CN103106346A - Character prediction system based on off-line writing picture division and identification - Google Patents
Character prediction system based on off-line writing picture division and identification Download PDFInfo
- Publication number
- CN103106346A CN103106346A CN201310059465XA CN201310059465A CN103106346A CN 103106346 A CN103106346 A CN 103106346A CN 201310059465X A CN201310059465X A CN 201310059465XA CN 201310059465 A CN201310059465 A CN 201310059465A CN 103106346 A CN103106346 A CN 103106346A
- Authority
- CN
- China
- Prior art keywords
- personality
- module
- picture
- identification
- hand
- 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
Images
Abstract
The invention discloses a character prediction system based on off-line writing picture division and identification. A character prediction data collection module collects different off-line writing picture information. An image preprocessing module conducts preprocessing on the off-line writing picture information. An image division and identification module conducts division and identification processing on the preprocessed off-line writing picture information. A picture feature extraction module conducts extraction of different features on a divided small picture and a whole picture. A feature classification module classifies each feature of the picture feature extraction module. A system training module conducts system training according to collected test data. A character database module stores character database which is formed by character data of each training sample. The character prediction module predicts different terms of character, and obtains comprehensive character features of a tester. The character prediction system is executed so that character prediction is more reliable, and improves reliability, accuracy and effectiveness of a system.
Description
Technical field
The present invention relates to technical field of image processing, relate in particular to a kind of personality prognoses system based on the hand-written picture segmentation of off-line and identification.
Background technology
Development along with computer graphics techniques, the processing power of computing machine aspect graph image improves constantly, but the essence of computing machine is all to process binary digit all the time, just need to carry out some changes if need to process more complicated content, such as the processing of some image contents.Now rule is printed the research of word aspect a lot, technology is comparative maturity also, all make great progress for printing word feature extraction and analyzing and processing aspect, but very large shortcoming is being arranged still but aspect hand-written picture, because everyone difference, the form that shows for a specific letter must be different, so just is difficult to catch specific information, for the processing of handwritten word maternal face has brought very large trouble.
people's personality shows each side, naturally also just there is a lot of external expressive form can react the specific features of a personal character aspect, such as walking posture, the word speed speed, right-hand man used etc. has a meal, but in the feature that also can find out by the person's handwriting of observing a people aspect this personal character, such as the words that the people is more export-oriented, it is very rough that the word that he writes out will seem, the word that the introvert writes out is just more well-behaved, observe in addition written handwriting radian size and wait some features that to guess his personality aspect, so can be by the extraction of a personal handwritten word feature being analyzed a people's personality.Extract although can utilize the personality that feature is predicted a people, for some features, if online handwriting picture, also process than being easier to, because can relatively be very easy to find the features such as font crooked radian and writing speed by following the tracks of, but if the hand-written picture of off-line just is difficult to hold these information, this just needs more technology to participate in into, in order to can extract more accurately hand-written alphabetic feature.
Summary of the invention
The object of the invention is to overcome the deficiencies in the prior art, the invention provides a kind of personality prognoses system based on the hand-written picture segmentation of off-line and identification, can carry out effective segmentation and recognition to the hand-written picture of off-line, make the personality prediction more reliable, and improved reliability, accuracy and the validity of system.
In order to address the above problem, the present invention proposes a kind of personality prognoses system based on the hand-written picture segmentation of off-line and identification, described system comprises personality predicted data acquisition module, image pretreatment module, image segmentation and identification module, picture feature extraction module, tagsort module, systematic training module, personality database module and personality prediction module; Wherein, described personality predicted data acquisition module is used for gathering the hand-written pictorial information of different off-lines;
The hand-written pictorial information of off-line that described image pretreatment module is used for described personality predicted data acquisition module is gathered carries out pre-service;
Described image segmentation and identification module are used for that the hand-written pictorial information of pretreated off-line is carried out segmentation and recognition to be processed;
Described picture feature extraction module is used for that described image segmentation and identification module are cut apart the little picture and the picture in its entirety that obtain and carries out the extraction of different characteristic, and the feature information of carrying out of each tester's different aspect is gathered;
Described tagsort module is used for each feature that described picture feature extraction module extracts is classified;
Described systematic training module is used for carrying out systematic training according to the test data of collecting, and forms the personality database;
Described personality database module is used for the personality database that storage is comprised of the personality data of each training sample;
Described personality prediction module is used for analyzing according to the pictorial information of tester's input, and the different aspect of personality is predicted respectively, obtains tester's comprehensive character trait.
Preferably, described personality predicted data acquisition module also is used for collecting the handwritten word supergraph sheet data of different test sample books by for a certain section specific English paragraph, and tests the character trait of the test sample book of each collection by personality Test Network station exercise question.
Preferably, described picture feature extraction module also is used for carrying out feature extraction to cutting apart the picture or the letter that obtain according to predefined feature, the feature of everyone different aspect is extracted gathered, and character trait is represented with characteristic.
Preferably, described tagsort module also is used for each feature that described picture feature extraction module extracts is classified, and the tester is belonged to the classification of character trait according to tester's characteristic.
Preferably, the classification of described character trait comprises interior to classification and export-oriented classification.
Preferably, the personality data of described training sample are various handwriting characteristic datas.
Preferably, the hand-written pictorial information of off-line that described image pretreatment module is used for described personality predicted data acquisition module is gathered carries out denoising, is processed into binary image.
Preferably, described image segmentation and identification module are used for the hand-written pictorial information of pretreated off-line is divided into single word and single letter.
Preferably, the feature of described personality database module stores comprises: entire image level characteristics, word level feature and alphabetical level characteristics.
Preferably, described entire image level characteristics comprises and gesticulates width, word spacing and word size; Described word level feature comprises horizontal projection variance, horizontal projection expectation, vertical projection variance and vertical projection expectation; Described alphabetical level characteristics comprises lower radian size and the alphabetical chain code of the t-bar position of tee, alphabetical average pitch, alphabetical Y.
Implement the embodiment of the present invention, have following beneficial effect:
1, the hand-written picture of off-line has been carried out effective segmentation and recognition, by a kind of effective partitioning algorithm, by progressively increasing the quantity of information of picture, compare with module and draw a coupling mark, when to the entire image end of scan, select the highest pixel of coupling mark to cut, can cut more accurately single letter.
2, extracted more fully feature, personality for a people can not just can reflect by some features, need the fusion of more information, by the extraction to information such as picture in its entirety level characteristics, word level feature, alphabetical level characteristics, reflect more all-sidedly and accurately a personal character, made the personality prediction more reliable.
3, in the training stage foundation that carries weight, training stage tests the website by authoritarian character and in advance each width picture writer's personality is all tested, make the test after system perfecting have more reliability, can be more accurately testee's personality be judged.
4, adopt effective sorting algorithm, by the comparison of multiple sorting algorithm, adopt the high sorting algorithm of this accuracy of Multiboost, the raising for the accuracy that predicts the outcome also provides effective help like this.
5, the modular construction of system makes it that excellent extensibility be arranged.What the present invention provided is the modular design of dividing by function, between each functional module, lotus root is closed low, high cohesion, so the implementor is in the situation that follow the whole system modular design, can be placed on the different soft and hard part according to large young pathbreaker's module of scale and realize, can be according to actual needs, balanced between security, entire system performance and value, construction is fit to the personality prognoses system of specific needs.
Description of drawings
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, the below will do to introduce simply to the accompanying drawing of required use in embodiment or description of the Prior Art, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is that the structure based on the personality prognoses system of the hand-written picture segmentation of off-line and identification of the embodiment of the present invention forms schematic diagram;
Fig. 2 is the formation schematic diagram of feature of the personality database module stores of the embodiment of the present invention;
Fig. 3 is the implementation procedure schematic diagram based on the personality prognoses system of the hand-written picture segmentation of off-line and identification of the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is only the present invention's part embodiment, rather than whole embodiment.Based on the embodiment in the present invention, those of ordinary skills belong to the scope of protection of the invention not making the every other embodiment that obtains under the creative work prerequisite.
Fig. 1 is that the structure based on the personality prognoses system of the hand-written picture segmentation of off-line and identification of the embodiment of the present invention forms schematic diagram, as shown in Figure 1, this system comprises personality predicted data acquisition module 10, image pretreatment module 11, image segmentation and identification module 12, picture feature extraction module 13, tagsort module 14, systematic training module 15, personality database module 16 and personality prediction module 17; Wherein, personality predicted data acquisition module 10 is used for gathering the hand-written pictorial information of different off-lines; The hand-written pictorial information of off-line that image pretreatment module 11 is used for personality predicted data acquisition module 10 is gathered carries out pre-service; Image segmentation and identification module 12 are used for that the hand-written pictorial information of pretreated off-line is carried out segmentation and recognition to be processed; Picture feature extraction module 13 be used for to image segmentation and identification module 12 cut apart the little picture and the picture in its entirety that obtain and carry out the extraction of different characteristic, and the feature information of carrying out of each tester's different aspect is gathered; Tagsort module 14 is used for each feature that picture feature extraction module 13 extracts is classified; Systematic training module 15 is used for carrying out systematic training according to the test data of collecting, and forms the personality database; Personality database module 16 is used for the personality database that storage is comprised of the personality data of each training sample; Personality prediction module 17 is used for analyzing according to the pictorial information of tester's input, and the different aspect of personality is predicted respectively, obtains tester's comprehensive character trait.
In concrete enforcement, personality predicted data acquisition module 10 is mainly used in whole system and carries out personality prediction data acquisition preliminary work before, is mainly to gather a large amount of different hand-written pictorial informations of off-line, for the class test of back is prepared; Main being responsible for of image pretreatment module 11 carried out pre-service to the pictorial information that gathers in personality predicted data acquisition module 10, for later process is prepared; Image segmentation and identification module 12 is responsible for picture to initial acquisition and carried out segmentation and recognition and process, by cut apart and identify after the figure sector-meeting be used in the personal characteristics extraction work of back; Picture feature extraction module 13 carries out different feature extractions mainly for cutting apart the little picture and the whole secondary picture that obtain, and the feature information of carrying out of each tester's different aspect is gathered, and prepares for the database of back forms; Tagsort module 14 is classified to each feature, determines a kind of tendency of personality, and such as being much to introversive and export-oriented tendency degree, the personality classification in the back has just had foundation like this; Systematic training module 15 will be carried out systematic training according to the test data of collecting, and forms database, predicts the accuracy of result afterwards to improve for a certain specific sample; Personality database module 16 is used for the personality data of each training sample of storage, is mainly various handwriting characteristic datas; Personality prediction module 17 is analyzed according to the image data of tester's input, predicts respectively for four different aspects of personality, draws at last this tester's comprehensive character trait.
In addition, personality predicted data acquisition module 10 also is used for passing through for a certain section specific English paragraph, collect the handwritten word supergraph sheet data of different test sample books, and test the character trait of the test sample book of each collection by personality Test Network station exercise question, preserve these data, for the class test of back is prepared.In force, the data that personality predicted data acquisition module 10 gathers are colour pictures, to just can be applied in the module of back through after pre-service, here the hand-written pictorial information of off-line that is used for personality predicted data acquisition module 10 is gathered by image pretreatment module 11 carries out denoising, is processed into binary image.
Image segmentation and identification module 12 will carry out the feature that the personality test needs to extract hand-written picture, need to use the segmentation and recognition technology of image, this module mainly is responsible for the initial picture of collecting is carried out preliminary segmentation and recognition, for the feature extraction work of back is prepared; Here the hand-written pictorial information of pretreated off-line is divided into single word and single letter, for the feature extraction work of back provides data.
Picture feature extraction module 13 also is used for carrying out feature extraction to cutting apart the picture or the letter that obtain according to predefined feature, the feature of everyone different aspect is extracted gathered, and character trait is represented with characteristic; Here can extract pre-set feature, as write font and gesticulate width, some can reflect the feature of personality characteristics word spacing etc., select effective feature to make good contribution to the accuracy of the result of system testing.
If successful prediction character trait just relates to classification problem, because only belong to a specific class or belong to the tendency degree according to an eigenwert and could reflect some personality characteristics, to set up strong background data base on the other hand, make later test more effective, utilize tagsort module 14 and systematic training module 15 to test all test pictures, form backstage personality database.As shown in Figure 2, the feature of personality database module stores comprises: entire image level characteristics, word level feature and alphabetical level characteristics.Wherein, the entire image level characteristics comprises and gesticulates width, word spacing and word size; The word level feature comprises horizontal projection variance, horizontal projection expectation, vertical projection variance and vertical projection expectation; The letter level characteristics comprises lower radian size and the alphabetical chain code of the t-bar position of tee, alphabetical average pitch, alphabetical Y.
No matter be the entire image feature, or word feature or alphabetic feature are all playing a significant role aspect reflection personality characteristics, there is very large application the accuracy aspect of personality test in the back.
Below in conjunction with Fig. 3, the implementation procedure based on the personality prognoses system of the hand-written picture segmentation of off-line and identification of the embodiment of the present invention is described, as shown in Figure 3, this implementation procedure comprises:
Step 1: start the personality prognoses system based on the hand-written picture segmentation of off-line and identification;
Step 2: carry out image information collecting, typing tester's hand-written picture;
Step 3: carry out the pre-service of view data, use some algorithms that image transitions is become data message more easy to identify, the extraction of effective image information after being convenient to;
Step 4: to pretreated Image Segmentation Using identification, use some partitioning algorithms that picture segmentation is become independent word or letter, for the feature extraction of back is prepared;
Step 5: carry out Characteristic of Image and extract, write specific program for each feature here, extract according to the feature of different stage, some can reflect the data of character trait many as far as possible extractions here, make the test of back more prepare reliably;
Step 6: judge whether it is new tester, because do not need to carry out the personality prediction when carrying out the database test, just prove test data if not new tester, so just can directly forward classification processing and the systematic training of back to, form backstage personality database, if new tester carries out tagsort and the personality test of back;
Step 7: during whether selection joins background data base with the personality data as the case may be after new test data occurs, can consider test result is joined in database for test result more accurately, can improve better database like this.
Implement the embodiment of the present invention, have following beneficial effect:
1, the hand-written picture of off-line has been carried out effective segmentation and recognition, by a kind of effective partitioning algorithm, by progressively increasing the quantity of information of picture, compare with module and draw a coupling mark, when to the entire image end of scan, select the highest pixel of coupling mark to cut, can cut more accurately single letter.
2, extracted more fully feature, personality for a people can not just can reflect by some features, need the fusion of more information, by the extraction to information such as picture in its entirety level characteristics, word level feature, alphabetical level characteristics, reflect more all-sidedly and accurately a personal character, made the personality prediction more reliable.
3, in the training stage foundation that carries weight, training stage tests the website by authoritarian character and in advance each width picture writer's personality is all tested, make the test after system perfecting have more reliability, can be more accurately testee's personality be judged.
4, adopt effective sorting algorithm, by the comparison of multiple sorting algorithm, adopt the high sorting algorithm of this accuracy of Multiboost, the raising for the accuracy that predicts the outcome also provides effective help like this.
5, the modular construction of system makes it that excellent extensibility be arranged.What the present invention provided is the modular design of dividing by function, between each functional module, lotus root is closed low, high cohesion, so the implementor is in the situation that follow the whole system modular design, can be placed on the different soft and hard part according to large young pathbreaker's module of scale and realize, can be according to actual needs, balanced between security, entire system performance and value, construction is fit to the personality prognoses system of specific needs.
One of ordinary skill in the art will appreciate that all or part of step in the whole bag of tricks of above-described embodiment is to come the relevant hardware of instruction complete by program, this program can be stored in a computer-readable recording medium, storage medium can comprise: ROM (read-only memory) (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), disk or CD etc.
In addition, the above personality prognoses system based on the hand-written picture segmentation of off-line and identification that the embodiment of the present invention is provided is described in detail, used specific case herein principle of the present invention and embodiment are set forth, the explanation of above embodiment just is used for helping to understand method of the present invention and core concept thereof; Simultaneously, for one of ordinary skill in the art, according to thought of the present invention, all will change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.
Claims (10)
1. personality prognoses system based on the hand-written picture segmentation of off-line and identification, it is characterized in that, described system comprises personality predicted data acquisition module, image pretreatment module, image segmentation and identification module, picture feature extraction module, tagsort module, systematic training module, personality database module and personality prediction module; Wherein,
Described personality predicted data acquisition module is used for gathering the hand-written pictorial information of different off-lines;
The hand-written pictorial information of off-line that described image pretreatment module is used for described personality predicted data acquisition module is gathered carries out pre-service;
Described image segmentation and identification module are used for that the hand-written pictorial information of pretreated off-line is carried out segmentation and recognition to be processed;
Described picture feature extraction module is used for that described image segmentation and identification module are cut apart the little picture and the picture in its entirety that obtain and carries out the extraction of different characteristic, and the feature information of carrying out of each tester's different aspect is gathered;
Described tagsort module is used for each feature that described picture feature extraction module extracts is classified;
Described systematic training module is used for carrying out systematic training according to the test data of collecting, and forms the personality database;
Described personality database module is used for the personality database that storage is comprised of the personality data of each training sample;
Described personality prediction module is used for analyzing according to the pictorial information of tester's input, and the different aspect of personality is predicted respectively, obtains tester's comprehensive character trait.
2. the personality prognoses system based on the hand-written picture segmentation of off-line and identification as claimed in claim 1, it is characterized in that, described personality predicted data acquisition module also is used for passing through for a certain section specific English paragraph, collect the handwritten word supergraph sheet data of different test sample books, and test the character trait of the test sample book of each collection by personality Test Network station exercise question.
3. the personality prognoses system based on the hand-written picture segmentation of off-line and identification as claimed in claim 1, it is characterized in that, described picture feature extraction module also is used for carrying out feature extraction to cutting apart the picture or the letter that obtain according to predefined feature, the feature of everyone different aspect is extracted gathered, and character trait is represented with characteristic.
4. the personality prognoses system based on the hand-written picture segmentation of off-line and identification as claimed in claim 1, it is characterized in that, described tagsort module also is used for each feature that described picture feature extraction module extracts is classified, and the tester is belonged to the classification of character trait according to tester's characteristic.
5. the personality prognoses system based on the hand-written picture segmentation of off-line and identification as claimed in claim 4, is characterized in that, the classification of described character trait comprises interior to classification and export-oriented classification.
6. the personality prognoses system based on the hand-written picture segmentation of off-line and identification as claimed in claim 1, is characterized in that, the personality data of described training sample are various handwriting characteristic datas.
7. the personality prognoses system based on the hand-written picture segmentation of off-line and identification as claimed in claim 1, it is characterized in that, the hand-written pictorial information of off-line that described image pretreatment module is used for described personality predicted data acquisition module is gathered carries out denoising, is processed into binary image.
8. the personality prognoses system based on the hand-written picture segmentation of off-line and identification as claimed in claim 1, is characterized in that, described image segmentation and identification module are used for the hand-written pictorial information of pretreated off-line is divided into single word and single letter.
9. the personality prognoses system based on the hand-written picture segmentation of off-line and identification as claimed in claim 1, is characterized in that, the feature of described personality database module stores comprises: entire image level characteristics, word level feature and alphabetical level characteristics.
10. the personality prognoses system based on the hand-written picture segmentation of off-line and identification as claimed in claim 9, is characterized in that, described entire image level characteristics comprises gesticulates width, word spacing and word size; Described word level feature comprises horizontal projection variance, horizontal projection expectation, vertical projection variance and vertical projection expectation; Described alphabetical level characteristics comprises lower radian size and the alphabetical chain code of the t-bar position of tee, alphabetical average pitch, alphabetical Y.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310059465XA CN103106346A (en) | 2013-02-25 | 2013-02-25 | Character prediction system based on off-line writing picture division and identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310059465XA CN103106346A (en) | 2013-02-25 | 2013-02-25 | Character prediction system based on off-line writing picture division and identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103106346A true CN103106346A (en) | 2013-05-15 |
Family
ID=48314200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310059465XA Pending CN103106346A (en) | 2013-02-25 | 2013-02-25 | Character prediction system based on off-line writing picture division and identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103106346A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103279770A (en) * | 2013-06-06 | 2013-09-04 | 哈尔滨工业大学 | Handwriting recognition method based on fragment and contour feature of stroke |
| CN103440864A (en) * | 2013-07-31 | 2013-12-11 | 湖南大学 | Personality characteristic forecasting method based on voices |
| CN104699665A (en) * | 2013-12-07 | 2015-06-10 | 姚振龙 | Text information analysis method |
| CN105893784A (en) * | 2016-06-28 | 2016-08-24 | 中国科学院自动化研究所 | Method for generating character test questionnaire based on image and surveying interactive method |
| CN106503629A (en) * | 2016-10-10 | 2017-03-15 | 语联网（武汉）信息技术有限公司 | A kind of dictionary picture dividing method and device |
| CN107292221A (en) * | 2016-04-01 | 2017-10-24 | 北京搜狗科技发展有限公司 | A kind of trajectory processing method and apparatus, a kind of device for trajectory processing |
| CN109086837A (en) * | 2018-10-24 | 2018-12-25 | 高嵩 | User property classification method, storage medium, device and electronic equipment based on convolutional neural networks |
| CN109284693A (en) * | 2018-08-31 | 2019-01-29 | 深圳壹账通智能科技有限公司 | Based on the banking operation prediction technique of writing key point, device, electronic equipment |
| CN113592044A (en) * | 2021-07-09 | 2021-11-02 | 广州逅艺文化科技有限公司 | Handwriting feature analysis method and device |
| CN113592044B (en) * | 2021-07-09 | 2024-05-10 | 广州逅艺文化科技有限公司 | Handwriting feature analysis method and device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101183430A (en) * | 2007-12-13 | 2008-05-21 | 中国科学院合肥物质科学研究院 | Handwriting digital automatic identification method based on module neural network SN9701 rectangular array |
-
2013
- 2013-02-25 CN CN201310059465XA patent/CN103106346A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101183430A (en) * | 2007-12-13 | 2008-05-21 | 中国科学院合肥物质科学研究院 | Handwriting digital automatic identification method based on module neural network SN9701 rectangular array |
Non-Patent Citations (5)
| Title |
|---|
| 505334588: "笔迹字体性格分析", 《百度文库》 * |
| J.PRADEEP ET AL.: "Diagonal feature extracting based handwritten character system using neural network", 《INTERNATIONAL JOURNAL OF COMPUTER APPLICATIONS》 * |
| YONG HAUR TAY ET AL.: "An offline cursive handwritten word recognition system", 《PROCEEDINGS OF IEEE REGION 10 INTERNATIONAL CONFERENCE ON ELECTRICAL AND ELECTRONIC TECHNOLOGY》 * |
| 任剑，冯晓华: "笔迹学，透露你的性格秘密", 《时代风采》 * |
| 彭湛峰: "笔迹，未来求职者的敲门砖", 《人才开发》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103279770A (en) * | 2013-06-06 | 2013-09-04 | 哈尔滨工业大学 | Handwriting recognition method based on fragment and contour feature of stroke |
| CN103279770B (en) * | 2013-06-06 | 2016-03-23 | 哈尔滨工业大学 | Based on the person's handwriting recognition methods of stroke fragment and contour feature |
| CN103440864A (en) * | 2013-07-31 | 2013-12-11 | 湖南大学 | Personality characteristic forecasting method based on voices |
| CN104699665A (en) * | 2013-12-07 | 2015-06-10 | 姚振龙 | Text information analysis method |
| CN107292221A (en) * | 2016-04-01 | 2017-10-24 | 北京搜狗科技发展有限公司 | A kind of trajectory processing method and apparatus, a kind of device for trajectory processing |
| CN105893784A (en) * | 2016-06-28 | 2016-08-24 | 中国科学院自动化研究所 | Method for generating character test questionnaire based on image and surveying interactive method |
| CN106503629A (en) * | 2016-10-10 | 2017-03-15 | 语联网（武汉）信息技术有限公司 | A kind of dictionary picture dividing method and device |
| CN109284693A (en) * | 2018-08-31 | 2019-01-29 | 深圳壹账通智能科技有限公司 | Based on the banking operation prediction technique of writing key point, device, electronic equipment |
| CN109086837A (en) * | 2018-10-24 | 2018-12-25 | 高嵩 | User property classification method, storage medium, device and electronic equipment based on convolutional neural networks |
| CN113592044A (en) * | 2021-07-09 | 2021-11-02 | 广州逅艺文化科技有限公司 | Handwriting feature analysis method and device |
| CN113592044B (en) * | 2021-07-09 | 2024-05-10 | 广州逅艺文化科技有限公司 | Handwriting feature analysis method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103106346A (en) | Character prediction system based on off-line writing picture division and identification | |
| CN109308476B (en) | Billing information processing method, system and computer readable storage medium | |
| Veit et al. | Coco-text: Dataset and benchmark for text detection and recognition in natural images | |
| CN109101469B (en) | Extracting searchable information from digitized documents | |
| Lawgali et al. | HACDB: Handwritten Arabic characters database for automatic character recognition | |
| CN107798321A (en) | A kind of examination paper analysis method and computing device | |
| CN106156766A (en) | The generation method and device of line of text grader | |
| CN101326518B (en) | Method and device for script recognition for ink notes | |
| CN103870823B (en) | Character recognition device and method | |
| CN109919060A (en) | A kind of identity card content identifying system and method based on characteristic matching | |
| AlKhateeb | A database for Arabic handwritten character recognition | |
| Kumar et al. | A systematic survey on CAPTCHA recognition: types, creation and breaking techniques | |
| Boubaker et al. | Online Arabic databases and applications | |
| CN110263539A (en) | A kind of Android malicious application detection method and system based on concurrent integration study | |
| CN111507330A (en) | Exercise recognition method and device, electronic equipment and storage medium | |
| CN105989341A (en) | Character recognition method and device | |
| CN106650696A (en) | Handwritten electrical element identification method based on singular value decomposition | |
| CN101655911A (en) | Mode identification method based on immune antibody network | |
| CN114021984A (en) | Invigilation data processing method | |
| CN110490237A (en) | Data processing method, device, storage medium and electronic equipment | |
| CN109388804A (en) | Report core views extracting method and device are ground using the security of deep learning model | |
| CN107992508A (en) | A kind of Chinese email signature extracting method and system based on machine learning | |
| Yu et al. | Mental workload classification via online writing features | |
| Zhang et al. | Computational method for calligraphic style representation and classification | |
| Lin et al. | Multilingual corpus construction based on printed and handwritten character separation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C53 | Correction of patent of invention or patent application | ||
| CB03 | Change of inventor or designer information |
Inventor after: Xu Songhua Inventor after: Lin Shujin Inventor after: Wang Yusong Inventor after: Lin Ge Inventor before: Luo Xiaonan Inventor before: Wang Yusong Inventor before: Lin Ge |
|
| COR | Change of bibliographic data |
Free format text: CORRECT: INVENTOR; FROM: LUO XIAONAN WANG YUSONG LIN GE TO: XU SONGHUA LIN SHUJIN WANG YUSONG LIN GE |
|
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130515 |