card, " title ", " address ", " telephone number ", " fax number ", " Email " and " network address " or other are suitable for the field of particular type file when document image 110.This drop-down menu 500 allows the user to come the not text message 125 of correct labeling of correct labeling with minimum action.
With reference to figure 6, provide another synoptic diagram according to the display screen 100 of the electronic installation of the embodiment of the invention.Here screen 100 is again only to comprise the second portion 120 of Fig. 1 to screen 100 shown in Figure 4.Also show touch-screen type miniature keyboard 600, it can be used to Edit Text information 125, is included in the text in the expanded text frame 605, and the expanded text frame can be used for showing the additional text outside the summary version that can be used as the text that text message 125 shows.
With reference to figure 7, the process flow diagram that is used for showing the OCR result's that can be edited by the user of electronic installation universal method 700 on display screen 100 is shown.At first, in step 705, in the first 105 of display screen 100, show to comprise at least one document image of text filed 115 110.Document image 110 can receive from any source (for example video camera) that is connected to electronic installation.In step 710, on the second portion 120 of display screen 100, show the text message 125 that to edit by the user of device.First and second parts 105,120 of display screen 100 are simultaneously displayed on the screen 100, and obtain text message 125 from least one OCR of text filed 115 analysis to document image 110.
Next, in step 715, by text filed 115 of user's select File image 110 of electronic installation.In step 720, the selection of document image 110 text filed 115 is replicated and pastes the first 105 of display screen 100.In step 725, use the OCR engine that the selection of document image 110 text filed 115 is handled to produce text output.At last, in step 730, text output shows in the second portion 120 of display screen 100 as text message 125.
Generally speaking, the present invention be used on the display screen 100 of electronic installation with the user that allows electronic installation convenient and quickly the mode of edited result show OCR result's method and system.Because document image 110 reproduces in editing process, therefore do not need the user to use original hardcopy file, for example business card.In fact, can contrast the result that text filed 115 of document image 110 checks that easily OCR handles.And droplet operation easy to use proofreaies and correct handling the text message 125 that obtains from OCR between document image 110 that can show simultaneously in first and second parts 105,120 of screen 100 and the text message 125.Comprise that other features in some embodiments of the invention allow document image 110 to move with respect to display screen 100,, and comprise that drop-down menu 500 is to simplify editing process so that can on the small screen 100, watch a plurality of fragments of file respectively.
Top detailed description only provides example embodiment, and is not in order to limit the scope of the invention, to use or disposing.On the contrary, the those skilled in the art that are specifically described as of example embodiment provide the open explanation that is used to implement example embodiment of the present invention.Should be appreciated that, can make various changes aspect the function of element and step and the configuration, and not break away from main idea of the present invention and the scope that proposes in the appended claims.
Claims (16)
1. method that is used on display screen showing optical character identification (OCR) result that can edit by the user of electronic installation, this method may further comprise the steps:
In the first of display screen, show and comprise the document image that at least one is text filed; And
On the second portion of display screen, show the text message that to edit by the user of described device, wherein, text message on document image in the first of screen and the second portion at screen shows simultaneously, and obtains described text message from least one the text filed OCR analysis to described document image.
2. the method for claim 1 further may further comprise the steps:
After showing described document image and text message, select the text filed of described document image;
It is text filed and it is pasted the first of display screen to duplicate the selection of described document image;
Use the OCR engine to handle the text filed text output of selection of described document image with the generation editor;
In the first of display screen, show described editor's text output.
3. the method for claim 1 further comprises step subsequently:
Use OCR engine processing selecting text filed in the second portion of display screen,, in the first of display screen, show this editor's text output then to produce editor's text output.
4. the method for claim 1, wherein analyze the witness marking indication of text filed quilt on described document image of the document image of having discerned by OCR.
5. method as claimed in claim 4, wherein, described witness marking is selected from following group: line, emphasis point, text filed color change.
6. the method for claim 1, wherein described document image is represented business card, and the second portion of display screen comprises the default fields name that can be selected and be changed by the user of described device.
7. method as claimed in claim 6, wherein, at least some in the described default fields name are selected from following group: " name ", " unit ", " title ", " address ", " telephone number ", " fax number ", " Email " and " network address ".
8. the method for claim 1, wherein described document image is represented the fragment of a file, and described image is movably with respect to display screen, so that the user can watch other images of other fragments of expression file.
9. method as claimed in claim 2, wherein, the selection of described xcopy image is text filed and use " drag and drop " program to carry out the step that it pastes the first of display screen.
10. system that is used to show optical character identification (OCR) result that can edit by the user, it comprises:
The display screen of electronic installation;
Comprise the document image that at least one is text filed what the first of display screen showed; With
On the second portion of display screen with the first of display screen on the demonstration text message that show simultaneously, that can edit by the user of described device of document image, wherein, described text message is analyzed from least one the text filed OCR to described document image and is obtained.
11. system as claimed in claim 10, wherein, described electronic installation is selected from comprising following group: mobile phone, personal digital assistant, digital camera and kneetop computer.
12. system as claimed in claim 10 wherein, analyzes the witness marking indication of text filed quilt on described document image of the document image of having discerned by OCR.
13. system as claimed in claim 12, wherein, described witness marking is selected from following group: line, emphasis point, text filed color change.
14. system as claimed in claim 10, wherein, described document image is represented business card, and the second portion of display screen comprises the default fields name that can be selected and be changed by the user of described device.
15. method as claimed in claim 14, wherein, at least some in the described default fields name are selected from following group: " name ", " unit ", " title ", " address ", " telephone number ", " fax number ", " Email " and " network address ".
16. method as claimed in claim 10, wherein, described document image is represented the fragment of a file, and described image is movably with respect to display screen, so that the user can watch other images of other fragments of expression file.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200510064987 CN1848109A (en) | 2005-04-13 | 2005-04-13 | Method and system for editing optical character identification result |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200510064987 CN1848109A (en) | 2005-04-13 | 2005-04-13 | Method and system for editing optical character identification result |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN1848109A true CN1848109A (en) | 2006-10-18 |
Family
ID=37077674
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200510064987 Pending CN1848109A (en) | 2005-04-13 | 2005-04-13 | Method and system for editing optical character identification result |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1848109A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102474902A (en) * | 2009-10-05 | 2012-05-23 | 索尼公司 | Mobile device visual input system and method |
| CN102547179A (en) * | 2011-12-29 | 2012-07-04 | 惠州Tcl移动通信有限公司 | Synchronous display method for hand-held device and television |
| US8503784B2 (en) | 2007-10-31 | 2013-08-06 | Fujitsu Limited | Image recognition apparatus, image recognition method, and storage medium recording image recognition program |
| CN104134057A (en) * | 2009-01-28 | 2014-11-05 | 谷歌公司 | Selective display of OCR'ed text and corresponding images from publications on a client device |
| CN104636322A (en) * | 2015-03-03 | 2015-05-20 | 广东欧珀移动通信有限公司 | Text copying method and text copying device |
| CN101833545B (en) * | 2009-03-11 | 2015-09-09 | 汉王科技股份有限公司 | Method for indexing data in digital recourse processing process |
| CN110598186A (en) * | 2019-07-31 | 2019-12-20 | 浙江口碑网络技术有限公司 | Auxiliary processing method, device and system for image recognition |
-
2005
- 2005-04-13 CN CN 200510064987 patent/CN1848109A/en active Pending
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8503784B2 (en) | 2007-10-31 | 2013-08-06 | Fujitsu Limited | Image recognition apparatus, image recognition method, and storage medium recording image recognition program |
| CN104134057A (en) * | 2009-01-28 | 2014-11-05 | 谷歌公司 | Selective display of OCR'ed text and corresponding images from publications on a client device |
| CN104134057B (en) * | 2009-01-28 | 2018-02-13 | 谷歌公司 | The selectivity of the text and correspondence image that are handled through OCR on a client device from publication is shown |
| CN101833545B (en) * | 2009-03-11 | 2015-09-09 | 汉王科技股份有限公司 | Method for indexing data in digital recourse processing process |
| CN102474902A (en) * | 2009-10-05 | 2012-05-23 | 索尼公司 | Mobile device visual input system and method |
| CN102547179A (en) * | 2011-12-29 | 2012-07-04 | 惠州Tcl移动通信有限公司 | Synchronous display method for hand-held device and television |
| US8988604B2 (en) | 2011-12-29 | 2015-03-24 | Huizhou TCL Mobile Communications Co., Ltd. | Handheld device and method for displaying synchronously with TV set |
| US9292901B2 (en) | 2011-12-29 | 2016-03-22 | Huizhou Tcl Mobile Communication Co., Ltd | Handheld device and method for displaying synchronously with TV set |
| CN104636322A (en) * | 2015-03-03 | 2015-05-20 | 广东欧珀移动通信有限公司 | Text copying method and text copying device |
| CN104636322B (en) * | 2015-03-03 | 2018-01-23 | 广东欧珀移动通信有限公司 | The method and device that a kind of text replicates |
| CN110598186A (en) * | 2019-07-31 | 2019-12-20 | 浙江口碑网络技术有限公司 | Auxiliary processing method, device and system for image recognition |
| WO2021017458A1 (en) * | 2019-07-31 | 2021-02-04 | 浙江口碑网络技术有限公司 | Auxiliary processing method, device, and system for image recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7194701B2 (en) | Video thumbnail | |
| US6332039B1 (en) | Structured document preparation apparatus and structured document preparation method | |
| JP4700423B2 (en) | Common charting using shapes | |
| CN1278533C (en) | Handset capable of automatically recording characters and images, and method of recording and processing thereof | |
| JP5361174B2 (en) | Display control apparatus, display control method, and program | |
| JP2013502861A (en) | Contact information input method and system | |
| CN116484812A (en) | Method and system for off-line page signing and reading circulation | |
| US20040021790A1 (en) | Method of and system for processing image information on writing surface including hand-written information | |
| CN100487702C (en) | Image processing apparatus | |
| US20100302429A1 (en) | Image processing apparatus and control method for image processing apparatus | |
| CN1848109A (en) | Method and system for editing optical character identification result | |
| US20080231869A1 (en) | Method and apparatus for displaying document image, and computer program product | |
| US20080018772A1 (en) | Input apparatus for image | |
| CN100452035C (en) | Document file management apparatus, document file management method, and document file management program | |
| CN107885860A (en) | A kind of method, storage medium and electronic equipment for marking and showing on media file | |
| US7336319B2 (en) | Digital camera apparatus having a recognizing function | |
| CN113835598A (en) | Information acquisition method and device and electronic equipment | |
| JP4712629B2 (en) | Equipment specification input device | |
| JP3773662B2 (en) | Data management apparatus and method of using the apparatus | |
| KR20060007852A (en) | Efficient image retrieval method of mobile communication terminal | |
| KR20040083178A (en) | Method and apparatus arranging a plural image | |
| JPS63150762A (en) | Hierarchy menu display method for electronic filing system | |
| JP3214378B2 (en) | Image processing apparatus and image processing method | |
| JP2008181223A (en) | Electronic document management system, electronic document management method, program, and recording medium | |
| CN111741181A (en) | Photographing printing method, computer device and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |