CN111143541A - Character generation system for deep learning based on handwriting - Google Patents
Character generation system for deep learning based on handwriting Download PDFInfo
- Publication number
- CN111143541A CN111143541A CN201911157090.4A CN201911157090A CN111143541A CN 111143541 A CN111143541 A CN 111143541A CN 201911157090 A CN201911157090 A CN 201911157090A CN 111143541 A CN111143541 A CN 111143541A
- Authority
- CN
- China
- Prior art keywords
- handwriting
- input end
- user
- data processing
- processing center
- 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.)
- Granted
Links
- 238000013135 deep learning Methods 0.000 title claims abstract description 25
- 238000013515 script Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 claims 2
- 238000007405 data analysis Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/338—Presentation of query results
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Collating Specific Patterns (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a font generation system based on handwriting deep learning, which comprises a first input end, a second input end and a background data processing center, wherein the first input end is connected with the first input end; the first input end comprises a handwriting input interface, a user performs identity authentication through the first input end, identity authentication information is stored in a background data processing center, the user inputs handwriting through the handwriting input interface of the first input end, alternative standard words are displayed on the interface for the user to confirm the standard words uniquely corresponding to the handwriting of the user, the background data processing center splits and stores the handwriting according to the strokes and radicals of the standard words uniquely corresponding to the handwriting, and the background data processing center performs deep learning through the strokes and radicals of the stored handwriting and combines the strokes and radicals of the stored handwriting into new handwriting containing the stored strokes and radicals of the handwriting notes; the user's own handwriting is used as the output font, so that the formed text content has the characteristics of the user and the recognition degree.
Description
Technical Field
The invention belongs to the technical field of font generation systems, and particularly relates to a font generation system for deep learning based on handwriting.
Background
The Chinese character is one of the oldest characters in the world, has at least thousands of years of history till now, and evolves from oracle-bone characters to the current simplified Chinese character regular script font. From the development of the times, the existing Chinese characters evolve to not need to be written by a pen, the corresponding Chinese characters can be directly input through software, and the characters can be printed by directly writing the characters through the software according to the history trend, namely after the intellectualization is completely popularized, so that the characteristics of the characters independently written by each person can not be shown. If in the future, all intelligent devices fail to work and the results of writing Chinese characters by software are relied on, only the form and meaning of the Chinese characters can be known, and the important information storage and transmission results do not exist at present. That is, as far as the development is concerned, people can only know the shape of the Chinese character and can not write the Chinese character, and the result is unpredictable. Meanwhile, the protection of the modern society on fonts is not perfect enough, the technology of the invention can prompt the user to frequently write handwriting, and the personalized fonts can be saved and converted and output by a computer.
The handwritten handwriting fonts of the users can be obtained under the development of the technology, the one-to-one unique font copyrights of the users are realized, the imposition signatures can be correspondingly reduced in the development trend of comprehensively realizing the electronization and paperless in the future, and the comprehensive safety level improvement is realized on the same aspect of signing and contracting. After acquiring the font handwriting of the user, the development has uniqueness, safety, uniqueness and impossibility in signing a legal meaning contract, publishing personal business and performing handwriting check on the disputed handwriting.
Disclosure of Invention
The invention provides a font generation system for deep learning based on handwritten handwriting, and particularly provides a system for generating the user handwritten handwriting as font output by disassembling and copying the user handwritten handwriting through the system, so that the user experience is improved, and a new font generation mode is provided.
Therefore, the invention provides a font generation system for deep learning based on handwriting, which comprises a first input end, a second input end and a background data processing center, wherein the first input end is used for inputting handwriting data; the first input end comprises a handwriting input interface, a user performs identity verification through the first input end and stores identity verification information in a background data processing center, the user inputs handwriting through the handwriting input interface of the first input end and displays alternative standard words on the interface so that the user can confirm the unique corresponding standard words of the handwriting, the background data processing center separates and stores the handwriting according to the strokes and radicals of the unique corresponding standard words of the handwriting, and the background data processing center performs deep learning through the strokes and radicals of the stored handwriting and combines the strokes and radicals of the stored handwriting into new handwriting containing the stored strokes and radicals of the handwriting notes; when the user passes the identity authentication at the first input end or the second input end, the first input end or the second input end automatically reads the stored information corresponding to the user passing the identity authentication from the background data processing center, and when the user inputs the standard word through the first input end or the second input end, the first input end or the second input end outputs and displays the handwriting corresponding to the standard word.
The first input end at least has a handwriting function as intelligent equipment of an input mode, and the second input end at least has a keyboard as intelligent equipment of the input mode.
The first input end is a mobile phone or a handwriting board, and the second input end is a computer.
When the background data processing center splits the handwriting, one or a plurality of modes of the field character grid, the radical, the continuous stroke and the broken stroke are used for splitting.
After the background data processing center performs deep learning on the handwriting of a certain font correspondingly formed, when a user writes the handwriting of the font through the first input end for the first time, the handwriting of the font written through the first input end by the user for the first time is adopted to replace the handwriting of the font correspondingly formed through the deep learning by the background data processing center and is stored in the background data processing center; and if the user types the font through the first input end or the second input end for the first time in a keyboard mode, outputting the handwriting of the changed font correspondingly formed by deep learning by the background data processing center for displaying.
The invention has the beneficial effects that: the invention discloses a handwriting deep learning-based font generation system, which provides a new font generation mode, can further improve the experience of a user on fonts, enriches the font display mode, and displays the fonts of the user as output fonts, so that the formed text content has the characteristics of the user and has identification degree.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below. In the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
Fig. 1 is a schematic block diagram of the present invention.
FIG. 2 is a flow chart of font generation according to the present invention.
FIG. 3 is a schematic diagram of an embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
As shown in fig. 1, 2 and 3: the system for generating the fonts for deep learning based on the handwritten handwriting comprises a first input end, a second input end and a background data processing center, wherein the first input end is connected with the first input end; the first input end comprises a handwriting input interface, a user performs identity verification through the first input end and stores identity verification information in a background data processing center, the user inputs handwriting through the handwriting input interface of the first input end and displays alternative standard words on the interface so that the user can confirm the unique corresponding standard words of the handwriting, the background data processing center separates and stores the handwriting according to the strokes and radicals of the unique corresponding standard words of the handwriting, and the background data processing center performs deep learning through the strokes and radicals of the stored handwriting and combines the strokes and radicals of the stored handwriting into new handwriting containing the stored strokes and radicals of the handwriting notes; when the user passes the identity authentication at the first input end or the second input end, the first input end or the second input end automatically reads the stored information corresponding to the user passing the identity authentication from the background data processing center, and when the user inputs the standard word through the first input end or the second input end, the first input end or the second input end outputs and displays the handwriting corresponding to the standard word.
The first input end at least has a handwriting function as intelligent equipment of an input mode, and the second input end at least has a keyboard as intelligent equipment of the input mode.
The first input end is a mobile phone or a handwriting board, and the second input end is a computer.
When the background data processing center splits the handwriting, one or a plurality of modes of the field character grid, the radical, the continuous stroke and the broken stroke are used for splitting.
After the background data processing center performs deep learning on the handwriting of a certain font correspondingly formed, when a user writes the handwriting of the font through the first input end for the first time, the handwriting of the font written through the first input end by the user for the first time is adopted to replace the handwriting of the font correspondingly formed through the deep learning by the background data processing center and is stored in the background data processing center; and if the user types the font through the first input end or the second input end for the first time in a keyboard mode, outputting the handwriting of the changed font correspondingly formed by deep learning by the background data processing center for displaying.
In this embodiment, the specific generation manner of the handwritten handwriting is as follows:
firstly, a user needs to register, real-name authentication information needs to be submitted during registration, and the real-name authentication information can comprise one authentication mode of an identity card, a mobile phone number, a fingerprint, portrait identification and the like, and can also be a combination of multiple modes. The background data processing center stores the registration information of the user, and provides an authentication mode according to the authentication information submitted by the user registration, the user can perform authentication through the first input end or the second input end, wherein to realize the generation and output of the handwritten handwriting, the user needs to enter the handwritten handwriting through the first input end or the second input end, in this implementation, in order to clearly explain the technical principle, the first input end is set as the entry end of the handwritten handwriting, wherein the touch screen of the mobile phone end is directly used as a tool for entering the handwriting, after the user completes the authentication at the mobile phone end, the handwritten handwriting is input through the touch screen, or other tools can be used for entering on the touch screen, such as a handwriting pen special for a capacitive screen, and then the mobile phone end matches a plurality of Chinese characters (namely, fonts mentioned in the foregoing or the following contents) corresponding to the handwritten handwriting according to the handwritten handwriting by the user, sequentially listing the fonts closest to the handwritten handwriting in sequence; at this time, the user needs to select the correct font uniquely corresponding to the handwritten character, and the background data processing center of the system stores the handwritten character corresponding to the Chinese character.
In addition, the background data processing center splits the handwritten handwriting by adopting the multiple splitting modes according to the writing rule and the writing sequence of the handwritten handwriting input by the user, and meanwhile, compares and divides the handwritten handwriting according to the correct font corresponding to the handwritten handwriting, and distinguishes the components, the radicals and the strokes which are matched with the correct font. Then, the background data processing center of the system can carry out deep learning on the splitting information, when the handwritten Chinese characters input by the user are more, the system can split the plurality of the components and the strokes, so that the handwritten handwriting of other Chinese characters containing the components and the strokes can be combined, and the handwritten handwriting accords with the writing habit of the user. For example, when the user enters the handwriting "Ru" and "He", the handwriting can be divided into "you", "woman", "alpha" and "also", so that the system can form the handwriting of Chinese characters of "her" and "pool", etc., and so on.
When the user passes the second input end for identity authentication and passes the identity authentication, the system can read the handwritten handwriting information stored in the background data processing center by the user and the correct font corresponding to the handwritten handwriting information. Therefore, when a Chinese character to be typed is entered or exited through the keyboard, the handwriting of the corresponding Chinese character can be output at this time, and the handwriting and the Chinese character can be switched.
As shown in fig. 3, the detailed implementation of the embodiment is as follows:
s1, after user real-name authentication, handwriting such as ① of a handwritten character is input through a first input end, a corresponding standard candidate character of 'week, week and state … …' is popped up by a background data processing center, and a user selects 'week' as the standard character.
S2, the background data processing center carries out field character lattice processing on the handwritten character handwriting, the handwriting is split through single or mode of radical, continuous stroke, broken stroke and the like, a central axis point of ① -shaped handwriting is taken and contained in the field character lattice, the distance between the whole periphery of the handwriting and the edge of the field character lattice is enabled to be close, ① radical A, broken stroke B, C and broken stroke and continuous stroke D, E are taken, a handwriting track of ① is basically obtained, and then background storage is carried out, and data analysis is carried out.
And S3, outputting a display word ① by the user.
The user skips S1 and S2 and directly displays S3 in the secondary input ①.
S4, the user inputs a second character form ②, the steps S1 and S2 are repeated to obtain a radical continuous stroke and broken stroke F of ②, a continuous stroke and broken stroke G, H are performed, and the step S3 is performed to obtain a display character ②.
S5, inputting a third character-shaped handwriting ③ by the user, and circulating the step S1.S2 to obtain ③ radical-connected stroke-broken J.
The A, B, C, D, E, F, G, H handwriting trace was obtained by these two handwriting inputs. The user carries out handwriting input of different characters for multiple times to obtain a handwriting track of the user, and the background data carries out storage data analysis copying.
For example, after a certain number of writing tracks of the user are obtained, the user writes by hand or inputs Yu through the second input terminal, and the background center directly calls the stored data F, G, E, J to directly output and display ④.
The A, B, C, D, E, F, G, H handwriting trace was obtained by these two handwriting inputs. The user carries out handwriting input of different characters for multiple times to obtain a handwriting track of the user, and the background data processing center carries out storage data analysis copying.
For example, after acquiring a certain number of writing tracks of the user, the user writes by hand or inputs "Yu" through the second input terminal, and the background data processing center directly calls the stored data F, G, E, J to directly output and display ④.
For a user who carries out real-name authentication, when the user carries out normal handwriting or outputs own real-name through the first input end and the second input end, the user carries out normal writing, and when the user carries out signature signing and the like under special conditions, real-name data acquisition authentication needs to be carried out again, and the user who does not carry out real-name authentication writing is represented as normal writing.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (5)
1. A font generation system for deep learning based on handwriting is characterized by comprising a first input end, a second input end and a background data processing center; the first input end comprises a handwriting input interface, a user performs identity verification through the first input end and stores identity verification information in a background data processing center, the user inputs handwriting through the handwriting input interface of the first input end and displays alternative standard words on the interface so that the user can confirm the unique corresponding standard words of the handwriting, the background data processing center separates and stores the handwriting according to the strokes and radicals of the unique corresponding standard words of the handwriting, and the background data processing center performs deep learning through the strokes and radicals of the stored handwriting and combines the strokes and radicals of the stored handwriting into new handwriting containing the stored strokes and radicals of the handwriting notes; when the user passes the identity authentication at the first input end or the second input end, the first input end or the second input end automatically reads the stored information corresponding to the user passing the identity authentication from the background data processing center, and when the user inputs the standard word through the first input end or the second input end, the first input end or the second input end outputs and displays the handwriting corresponding to the standard word.
2. The system of claim 1, wherein the first input terminal comprises a smart device having at least a handwriting function as an input method, and the second input terminal comprises a smart device having at least a keyboard as an input method.
3. The system of claim 2, wherein the first input is a mobile phone or a tablet, and the second input is a computer.
4. The system for generating fonts for deep learning based on handwritten handwriting as claimed in claim 1, wherein when the background data processing center splits the handwritten handwriting, the handwriting is split by using one or more of field character lattice, radical, continuous stroke and broken stroke.
5. The system for generating fonts based on deep learning of handwritten scripts according to claim 1, wherein after deep learning of handwritten scripts of a certain font correspondingly formed by the background data processing center is performed, when a user writes the handwritten scripts of the font through the first input terminal for the first time, the handwritten scripts written by the user through the first input terminal for the first time are used for replacing the handwritten scripts of the font correspondingly formed by deep learning through the background data processing center, and are stored in the background data processing center; and if the user types the font through the first input end or the second input end for the first time in a keyboard mode, outputting the handwriting of the changed font correspondingly formed by deep learning by the background data processing center for displaying.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911157090.4A CN111143541B (en) | 2020-03-07 | 2020-03-07 | Font generation system for deep learning based on handwriting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911157090.4A CN111143541B (en) | 2020-03-07 | 2020-03-07 | Font generation system for deep learning based on handwriting |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111143541A true CN111143541A (en) | 2020-05-12 |
| CN111143541B CN111143541B (en) | 2023-11-03 |
Family
ID=70517217
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911157090.4A Active CN111143541B (en) | 2020-03-07 | 2020-03-07 | Font generation system for deep learning based on handwriting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111143541B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112115680A (en) * | 2020-08-18 | 2020-12-22 | 天津洪恩完美未来教育科技有限公司 | Font splitting method and device, computer equipment and computer readable storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09258885A (en) * | 1996-03-21 | 1997-10-03 | Nec Corp | Handwritten input display device |
| JPH10320107A (en) * | 1997-05-14 | 1998-12-04 | Toshiba Corp | Handwritten character input device having handwritten character recognizing function |
| CN201374068Y (en) * | 2008-11-28 | 2009-12-30 | 上海凌锐信息技术有限公司 | Personal computer with handwriting identification function |
| CN103455741A (en) * | 2013-09-06 | 2013-12-18 | 武汉汉德瑞庭科技有限公司 | Character-based on-line handwriting authentication template extension method |
| CN103678976A (en) * | 2012-09-18 | 2014-03-26 | 阿里巴巴集团控股有限公司 | Method for authenticating identity through handwriting input device and handwriting input device |
| 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 |
| WO2014183677A1 (en) * | 2013-05-17 | 2014-11-20 | Zhu Haiwei | Method for acquiring and displaying original handwriting information of handwriting input device |
| WO2015032304A1 (en) * | 2013-09-04 | 2015-03-12 | 武汉汉德瑞庭科技有限公司 | Online handwriting and identity authentication method having capability for identifying identity of attacker |
| WO2015078383A1 (en) * | 2013-11-27 | 2015-06-04 | 夏普株式会社 | Handwritten character recognition method and system |
| CN109801076A (en) * | 2019-01-02 | 2019-05-24 | 广东金赋科技股份有限公司 | Handwriting authentication method, equipment and storage medium based on self-aided terminal |
-
2020
- 2020-03-07 CN CN201911157090.4A patent/CN111143541B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09258885A (en) * | 1996-03-21 | 1997-10-03 | Nec Corp | Handwritten input display device |
| JPH10320107A (en) * | 1997-05-14 | 1998-12-04 | Toshiba Corp | Handwritten character input device having handwritten character recognizing function |
| CN201374068Y (en) * | 2008-11-28 | 2009-12-30 | 上海凌锐信息技术有限公司 | Personal computer with handwriting identification function |
| CN103678976A (en) * | 2012-09-18 | 2014-03-26 | 阿里巴巴集团控股有限公司 | Method for authenticating identity through handwriting input device and handwriting input device |
| WO2014183677A1 (en) * | 2013-05-17 | 2014-11-20 | Zhu Haiwei | Method for acquiring and displaying original handwriting information of handwriting input device |
| WO2015032304A1 (en) * | 2013-09-04 | 2015-03-12 | 武汉汉德瑞庭科技有限公司 | Online handwriting and identity authentication method having capability for identifying identity of attacker |
| CN103455741A (en) * | 2013-09-06 | 2013-12-18 | 武汉汉德瑞庭科技有限公司 | Character-based on-line handwriting authentication template extension method |
| WO2015078383A1 (en) * | 2013-11-27 | 2015-06-04 | 夏普株式会社 | Handwritten character recognition method and system |
| 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 |
| CN109801076A (en) * | 2019-01-02 | 2019-05-24 | 广东金赋科技股份有限公司 | Handwriting authentication method, equipment and storage medium based on self-aided terminal |
Non-Patent Citations (1)
| Title |
|---|
| 俞庆英,吴建国: "对联机手写汉字识别技术的研究――实现笔画识别" * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112115680A (en) * | 2020-08-18 | 2020-12-22 | 天津洪恩完美未来教育科技有限公司 | Font splitting method and device, computer equipment and computer readable storage medium |
| CN112115680B (en) * | 2020-08-18 | 2023-01-10 | 天津洪恩完美未来教育科技有限公司 | Font splitting method and device, computer equipment and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111143541B (en) | 2023-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102449640B (en) | Recognizing handwritten words | |
| US10846553B2 (en) | Recognizing typewritten and handwritten characters using end-to-end deep learning | |
| CN101246410B (en) | Context or linguistic context input method and system | |
| US6795579B2 (en) | Method and apparatus for recognizing handwritten chinese characters | |
| CN102982021B (en) | For eliminating the method for the ambiguity of the multiple pronunciations in language conversion | |
| TWI464678B (en) | Handwritten input for asian languages | |
| JP2007317022A (en) | Handwritten character processor and method for processing handwritten character | |
| CN101739143B (en) | Character inputting method and character inputting system | |
| CN101520693A (en) | Method and system for rapidly inputting bulk information | |
| US8849034B2 (en) | System, method, and apparatus for triggering recognition of a handwritten shape | |
| CN101369209B (en) | Hand-written input device and method for complete mixing input | |
| US20110298719A1 (en) | Method and apparatus for inputting chinese characters | |
| US20140022180A1 (en) | Method for Inputting and Searching Chinese Characters with Easy-Strokes | |
| CN111143541A (en) | Character generation system for deep learning based on handwriting | |
| US8386236B2 (en) | Method for prompting by suggesting stroke order of chinese character, electronic device, and computer program product | |
| WO2000043861A1 (en) | Method and apparatus for chinese character text input | |
| KR102035087B1 (en) | Keypad system for foreigner korean alphabet learner | |
| JP6325218B2 (en) | Character recognition result verification device and character reading system | |
| JP2012108893A (en) | Hand-written entry method | |
| KR101697237B1 (en) | Apparatus and method for learning the korean pronunciation of the chinese words | |
| CN111857362A (en) | Character input method and character input device | |
| CN113778281B (en) | Auxiliary information generation method and device, electronic equipment and storage medium | |
| US20230418464A1 (en) | Enhanced Shape-Based Keyboard | |
| CN110647785A (en) | Method and device for identifying accuracy of input text and electronic equipment | |
| CN112966689B (en) | Text recognition method, apparatus, electronic device and readable storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |