CN106951890A - Character recognition method and device of dictionary pen - Google Patents
Character recognition method and device of dictionary pen Download PDFInfo
- Publication number
- CN106951890A CN106951890A CN201710083990.3A CN201710083990A CN106951890A CN 106951890 A CN106951890 A CN 106951890A CN 201710083990 A CN201710083990 A CN 201710083990A CN 106951890 A CN106951890 A CN 106951890A
- Authority
- CN
- China
- Prior art keywords
- word
- identified
- feature
- storehouse
- font
- 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 20
- 238000013515 script Methods 0.000 claims description 16
- 238000013507 mapping Methods 0.000 claims description 11
- 238000005516 engineering process Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 239000000686 essence Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 210000003813 thumb Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Character Discrimination (AREA)
Abstract
The invention is applicable to the technical field of computers, and provides a method and a device for recognizing characters by a dictionary pen, wherein the method comprises the following steps: when a scanning command of a user is received, characters to be recognized are obtained through a preset scanning end, the characters to be recognized are recognized according to a preset handwriting font library and a printing general font library, character information of the characters to be recognized is obtained in a preset dictionary library according to a recognition result corresponding to the characters to be recognized, and the character information of the characters to be recognized is displayed and output, so that the handwriting font library and the printing general font library are added to a dictionary pen, recognition of the handwriting characters and the printing general font characters on the dictionary pen is achieved, and character recognition rate of the dictionary pen is effectively improved.
Description
Technical field
The invention belongs to the character recognition method and device of field of computer technology, more particularly to a kind of dictionary pen.
Background technology
Students need to only use dictionary pen to sweep word and sweep, and just can obtain pronunciation, lexical or textual analysis and translation of the word etc.
Information, without repeatedly going to thumb dictionary book, also need not every time go to school and carry heavy dictionary book, it is seen that the appearance of dictionary pen
It is a big Gospel of student group.
At present, most dictionary pen is all only limited to the bookish print hand writing of identification printing, and in daily life,
Hand-written contribution or material (the prescription list that such as doctor outputs) or relatively common, the also often appearance one on printing books
The manuscript of a little writers, is changed greatly due to handwritten text, great personal style, and the difference of print hand writing is larger, only limits
Handwritten text can not be recognized well in the dictionary pen of identification print hand writing.
The content of the invention
It is an object of the invention to provide the character recognition method and device of a kind of dictionary pen, it is intended to solves due to existing skill
Art can not provide a kind of character recognition method of effective dictionary pen so that dictionary pen is generally only used for recognizing print hand writing,
And the problem of preferably can not recognize handwritten text.
On the one hand, the invention provides a kind of character recognition method of dictionary pen, methods described comprises the steps:
When receiving the scan command of user, word to be identified is obtained by default scanning end;
According to default handwriting font object library and printing general font storehouse, the word to be identified is identified;
According to the corresponding recognition result of the word to be identified, the word to be identified is obtained in default dictionary
Text information, the text information of word to be identified described in display output.
On the other hand, the invention provides a kind of character recognition device of dictionary pen, described device includes:
Scan module, for when receiving the scan command of user, word to be identified to be obtained by default scanning end;
Identification module, for according to default handwriting font object library and printing general font storehouse, entering to the word to be identified
Row identification;And
Output module is inquired about, for according to the corresponding recognition result of the word to be identified, being obtained in default dictionary
The text information of the word to be identified is taken, the text information of word to be identified described in display output.
The present invention is when receiving the scan command of user, by default scanning end acquisition word to be identified, and according to
Default handwriting font object library and printing general font storehouse, word to be identified are identified, after recognition result is obtained, according to knowledge
Other result obtains the text information of word to be identified, last display output text information, so that logical in default dictionary
Cross and increase handwriting font object library and printing general font storehouse on dictionary pen, realize the upper handwritten text of dictionary pen and print general
The identification of font file, is effectively improved the Text region rate of dictionary pen.
Brief description of the drawings
Fig. 1 is that the character recognition method for the dictionary pen that the embodiment of the present invention one is provided realizes flow chart;
Fig. 2 is the structural representation of the character recognition device for the dictionary pen that the embodiment of the present invention two is provided;And
Fig. 3 is the preferred structure schematic diagram of the character recognition device for the dictionary pen that the embodiment of the present invention two is provided.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Implementing for the present invention is described in detail below in conjunction with specific embodiment:
Embodiment one:
Fig. 1 shows that the character recognition method for the dictionary pen that the embodiment of the present invention one is provided realizes flow, for the ease of
Illustrate, illustrate only the part related to the embodiment of the present invention, details are as follows:
In step S101, when receiving the scan command of user, word to be identified is obtained by default scanning end.
The embodiment of the present invention is applied to the dictionary pen with textual scan function.After the scan command of user is received,
Default scanning end is opened, and the word of user designated area is scanned by scanning end, to obtain these words.Specifically, in advance
If scanning end can be located at dictionary pen nib at, scanning end can get all words of user designated area, text to be identified
Word can be one or more of these words word.
In step s 102, according to default handwriting font object library and printing general font storehouse, word to be identified is known
Not.
In embodiments of the present invention, the word of a variety of hand-written scripts is stored in handwriting font object library, specifically can from network or
Person is obtained storing the text of the general font on printed text in these hand-written scripts, printing general font storehouse by user input
Word.After word to be identified is got, the feature of word to be identified can be first extracted, by this feature and printing general font storehouse Chinese
The feature of word is matched, when the match is successful, with the successful word of characters matching to be identified in acquisition printing general font storehouse,
The word is the recognition result of word to be identified.
, can be by text to be identified when the feature and the characteristic matching of word in printing general font storehouse of word to be identified fail
The feature of word is matched with the feature of word in handwriting font object library, when the match is successful, is obtained in handwriting font object library with waiting to know
The other successful word of characters matching, then, according to the word pre-established between handwriting font object library and printing general font storehouse
The word that the match is successful in mapping relations, acquisition handwriting font object library corresponding word in printing general font storehouse, now, printing
Corresponding word is the recognition result of word to be identified in general font storehouse.
Alternatively, printing general font storehouse can be first set up, then obtains the corresponding handwritten word of word in printing general font storehouse
Body, resettles handwriting font object library, and these hand-written scripts are stored in handwriting font object library, while according to word in handwriting font object library
With the corresponding relation of word in printing general font storehouse, the word mapping set up between handwriting font object library and printing general font storehouse
Relation, specifically, the word of a printing general font can correspond to the word of multiple different hand-written scripts.
In step s 103, according to the corresponding recognition result of word to be identified, obtain to be identified in default dictionary
The text information of word, the text information of display output word to be identified.
In embodiments of the present invention, after word to be identified is matched in printing general font storehouse and handwriting font object library, obtain
Corresponding word, the corresponding word is recognition result, searches the text information of the word in dictionary, and by the word
Information is set to the text information of word to be identified, the text information of last display output word to be identified.Specifically, dictionary
In store the text information of multiclass word, wherein, text information may include the pronunciation of word, lexical or textual analysis, group word and translation etc..
Specifically, the text information of word to be identified can be exported by modes such as voice, words.
In embodiments of the present invention, after scanning gets word to be identified, by default handwriting font object library and printing
Word to be identified is identified in brush general font storehouse, and further according to recognition result, text to be identified is obtained in default dictionary
The corresponding text information of word, the text information of last display output word to be identified, it is achieved thereby that dictionary pen is to printing type face
With the identification of hand-written script, the Text region rate of dictionary pen is effectively improved.
Can be with one of ordinary skill in the art will appreciate that realizing that all or part of step in above-described embodiment method is
The hardware of correlation is instructed to complete by program, described program can be stored in a computer read/write memory medium,
Described storage medium, such as ROM/RAM, disk, CD.
Embodiment two:
Fig. 2 shows the structure of the character recognition device for the dictionary pen that the embodiment of the present invention two is provided, for convenience of description,
The part related to the embodiment of the present invention is illustrate only, including:
Scan module 21, for when receiving the scan command of user, text to be identified to be obtained by default scanning end
Word.
In embodiments of the present invention, after the scan command of user is received, default scanning end is opened, and pass through scanning
The word of end scanning user designated area, to obtain these words.Specifically, default scanning end can be located at the nib of dictionary pen
Place, scanning end can get all words of user designated area, and word to be identified can be one or more of these words
Word.
Identification module 22, for according to default handwriting font object library and printing general font storehouse, being carried out to word to be identified
Identification.
In embodiments of the present invention, the word of a variety of hand-written scripts is stored in handwriting font object library, specifically can from network or
Person is obtained storing the text of the general font on printed text in these hand-written scripts, printing general font storehouse by user input
Word.After word to be identified is got, the feature of word to be identified can be first extracted, by this feature and printing general font storehouse Chinese
The feature of word is matched, when the match is successful, with the successful word of characters matching to be identified in acquisition printing general font storehouse,
The word is the recognition result of word to be identified.
, can be by text to be identified when the feature and the characteristic matching of word in printing general font storehouse of word to be identified fail
The feature of word is matched with the feature of word in handwriting font object library, when the match is successful, is obtained in handwriting font object library with waiting to know
The other successful word of characters matching, then, according to the word pre-established between handwriting font object library and printing general font storehouse
The word that the match is successful in mapping relations, acquisition handwriting font object library corresponding word in printing general font storehouse, now, printing
Corresponding word is the recognition result of word to be identified in general font storehouse.
Output module 23 is inquired about, for according to the corresponding recognition result of word to be identified, being obtained in default dictionary
The text information of word to be identified, the text information of display output word to be identified.
In embodiments of the present invention, after word to be identified is matched in printing general font storehouse and handwriting font object library, obtain
Corresponding word, the corresponding word is recognition result, searches the text information of the word in dictionary, and by the word
Information is set to the text information of word to be identified, the text information of last display output word to be identified.Specifically, dictionary
In store the text information of multiclass word, wherein, text information may include the pronunciation of word, lexical or textual analysis, group word and translation etc..
Specifically, the text information of word to be identified can be exported by modes such as voice, words.
Preferably, as shown in figure 3, the character recognition device of dictionary pen also includes initialization module 31, wherein:
Initialization module 31, for according to printing general font storehouse, obtaining the corresponding hand of word in printing general font storehouse
Write body, and according to hand-written script, sets up handwriting font object library and word mapping relations.
In embodiments of the present invention, printing general font storehouse can be first set up, then obtains word pair in printing general font storehouse
The hand-written script answered, resettles handwriting font object library, and these hand-written scripts are stored in handwriting font object library, while logical according to printing
With the corresponding relation of word in word in fontlib and handwriting font object library, set up between printing general font storehouse and handwriting font object library
Word mapping relations.Specifically, the word of a printing general font can correspond to the word of multiple different hand-written scripts.
Preferably, as shown in figure 3, identification module 22 also includes the first matching module 321, the first matching result acquisition module
322nd, the second matching module 323, the second matching result acquisition module 324 and mapping text acquisition module 325, wherein:
First matching module 321, the feature for extracting word to be identified is general with printing by the feature of word to be identified
The feature of word is matched in fontlib;
First matching result acquisition module 322, for when the feature of word to be identified and word in printing general font storehouse
Characteristic matching success when, obtain the word that the match is successful in printing general font storehouse;
Second matching module 323, for when the feature of word to be identified and the feature of word in printing general font storehouse
During with failure, the feature of word to be identified is matched with the feature of word in handwriting font object library;
Second matching result acquisition module 324, for as the spy of word in the feature and handwriting font object library of word to be identified
When levying that the match is successful, the word that the match is successful in handwriting font object library is obtained;And
Text acquisition module 325 is mapped, for according to default word between handwriting font object library and printing general font storehouse
The word that the match is successful in mapping relations, acquisition handwriting font object library corresponding word in printing general font storehouse.
Preferably, as shown in figure 3, inquiry output module 23 includes text information acquisition module 331, wherein:
Text information acquisition module 331, for obtaining corresponding word after Text region to be identified, is searched in dictionary
The text information of correspondence word after identification, the word that the text information of correspondence word after identification is set into word to be identified is believed
Breath.
In embodiments of the present invention, after scanning gets word to be identified, by default handwriting font object library and printing
Word to be identified is identified in brush general font storehouse, and further according to recognition result, text to be identified is obtained in default dictionary
The corresponding text information of word, the text information of last display output word to be identified, it is achieved thereby that dictionary pen is to printing type face
With the identification of hand-written script, the Text region rate of dictionary pen is effectively improved.
In embodiments of the present invention, each module of the character recognition device of dictionary pen can be by corresponding hardware or software module
Realize, each module can be independent soft and hardware module, a soft and hardware module can also be integrated into, herein not to limit
The present invention.
Presently preferred embodiments of the present invention is the foregoing is only, is not intended to limit the invention, all essences in the present invention
Any modification, equivalent and improvement made within refreshing and principle etc., should be included within the scope of the present invention.
Claims (10)
1. a kind of character recognition method of dictionary pen, it is characterised in that methods described comprises the steps:
When receiving the scan command of user, word to be identified is obtained by default scanning end;
According to default handwriting font object library and printing general font storehouse, the word to be identified is identified;
According to the corresponding recognition result of the word to be identified, the word of the word to be identified is obtained in default dictionary
Information, the text information of word to be identified described in display output.
2. the method as described in claim 1, it is characterised in that according to default handwriting font object library and printing general font storehouse,
The step of word to be identified is identified, including:
The feature of the word to be identified is extracted, by the feature of the word to be identified and word in the printing general font storehouse
Feature matched;
When the feature of the word to be identified is with the characteristic matching success of word in the printing general font storehouse, obtain described
Print the word that the match is successful in general font storehouse.
3. method as claimed in claim 2, it is characterised in that by the feature of the word to be identified and the printing general words
After the step of feature of word is matched in body storehouse, methods described also includes:
When the feature and the characteristic matching of word in the printing general font storehouse of the word to be identified fail, treated described
The feature of identification word is matched with the feature of word in the handwriting font object library;
When the feature of the word to be identified is with the characteristic matching success of word in the handwriting font object library, obtain described hand-written
The word that the match is successful in fontlib;
According to default word mapping relations between the handwriting font object library and the printing general font storehouse, obtain described hand-written
The word that the match is successful in fontlib corresponding word in the printing general font storehouse.
4. the method as described in claim 1, it is characterised in that according to the corresponding recognition result of the word to be identified, pre-
If dictionary in the step of obtain the text information of the word to be identified, including:
Corresponding word after the Text region to be identified is obtained, correspondence word after the identification is searched in the dictionary
Text information, the text information of correspondence word after the identification is set to the text information of the word to be identified.
5. method as claimed in claim 3, it is characterised in that when receiving the scan command of user, swept by default
Retouch before the step of end obtains word to be identified, methods described also includes:
According to the printing general font storehouse, the corresponding hand-written script of word in the printing general font storehouse is obtained, and according to
The hand-written script, sets up the word mapping relations in the handwriting font object library and the printing general font storehouse.
6. a kind of character recognition device of dictionary pen, it is characterised in that described device includes:
Scan module, for when receiving the scan command of user, word to be identified to be obtained by default scanning end;
Identification module, for according to default handwriting font object library and printing general font storehouse, knowing to the word to be identified
Not;And
Output module is inquired about, for according to the corresponding recognition result of the word to be identified, institute to be obtained in default dictionary
The text information of word to be identified is stated, the text information of word to be identified described in display output.
7. device as claimed in claim 6, it is characterised in that the identification module includes:
First matching module, the feature for extracting the word to be identified, by the feature of the word to be identified and the print
The feature of word is matched in brush general font storehouse;And
First matching result acquisition module, for when the feature of the word to be identified and word in the printing general font storehouse
Characteristic matching success when, obtain the word that the match is successful in the printing general font storehouse.
8. device as claimed in claim 7, it is characterised in that the identification module also includes:
Second matching module, for when the feature of the word to be identified and the feature of word in the printing general font storehouse
During with failure, the feature of the word to be identified is matched with the feature of word in the handwriting font object library;
Second matching result acquisition module, for as the spy of word in the feature of the word to be identified and the handwriting font object library
When levying that the match is successful, the word that the match is successful in the handwriting font object library is obtained;And
Text acquisition module is mapped, for according to default word between the handwriting font object library and the printing general font storehouse
The word that the match is successful in mapping relations, the acquisition handwriting font object library corresponding word in the printing general font storehouse.
9. device as claimed in claim 6, it is characterised in that the inquiry output module includes:
Text information acquisition module, for obtaining corresponding word after the Text region to be identified, is looked into the dictionary
The text information of correspondence word after the identification is looked for, the text information of correspondence word after the identification is set to described to be identified
The text information of word.
10. device as claimed in claim 8, it is characterised in that described device also includes:
Initialization module, it is corresponding for according to the printing general font storehouse, obtaining word in the printing general font storehouse
Hand-written script, and according to the hand-written script, set up the handwriting font object library and the word mapping relations.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710083990.3A CN106951890A (en) | 2017-02-16 | 2017-02-16 | Character recognition method and device of dictionary pen |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710083990.3A CN106951890A (en) | 2017-02-16 | 2017-02-16 | Character recognition method and device of dictionary pen |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106951890A true CN106951890A (en) | 2017-07-14 |
Family
ID=59467726
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710083990.3A Pending CN106951890A (en) | 2017-02-16 | 2017-02-16 | Character recognition method and device of dictionary pen |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106951890A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109753967A (en) * | 2018-12-29 | 2019-05-14 | 北京师范大学 | A kind of picture character recognition methods |
CN111144191A (en) * | 2019-08-14 | 2020-05-12 | 广东小天才科技有限公司 | Font identification method and device, electronic equipment and storage medium |
CN111597324A (en) * | 2020-05-20 | 2020-08-28 | 北京搜狗科技发展有限公司 | Text query method and device |
CN112862024A (en) * | 2021-04-28 | 2021-05-28 | 明品云(北京)数据科技有限公司 | Text recognition method and system |
CN113963151A (en) * | 2021-11-19 | 2022-01-21 | 广州市讯码通讯科技有限公司 | Character recognition method and recognition device based on light weight neural network |
CN114489447A (en) * | 2022-03-28 | 2022-05-13 | 山东大学 | Word processing control method and system based on user behavior and readable storage medium |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101149804A (en) * | 2006-09-19 | 2008-03-26 | 北京三星通信技术研究有限公司 | Self-adaptive hand-written discrimination system and method |
CN101276414A (en) * | 2008-04-07 | 2008-10-01 | 宇龙计算机通信科技(深圳)有限公司 | Method and device of hand-written character recognition |
CN101853313A (en) * | 2010-07-01 | 2010-10-06 | 无锡骏聿科技有限公司 | Handwriting font object library generating method based on font categorization |
CN201655057U (en) * | 2010-04-21 | 2010-11-24 | 成都时代诺亚舟教育软件有限公司 | Handheld learning device utilizing optical scanning for input |
CN102646023A (en) * | 2012-04-11 | 2012-08-22 | 广东欧珀移动通信有限公司 | Method for generating original user handwriting fonts |
CN104007836A (en) * | 2014-05-07 | 2014-08-27 | 惠州Tcl移动通信有限公司 | Handwriting input processing method and terminal device |
CN105260751A (en) * | 2015-11-02 | 2016-01-20 | 冯清亮 | Character identification method and system |
CN105335198A (en) * | 2015-11-13 | 2016-02-17 | 小米科技有限责任公司 | Font addition method and device |
CN106096524A (en) * | 2016-06-01 | 2016-11-09 | 广东小天才科技有限公司 | Method and device for acquiring beauty degree of Chinese characters |
-
2017
- 2017-02-16 CN CN201710083990.3A patent/CN106951890A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101149804A (en) * | 2006-09-19 | 2008-03-26 | 北京三星通信技术研究有限公司 | Self-adaptive hand-written discrimination system and method |
CN101276414A (en) * | 2008-04-07 | 2008-10-01 | 宇龙计算机通信科技(深圳)有限公司 | Method and device of hand-written character recognition |
CN201655057U (en) * | 2010-04-21 | 2010-11-24 | 成都时代诺亚舟教育软件有限公司 | Handheld learning device utilizing optical scanning for input |
CN101853313A (en) * | 2010-07-01 | 2010-10-06 | 无锡骏聿科技有限公司 | Handwriting font object library generating method based on font categorization |
CN102646023A (en) * | 2012-04-11 | 2012-08-22 | 广东欧珀移动通信有限公司 | Method for generating original user handwriting fonts |
CN104007836A (en) * | 2014-05-07 | 2014-08-27 | 惠州Tcl移动通信有限公司 | Handwriting input processing method and terminal device |
CN105260751A (en) * | 2015-11-02 | 2016-01-20 | 冯清亮 | Character identification method and system |
CN105335198A (en) * | 2015-11-13 | 2016-02-17 | 小米科技有限责任公司 | Font addition method and device |
CN106096524A (en) * | 2016-06-01 | 2016-11-09 | 广东小天才科技有限公司 | Method and device for acquiring beauty degree of Chinese characters |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109753967A (en) * | 2018-12-29 | 2019-05-14 | 北京师范大学 | A kind of picture character recognition methods |
CN111144191A (en) * | 2019-08-14 | 2020-05-12 | 广东小天才科技有限公司 | Font identification method and device, electronic equipment and storage medium |
CN111144191B (en) * | 2019-08-14 | 2024-03-22 | 广东小天才科技有限公司 | Font identification method, font identification device, electronic equipment and storage medium |
CN111597324A (en) * | 2020-05-20 | 2020-08-28 | 北京搜狗科技发展有限公司 | Text query method and device |
CN111597324B (en) * | 2020-05-20 | 2023-10-03 | 北京搜狗科技发展有限公司 | Text query method and device |
CN112862024A (en) * | 2021-04-28 | 2021-05-28 | 明品云(北京)数据科技有限公司 | Text recognition method and system |
CN113963151A (en) * | 2021-11-19 | 2022-01-21 | 广州市讯码通讯科技有限公司 | Character recognition method and recognition device based on light weight neural network |
CN114489447A (en) * | 2022-03-28 | 2022-05-13 | 山东大学 | Word processing control method and system based on user behavior and readable storage medium |
CN114489447B (en) * | 2022-03-28 | 2022-07-12 | 山东大学 | Word processing control method and system based on user behavior and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106951890A (en) | Character recognition method and device of dictionary pen | |
US7983478B2 (en) | Hidden markov model based handwriting/calligraphy generation | |
Nakagawa et al. | Collection of on-line handwritten Japanese character pattern databases and their analyses | |
US7496547B2 (en) | Handwriting recognition using a comparative neural network | |
US7865018B2 (en) | Personalized implicit and explicit character shape adaptation and recognition | |
US20060045337A1 (en) | Spatial recognition and grouping of text and graphics | |
KR20050053498A (en) | Scaled text replacement of ink | |
BRPI0615318A2 (en) | conscious use of writing input style | |
JP2004348714A (en) | System and method for accommodative handwritten character recognition | |
Meshesha et al. | Matching word images for content-based retrieval from printed document images | |
Kaur et al. | A comprehensive survey on word recognition for non-Indic and Indic scripts | |
CN108121987B (en) | Information processing method and electronic equipment | |
JP2023503272A (en) | Gesture Stroke Recognition in Touch-Based User Interface Input | |
US6567548B2 (en) | Handwriting recognition system and method using compound characters for improved recognition accuracy | |
US20050276480A1 (en) | Handwritten input for Asian languages | |
Sareen et al. | Gurmukhi handwritten word conversion using feature extraction using deep learning | |
Ajmire et al. | Handwritten Marathi character (vowel) recognition | |
Asrayev | MA ONLINE HANDWRITING RECOGNITION: Handwriting, recognition, online, offline, text, technologies, system, application. | |
Solangi et al. | Offline-printed sindhi optical text recognition: Survey | |
JP4101345B2 (en) | Character recognition device | |
Agrawal et al. | Data collection for handwriting corpus creation in Indic scripts | |
Kunte et al. | 170wavelet features based on-line recognition of handwritten | |
Paturkar et al. | Handwriting Comparison and Character Analysis | |
Ogli | ONLINE HANDWRITING RECOGNITION | |
Nisa et al. | A Messy Handwriting Dataset with Student Crossouts and Corrections |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170714 |
|
RJ01 | Rejection of invention patent application after publication |