CN102981753B - The hand-written Chinese character input recognition method improved - Google Patents
The hand-written Chinese character input recognition method improved Download PDFInfo
- Publication number
- CN102981753B CN102981753B CN201210249413.4A CN201210249413A CN102981753B CN 102981753 B CN102981753 B CN 102981753B CN 201210249413 A CN201210249413 A CN 201210249413A CN 102981753 B CN102981753 B CN 102981753B
- Authority
- CN
- China
- Prior art keywords
- word
- district
- candidate
- chinese character
- stroke
- 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.)
- Expired - Fee Related
Links
Landscapes
- Document Processing Apparatus (AREA)
- Character Discrimination (AREA)
Abstract
A kind of equipment of the input of the handwritten Chinese character for electronic installation identification of improvement and method.Wherein, described equipment comprises for identifying that user writes the device of the Chinese character that district writes of described electronic installation, wherein said identification only just completes when meeting following condition: the starting point of previous stroke or intermediate point be not or not a predetermined beginning district, front several stroke forms a word completed, and the initial point of current stroke or intermediate point are in described beginning district.
Description
The application is application number 200310115725.7, November 28 2003 applying date day, be called the divisional application of " hand-written Chinese character input recognition method of improvement ".
Technical field
The present invention relates to handwritten Chinese character input to identify, the hand-written Chinese character input recognition method for electronic installation of particularly a kind of improvement, it can tolerate that time-out does not even affect by time-out, and can allow to carry out part amendment to the word inputted.
Background technology
Handwritten Chinese character input has the computing machine of touch-screen or touch pad (board) and the conventional input method of other electronic equipment.Along with the widespread use of notebook computer, mobile phone and personal digital assistant (PDA) etc., handwritten Chinese character input fast, efficiently and accurately identifies the hope having become many people.
For writing Chinese characters, different people has different writing styles and writing style.The difficult problem that handwritten Chinese character input identifies is exactly how to determine whether user has write a word.Therefore, hinder the obstacle identified fast and to be accurately exactly so-called time-out, the stand-by period namely after finishing touch, because time-out detects the most effective way whether user has write a word.In order to enable handwritten Chinese character input identification actual use, time-out is actually very short, usually between 0.2-0.8 second, generally can be regulated between 0.2-2.0 second by system or user.
But, utilize time-out to determine input whether to complete and sometimes have problem.First, be difficult to the best time-out of setting one, because time-out is very different with the difference of user, that is, writing speed and the interruption between stroke and word are depended on and user to a great extent.Secondly, the difference time-out with word is different.For some word, user will move a very long segment distance between two strokes.When apart from time long, just need the time longer than the time needed for common stroke to stroke.In this case, before user writes a word, there is time-out, will occur before the timeout with time-out after the stroke write be identified as the situation of two words.
In order to solve this problem caused due to time-out, common solution is with the form of person's handwriting for user provides visual feedback, can confirm when identifying.In addition, most handwritten Chinese character input identification software all allows user manually to set the length of time-out.Some solution provides two or more handwriting input district to user, only writes a word to force user an input field.
In fact, person's handwriting feedback must be arranged on the below of person's handwriting, otherwise user can not notice ongoing identification.This way can not be used in not to be had on the device of touch-screen, and such as those only have on the device of handwriting pad.Allow user oneself set time-out and stand-by period (time-out) more flexibly can be provided, but can not deal with problems.Because concerning all words, only has the time-out that identical.In fact, require that it is unpractical for obtaining the real time-out flexibly of different stroke in applicable each word and a word.Those are only had to the portable electric appts of a relatively little screen, only have one relatively limited to write district, therefore, cannot provide multiple and write district.
In addition, due to handwriting recognition be not 100% accurate, user may rewrite a word sometimes, to guarantee that word can be correctly validated.Because Chinese character needs complicated writing process, concerning user, no matter repeatedly write a word muscle power or be all a burden psychologically.And, can hinder like this and identify fast and effectively.In addition, if only have part (such as, a part) correct in primary candidate word, and system provides the words of candidate's word table, user also browses all candidate words (normally 8-10 word) possibly, and this makes selection course more difficult.And if user thinks identification error, he must rewrite whole word.
Rewrite to reduce and be conducive to input and identify, have already been proposed various solution, such as: classified or decomposition (as: the Five-stroke Method and grey a word used in person's names code etc.) by word according to radical etc.United States Patent (USP) 5,923,778 disclose one utilizes radicals by which characters are arranged in traditional Chinese dictionaries information to carry out knowledge method for distinguishing, and proposes a kind of database based on radicals by which characters are arranged in traditional Chinese dictionaries information grading structure word information.United States Patent (USP) 6,272,243 disclose a kind of for the thin method and apparatus carrying out inputting of handwriting, and it has a predefined sub-input field.But it is only suitable for inputting Japanese.
Summary of the invention
The object of the present invention is to provide a kind of hand-written Chinese character input recognition method of improvement, it substantially not by the impact of time-out, and can tolerate that time-out does not even affect by time-out completely.
The present invention also aims to the hand-written Chinese character input recognition method providing a kind of improvement, it can reduce the rewriting in handwritten Chinese character input identifies, increases the speed of input and allows to revise the part of a word.
According to an aspect of the present invention, provide a kind of hand-written Chinese character input recognition method for electronic installation of improvement, comprise the following steps: according to the Chinese character writing district write of predetermined rule identification user at described electronic installation, produce a candidate's word table in above-mentioned identification step identification, and show described candidate's word table in a viewing area of described electronic installation; Wherein said candidate's word table at least comprises the current word and this current word and the candidate's combinatorics on words being identified before this current word and showing that have just been identified.
According to another aspect of the present invention, provide a kind of hand-written Chinese character input recognition method for electronic installation of improvement, comprise and identify that user writes the step of the Chinese character that district writes of described electronic installation, wherein said Chinese Character Recognition only just completes when meeting following condition: the starting point of previous stroke or intermediate point be not or not a predetermined beginning district, front several stroke forms a word completed, and the initial point of current stroke or intermediate point are in described beginning district.
According to a further aspect of the invention, provide a kind of hand-written Chinese character input recognition method for electronic installation of improvement, it comprises and identifies that user writes the step of the Chinese character that district writes of described electronic installation, and writes described the step that district is presented at the main candidate word table of described identification step identification; Wherein said display is included in the different piece that background parts points out the font of this primary candidate word, and described notification portion forms one independently writes district, writes in district, can identify independently at this.
Accompanying drawing explanation
Illustrate embodiments of the invention with reference to the accompanying drawings.
Figure 1A and 1B schematically illustrates the mistake identification utilizing the overtime hand-written Chinese character input recognition method carrying out the prior art identified to occur;
Fig. 2 shows an embodiment according to the inventive method;
Fig. 3 is the process flow diagram of embodiment described in Fig. 2;
Fig. 4 is another embodiment according to the inventive method;
Fig. 5 is the process flow diagram of embodiment described in Fig. 4;
Fig. 6 A and 6B is another embodiment according to the inventive method.
Fig. 7 is the process flow diagram of embodiment described in Fig. 6.
Embodiment
Because handwritten Chinese character input identification can utilize various mode well known in the art to realize, and conventional system or software can be used to identify, for the sake of simplicity, identifying itself is not described in detail at this.
First with reference to Fig. 1, wherein Figure 1A schematically illustrates the mistake identification utilizing the overtime hand-written Chinese character input recognition method carrying out the prior art identified to occur.As shown in Figure 1A, the bipartite word " bright " of a left right model is write in user's plan.He first writes " day " on the left side usually, then writes " moon " on the right.Because " bright " is by can independently become the radical of word " day " and " moon " two parts to form, he needs the first stroke (inputting/write the top part in centre in district) from the mobile longer segment distance of the finishing touch (inputting/write the centre part on the lower in district) of left-half " day " to right half part " moon ", and this spends the long time and may occur of short duration pause between the two sections.If the time of pausing is longer than predetermined time-out, the part on the left side can be identified as " day " or " moon " word by system, and shows " day " and " moon " in candidate's word table.Then, system the part on the right is identified as " moon " or " day " and in candidate's word table " moon " and " day " of Identification display.In other words, due to time-out, two parts are identified as two independently words by system.
The identification of the word that two parts that same problem also appears in mo(u)ld bottom half are formed.As shown in Figure 1B, Chinese character " fortunately " is by radicals by which characters are arranged in traditional Chinese dictionaries " soil " and the latter half formation or not complete word.Due to time-out, system may be identified as two words by " fortunately " word, i.e. " soil " word and " sheep " word looking like the latter half.
When practical application, adjustment stand-by period (time-out) does not have anything to help, because time-out is different with the difference of Chinese character, stroke, writing style and user.Even same user, concerning him, fixing time-out also and inapplicable all words.
Fig. 2 shows an embodiment of the method according to improvement of the present invention.This embodiment utilizes conventional handwritten Chinese character input identifies and vital candidate's word table, makes it while comprising current word, also comprises the combinatorics on words that this current word is identified and shows before current word therewith.This candidate's word table may be displayed on touch-screen or an independent display screen (when board, usually need independently display screen to be presented at the word that board is write).This embodiment just adds the most probable combination of a word that current word is identified before current word therewith and shows in candidate's word table, does not require that increasing extra display unit takies display screen.
As shown in Figure 2, suppose that same user will write same bipartite word " bright ".According to the rules for writing of stroke, first he will write left-half " day " with the speed being applicable to its writing style, if due to its writing style or other reason, a pause was had before starting to write right half part, and this pause is longer than predetermined time-out time, system will think that input completes, and by known mode, left-half is identified as " day " word." day " is presented at certain position of a display screen as primary candidate word, in the present embodiment, candidate word is presented to be write above district.
User continues to write remainder, i.e. right half part " moon ".System produces new candidate's word table upon timing-out, lists the combination of " day " of " moon " and " moon " that he has just write and identification before this and display, i.e. his " bright " word that will write.Then, " bright " word can be used as one of primary candidate word or candidate word word and is presented at and writes above district.Can Operation system setting be passed through, make " bright " word as primary candidate word automatically enter text area or by user by selecting, such as: to click or otherwise, and choose this word.After selection, this word is moved to text area.
In this embodiment, the word that can be identified needs not to be complete Chinese character, and can be the ingredient of the words such as radical.Such as: if user writing " companion " word, time-out is there is after completing left-half, and left-half is a radical and incomplete Chinese character, before he continues to write right half part " partly ", system is by this radical of identification and show this radical in candidate's word table.After user writes right half part, system by candidate's word table new for generation one, the word " companion " that this table comprises the current word " partly " that just identified and is combined with the radical identified before this and show by " partly ".User can select this word, and this word is moved on to text area by system.
In addition, described combination must form a complete word.According to size and the layout of display screen, candidate's word table can comprise maximum 10 words, so that select.
Like this, by the most probable combination of a word only increasing current word be identified before current word therewith in candidate's word table and show, a just word usually, can improve the efficiency of identification greatly, and need not increase display unit and occupy display screen.
Fig. 3 shows the process flow diagram of Fig. 2 embodiment.When user starts to write on touch-screen or board, detect and start.System detects the interruption (time-out) (step 102) whether having between stroke and be longer than the schedule time at any time.If systems axiol-ogy is to time-out, then will identify the word (step 201) be made up of the stroke before time-out, then, the word (step 202) of Identification display in candidate's word table.Simultaneity factor continues to detect (step 103).If another time-out (step 104) detected, then carry out identifying (step 105) and display (step 106).In step 106, system be presented at step 105 identify word and step 105 identify word and step 201 and 202 identify and display combinatorics on words.If time-out do not detected, then continue to detect.After the display of step 106, the word that user selects, according to the selection of user, is placed in text editing district by system.
Fig. 4 is another embodiment according to the inventive method.Except utilizing above-mentioned candidate's word table, by the position of stroke on touch-screen or board of detected words, time-out almost can be eliminated completely on the impact identified.
Because Chinese-character writing follows rule from left to right and from top to bottom, such as: on touch-screen/board, write normally from the upper left corner of writing district, terminate in the lower right corner, the position of a word first stroke of a Chinese character, can namely write the upper left quarter in district, be defined as in one " beginning district ".The size starting district is slightly larger like write district or writing frame 1/4th, so that most of user can start to write in beginning district.If a word comprises two or more part, such as: left and right or up and down two parts, can from place beyond district start to write another part.In the present embodiment, utilize this feature of Chinese charater input to detect a word and whether write, and whether start writing of another word.
According to the present embodiment, in situations, a stroke will be considered to the beginning of a new word: 1) starting point of previous stroke or front several stroke or intermediate point be not or not beginning district; 2) front several stroke forms a complete word; 3) starting point of current stroke or the intermediate point of current stroke are in beginning district.That is, only when above-mentioned three conditions meet simultaneously, just think that the word be made up of front several stroke writes, current stroke is the beginning of a new word.Therefore, need not wait timeout, according to above-mentioned condition instead of time-out, system will determine whether a word writes.
As shown in Figure 4, start district in the upper left corner of writing district or writing frame, and can mark with line or figure, start to write in this region to point out user.
Same for " bright " word, this word is made up of left and right two parts and should writes from " day " word on the left side is other.The starting point of first three stroke that " day " word is other and intermediate point are all in beginning district.Although the starting point of the 4th may beyond beginning district, first three does not form a complete word.Therefore, the beginning of the 4th is not considered to the beginning of a new word.Right half part " moon " generally from start to write beyond district.Although left-half " day " also can form a complete word as radical, the first stroke of right half part " moon " can not be considered to the beginning of a new word, because the first stroke of " moon " is beyond beginning district, does not meet above-mentioned 3rd condition.System can detect the starting point of each stroke, to determine whether according to this rule to write a word.Also can arrange the intermediate point making each stroke of systems axiol-ogy, namely whether the part of the centre of stroke drops on and starts district.The word write can be identified and be presented at candidate block.
Because user may start in beginning district " moon " of writing right half part due to reasons such as ignorance, and this may cause system " moon " of right half part to be mistakenly identified as complete " moon " word, therefore, candidate's word table is except comprising current word, also should comprise current word and the combinatorics on words be close to before this current word, as reference to Figure 2.In this example, " moon " and " bright " is all displayed in candidate's word table, therefore, due to user fails the mistake that causes starting to start to write right half part " moon " beyond district can not the correct identification of influential system.
Fig. 5 shows the flow process of embodiment described in Fig. 4.When user starts to write on touch-screen or board, detect and start.Whether first system detect the starting point/intermediate point of previous stroke in predetermined beginning district (step 301).If not, then before detecting, whether several stroke forms a complete Chinese character (step 302).If so, then continue to detect, until detect that the starting point/intermediate point of a stroke is not in beginning district (step 401).If front several stroke forms a complete Chinese character, then whether detect current stroke starting point/intermediate point in beginning district (step 303).If the result detected is affirmative, then the word that front several stroke is formed is identified (step 304), and show word that (step 305) identifies in step 304 and in this previous round detects and the word identifying and show.If the result of step 303 is negatives, then get back to step 401.Finally, system, according to the selection of user, produces and selected word is placed in text editing district.
Fig. 6 A and 6B is another embodiment according to the inventive method, and it makes user partly can revise a word.
According to Hanzi font directory system (SKIP), Chinese character can be divided into four kinds of fonts, namely left right model (such as: " bright " word) as follows, upper mo(u)ld bottom half (such as: " Wu " word), encirclement type (such as: " state " word) and solid type (such as: " greatly " word).Thus, except the district of writing at display screen presets one and starts except district, can by some way, such as: color or gray scale (when single color display screen) prompting are with the font of the word identified.
Each uses the part of color tips, such as: the left half of left right model and right half form an independently cog region respectively, at this, system can identify a complete word or a radical etc., but the whole primary candidate word identified in district of writing should be made to be a complete word.
As shown in Figure 6A, touch-screen write district's input Chinese character " mix " time, user starts from the upper left corner (district).The input of system of users identifies.Identification can be undertaken by the method described in Fig. 2, also can be undertaken by the method for Fig. 4, even can identify in a known manner.Due to, such as: careless handwriting, write district display primary candidate word be " companion " instead of he to write " mixing ", the background of writing district points out this word for left right model with different colors or gray scale.Now, user need not rewrite whole word, because primary candidate word " being almost correct ", namely look the word will write as user, just left-half is not right.Now, user only can rewrite left-half.When user rewrites left-half, the background color (gray scale) of left field changes, and to confirm that user only revises left-half, and right half part remains unchanged.System produces a new primary candidate word according to the amendment of user and " mixes ", and this is the word that will write of user just.
Candidate word also can be simultaneously displayed in candidate's word table, such as: shown in Fig. 4 writing in the candidate's word table above district.
Another kind of mode is, makes candidate's word table comprise all (determine according to the quantity of the word that can show) with the radical of user's selection or the word of radicals by which characters are arranged in traditional Chinese dictionaries.In this case, user can select correct part writing district, instead of the part of amendment mistake.As shown in Figure 6B, when user notice shown primary candidate word be not he in fact to write word time, he can select correct part, such as: select correct part by the region (right side area) clicked with correct part.Then, all words with correct part " partly " are all displayed in candidate's word table, in this example, and " companion ", " mixing ", stumbles " etc.User can pass through from candidate's word table, such as: click the word (" mixing ") selecting him to write and select " mixing " word.
The present embodiment is not suitable for the board with independent display screen.
Fig. 7 is the process flow diagram of embodiment described in Fig. 6.After user writes a word, system is with the method for Fig. 2 or Fig. 4, or known mode identifies, show the primary candidate word (step 502) be identified subsequently, and the font (step 503) of this word is pointed out by color/gray scale, different color/gray scales represents the not same district of font.If the word of display is exactly the word (step 504) that user writes, then system is according to the selection of user, and the word selected by generation is also placed on text editing district (step 505).If the character segment shown by step 503 is correct, user can select the part confirming correct part or directly amendment mistake.If user selects to confirm correct part (step 601), system is by generation candidate's word table (step 602), and this table comprises all words containing this correct part.If user selects the part (step 603) of directly amendment mistake, the color/gray scale by changing amendment part is pointed out user by system, identifies and part after display update.
Although describe the mode of prompting user for color/gray scale, obviously also alternate manner well known to those skilled in the art can be adopted.
Below invention has been described by way of example, but the present invention is not limited to described embodiment, and those skilled in the art within the scope of the appended claims, can make various amendment to the present invention.
Claims (12)
1. the equipment of the input of the handwritten Chinese character for the electronic installation identification improved, comprise for identifying that user writes the device of the Chinese character that district writes of described electronic installation, wherein said identification only just completes when meeting following condition: the starting point of previous stroke or intermediate point be not or not a predetermined beginning district, front several stroke forms a word completed, and the starting point of current stroke or intermediate point are in described beginning district.
2. equipment according to claim 1, writes the upper left quarter in district described in wherein said beginning district is positioned at.
3., according to the equipment of claim 1 or 2, described in the area in wherein said beginning district is greater than, write 1/4th of district.
4. equipment according to claim 1, described equipment also comprises the device for generation of an above-mentioned candidate's word table identified for the device identified, and for showing the device of described candidate's word table in a viewing area of described electronic installation.
5. equipment according to claim 4, wherein said candidate's word table at least comprises the current word and this current word and the candidate's combinatorics on words identifying before this current word and show that have just been identified.
6. equipment according to claim 4, also comprises the device for selecting a word in the described candidate's word table from the display of described candidate word viewing area.
7. the hand-written Chinese character input recognition method for electronic installation improved, comprise and identify that user writes the Chinese character step of writing in district of described electronic installation, wherein said identification only just completes when meeting following condition: the starting point of previous stroke or intermediate point be not or not a predetermined beginning district, front several stroke forms a word completed, and the starting point of current stroke or intermediate point are in described beginning district.
8. method according to claim 7, writes the upper left quarter in district described in wherein said beginning district is positioned at.
9., according to the method for claim 7 or 8, described in the area in wherein said beginning district is greater than, write 1/4th of district.
10. method according to claim 7, also comprises the step of generation one at candidate's word table of above-mentioned identification step identification, and shows the step of described candidate's word table in a viewing area of described electronic installation.
11. methods according to claim 10, wherein said candidate's word table at least comprises the current word and this current word and the candidate's combinatorics on words identifying before this current word and show that have just been identified.
12. methods according to claim 10, also comprise the step selecting a word from described candidate's word table of described candidate word viewing area display.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200310115725A CN1622121B (en) | 2003-11-28 | 2003-11-28 | Modified handwritten Chinese character input recognition method |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200310115725A Division CN1622121B (en) | 2003-11-28 | 2003-11-28 | Modified handwritten Chinese character input recognition method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102981753A CN102981753A (en) | 2013-03-20 |
| CN102981753B true CN102981753B (en) | 2015-10-07 |
Family
ID=34760531
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210249413.4A Expired - Fee Related CN102981753B (en) | 2003-11-28 | 2003-11-28 | The hand-written Chinese character input recognition method improved |
| CN200310115725A Expired - Fee Related CN1622121B (en) | 2003-11-28 | 2003-11-28 | Modified handwritten Chinese character input recognition method |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200310115725A Expired - Fee Related CN1622121B (en) | 2003-11-28 | 2003-11-28 | Modified handwritten Chinese character input recognition method |
Country Status (2)
| Country | Link |
|---|---|
| CN (2) | CN102981753B (en) |
| HK (1) | HK1077900A1 (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104656938B (en) * | 2013-11-19 | 2018-07-06 | 阿尔派株式会社 | Input device and character input method |
| US10095673B2 (en) | 2014-11-17 | 2018-10-09 | Lenovo (Singapore) Pte. Ltd. | Generating candidate logograms |
| CN104598148B (en) * | 2014-12-16 | 2017-09-19 | 任文 | A kind of computer contact screen handwritten Chinese character method |
| CN107870678A (en) * | 2016-09-26 | 2018-04-03 | 中兴通讯股份有限公司 | A kind of hand-written inputting method and device |
| TWI664604B (en) * | 2018-03-20 | 2019-07-01 | 王佑鈞 | System for construction and application of handwriting chinese character glyph sets to be used in a computer system |
| US20220122477A1 (en) * | 2020-10-20 | 2022-04-21 | Holistic Language Solutions LLC | Computerized method and apparatus for determining accuracy of written characters and stroke order and compliance with rules and providing visual and audio feedback |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1232204A (en) * | 1998-04-16 | 1999-10-20 | 国际商业机器公司 | Chinese handwriting identifying method and device |
| CN1279443A (en) * | 1999-06-28 | 2001-01-10 | 夏普公司 | Method and device for correcting faults in symbols identification |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1040340A (en) * | 1996-05-01 | 1998-02-13 | Nippon Steel Corp | Handwritten character recognizing device and recording medium |
| JPH10162101A (en) * | 1996-11-28 | 1998-06-19 | Hitachi Ltd | Device and method for recognizing handwritten character |
| JPH11191138A (en) * | 1997-12-25 | 1999-07-13 | Toshiba Corp | Kanji input method utilizing handwritten character recognizing function and character input device |
| CN1197333A (en) * | 1998-03-09 | 1998-10-28 | 柏凯 | Computer hand writing input machine codes |
| US6681044B1 (en) * | 2000-03-29 | 2004-01-20 | Matsushita Electric Industrial Co., Ltd. | Retrieval of cursive Chinese handwritten annotations based on radical model |
-
2003
- 2003-11-28 CN CN201210249413.4A patent/CN102981753B/en not_active Expired - Fee Related
- 2003-11-28 CN CN200310115725A patent/CN1622121B/en not_active Expired - Fee Related
-
2005
- 2005-11-07 HK HK05109897.0A patent/HK1077900A1/en not_active IP Right Cessation
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1232204A (en) * | 1998-04-16 | 1999-10-20 | 国际商业机器公司 | Chinese handwriting identifying method and device |
| CN1279443A (en) * | 1999-06-28 | 2001-01-10 | 夏普公司 | Method and device for correcting faults in symbols identification |
Also Published As
| Publication number | Publication date |
|---|---|
| HK1077900A1 (en) | 2006-02-24 |
| CN1622121A (en) | 2005-06-01 |
| CN102981753A (en) | 2013-03-20 |
| CN1622121B (en) | 2012-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5140377B2 (en) | Browser control method and system using image | |
| KR100261011B1 (en) | Document input device and the method thereof | |
| US20020190946A1 (en) | Pointing method | |
| JPH04326488A (en) | Hand written recognition system and method by character template | |
| US20030099398A1 (en) | Character recognition apparatus and character recognition method | |
| US7562314B2 (en) | Data processing apparatus and method | |
| JP3292752B2 (en) | Gesture processing device and gesture processing method | |
| CN102981753B (en) | The hand-written Chinese character input recognition method improved | |
| KR100298547B1 (en) | Character input apparatus | |
| Hornbuckle | The computer graphics user/machine interface | |
| CN100410966C (en) | Modified hand-written Chinese character input recognition method | |
| US20020085772A1 (en) | Intelligent correction key | |
| KR100320062B1 (en) | Hand-written input display | |
| AU7581691A (en) | Display system and method for context-based scrolling | |
| US6973214B1 (en) | Ink display for multi-stroke hand entered characters | |
| JPH1063408A (en) | Portable information terminal equipment | |
| Dell et al. | Improving form-based data entry with image snippets | |
| JPH11345072A (en) | Gesture processor and gesture processing method | |
| JP3153704B2 (en) | Character recognition device | |
| Bunke et al. | A tool for versatile and user-friendly document correction | |
| JPH0562008A (en) | Character recognition method | |
| KR100448967B1 (en) | Position magnify method of Enter Key and equipment thereof | |
| JPH10320107A (en) | Handwritten character input device having handwritten character recognizing function | |
| JPH1078956A (en) | Information processor | |
| CN102906733B (en) | The successional designator of text |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20160118 Address after: Espoo, Finland Patentee after: Technology Co., Ltd. of Nokia Address before: Espoo, Finland Patentee before: Nokia Oyj |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20151007 Termination date: 20191128 |