CN106354277A - Method and system for rapidly inputting phrases and sentences - Google Patents
Method and system for rapidly inputting phrases and sentences Download PDFInfo
- Publication number
- CN106354277A CN106354277A CN201610837379.0A CN201610837379A CN106354277A CN 106354277 A CN106354277 A CN 106354277A CN 201610837379 A CN201610837379 A CN 201610837379A CN 106354277 A CN106354277 A CN 106354277A
- Authority
- CN
- China
- Prior art keywords
- input
- image
- character
- voice
- collection
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
- G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
- G06F3/0233—Character input methods
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a method for rapidly inputting phrases and sentences. The method is characterized by comprising steps as follows: step one: keyboard codes are acquired, associated character sets are found from a database by the aid of an index file; step two: a touch screen induction unit acquires font images, font synthesis and feature extraction are performed, and associated character sets are found through font recognition; step three: a voice acquisition unit acquires a voice signal, preprocessing and feature extraction are performed, and associated character sets are found through voice recognition; step four: the character sets acquired with different input methods are matched in the input sequence for screening, and the optimal combination is found out; multiple input modes including images, scanning, thinking, smells and the like are added. The original single input mode of the phrases and sentences is improved, multiple input methods are adopted and are combined and screened, and the input speed and the accuracy rate of the phrases and sentences are increased.
Description
Technical field
The present invention relates to input method field, the method and system that especially a kind of phrase sentence rapidly inputs.
Background technology
Present input method has inputting method, hand-writing input method and phonitic entry method, and every kind of input method can complete to use
The input at family, but all can only individually be operated before the switching of every kind of input method, only a kind of input method completes an input, so
After be switched to other input method；Especially for the input of phrase and sentence, because the word of unisonance is relatively more, obtain after input
Combination with regard to phrase sentence relatively many it is impossible to quickly filter out desired word or sentence, and switch between input method
Also very inconvenient, thus causing the inefficient problem of present input method；There are currently no and input methods are tied
The input method closed.
Existing input method input acquisition mode is more single, only input through keyboard, handwriting input and phonetic entry, for having
A little images can not directly input, and does not more have the scheme about thinking and abnormal smells from the patient input, and input method is inefficient.
Content of the invention
The goal of the invention of the present invention is: for above-mentioned problem, provides a kind of set input methods, and realizes
Cooperation between input method, by the combination screening to input methods, improves breakneck acceleration it is not necessary to carry out between input method
Switching, the common input of input methods can be carried out simultaneously, and increased input method, including picture input, scanning
Input, abnormal smells from the patient input and thinking input etc., thus reach the method and system that the phrase sentence rapidly inputting rapidly inputs comprehensively.
The technical solution used in the present invention is as follows:
The method that a kind of present invention phrase sentence rapidly inputs, including following step:
Step one: coding collecting unit obtains the coding of input through keyboard, and utilizes index file, finds correlation in data base
The character of connection, the stronger character set of output dependency；
Step 2: touch screen sensing unit obtains the glyph image sensing, and carries out Image semantic classification, then carries out font synthesis and spy
Levy extraction, be identified according to the font master in data base, output character collection；
Step 3: voice collecting unit collection voice signal, carry out pretreatment and feature extraction, further according to the voice in data base
Template, as with reference to being identified, finds corresponding character set；
Step 4: the character set that will obtain in step one, two, three, according to the order of input, using the phase between kinds of characters collection
Mutually mate and screen, find most preferred combination, and export corresponding character string；
Step 5: directly pass through camera head, the picture of collection input, through image procossing, find contrast mould from data base
Plate, image exports；
Step 6: by scanning means, input object is scanned, and combines the template in data base, according to scanogram
Feature be identified, export corresponding character or image；
Step 7: gas collecting device is provided with input method configuration equipment, the gas of collection is detected, and by testing result
It is converted into corresponding character, exported；
Step 8: described input method configuration equipment is carried out data transmission with human body thinking sensor by radio transmitting device, adopts
The nerve information of collection human brain, is converted into character, realizes thinking input, and according to collection information, input value is carried out judge identification.
Above method, using multiple input modes, and by associated all characters that each recognition unit obtains, is carried out
The combination of character, is screened according to input sequence again, thus excluding some character combinations, obtain correct and coherent phrase and
Sentence, accelerates the efficiency of input.
The method that a kind of present invention phrase sentence rapidly inputs, the method for the font synthesis in described step 2: to image
It is scanned, the stepping of scanning is changed into three, find current pixel point, judge whether are the previous point of current point and a rear point
For pixel, three positions of stepping；Find the point that the corresponding coordinate distance of pixel in image is equal to 1, regard a sample set as,
Initial value as first cluster centre；Calculate next pixel to the distance of cluster centre, when distance is less than preset value
When, it is included into the cluster at center；Pixel point analysiss are carried out with this, until pixel point analysiss complete；By cluster synthesis, by clustering it
Between connect track it is possible to obtain synthesize font.
In the method for above font synthesis, the stepping of scanning is changed into three, scanning speed can be accelerated, due to original image
Most of region be blank, only seldom partly have pixel, whole image be scanned spend too much of his time, general
Scan method is improved to interval scan, and processing speed will be improved in three positions of stepping；The clustering processing of font synthesis, due to poly-
The center of class is often the place in efficient point set, and the combination of cluster centre can find the track of font quickly, thus
To fit font.
The method that a kind of present invention phrase sentence rapidly inputs, the method for the pretreatment in described step 3: carry out voice
End-point detection, to noise and quiet be sampled respectively and analyze, obtain noise and the upper limit of quiet energy, by two energy
Limit, as the threshold values of voice signal, has been crossed threshold values and has then been entered voice segments, determined the original position of voice segments；Carry out preemphasis, language
Sound data framing and adding window.
Above speech terminals detection, by arranging the noise energy upper limit and quiet upper energy limit, through the limit of two-door threshold value
System, filters out quiet section in continuous speech signal and noise, retains effective voice segments, and determines the start bit of voice segments
Put；Preemphasis can strengthen voice signal and remove certain noise simultaneously；Voice can be divided into more by speech data framing
Little section is it is ensured that the short-term stationarity of speech model and reach linear；The frequency conversion impact that windowing process can reduce voice strengthens
Average information.
The method that a kind of present invention phrase sentence rapidly inputs, the system rapidly inputting including phrase sentence, described phrase
The system that sentence rapidly inputs includes acquisition module, identification module；Described acquisition module includes encoding collecting unit, touch screen sensing
Unit and voice collecting unit；Described coding collecting unit, for gathering the coding of input through keyboard, as knowledge another characteristic；Institute
State touch screen sensing unit, for obtaining hand-written image；Described voice collecting unit, gathers voice signal, for phonetic feature
Extraction；Described identification module includes code identification unit, touch screen recognition unit, voice recognition unit and comprehensive recognition unit；
Described code identification unit, for encoding as feature, based on index file, finds corresponding character set from data base；
Described touch screen recognition unit, for carrying out Image semantic classification, font synthesis, feature extraction by the image of collection, and according to data
In storehouse, font master is identified, and obtains corresponding character set；Described voice recognition unit, for carrying out pre- place by voice signal
Reason and feature extraction, are identified further according to the sound template in data base, find corresponding character set；Described comprehensive identification is single
Unit, the character for identifying multiple recognition units is combined according to input sequence, finds optimal character combination, output is just
True character string.
The system that a kind of present invention phrase sentence rapidly inputs, also includes image input module, described image input module
Including image unit and scanning element, described image unit, collection image carries out image procossing, and according to template, input picture；
Described scanning element, the image of scanning is converted into character through identification, thus exporting.
Above image unit can solve cannot directly utilize camera head to clap in existing input method in the way of increasing input
Take the photograph the problem that image is inputted, provide input channel for image retrieval afterwards；Scanning element can be by the image being scanned
It is converted into character input, the information on minimizing artificial cognition image, then carries out the process of character input, improve input efficiency.
The system that a kind of present invention phrase sentence rapidly inputs, also includes thinking input system, it is included for gathering god
Thinking sensor through information and the radio transmission apparatus for carrying out data transfer between thinking and equipment, and carry out thinking
Information and the device of character conversion.
Above structure, receives the nerve information in human brain by thinking sensor, and by the thinking of people, that is, idea is converted into number
Word signal, and exported according to corresponding character, reach and directly will form character input when the idea in brain is formed, reach
Fast input speed.
The system that a kind of present invention phrase sentence rapidly inputs, also includes gas detecting input system, and it includes gas inspection
Survey device, for the gas componant of detection input, and testing result is exported in the way of character.
Above structure, by gas-detecting device detected gas, and testing result is converted into character output, can be not
The gas known is converted into input character, thus solving some gases do not know title, but needs the problem of input.
In sum, due to employing technique scheme, the invention has the beneficial effects as follows:
1st, improve the efficiency of input, in invention, different input methods is combined, the character being identified by different input methods
In conjunction with the screening carrying out character combination, can faster, more accurate find optimal character combination, thus the coherent word of output or
Sentence, reaches faster output effect.
2nd, there is more multimode can input and identify, in addition to general keyboard, hand-written and voice, two kinds of ways can be passed through
Footpath obtains image information, inputs character, and a kind of is shooting, and collection image carries out image recognition, finds character；Another kind of is to sweep
Retouch, say that the information of scanning is converted into character output, the input of input method can be convenient to；The thinking input method also setting up, even more
Idea in brain is converted into digital signal, is then converted to character output, reaches the effect expecting just exporting.Different acquisition
The use of mode in different situations, can carry out the input of different modes.
Brief description
Examples of the present invention will be described by way of reference to the accompanying drawings, wherein:
Fig. 1 is the method flow diagram that a kind of present invention phrase sentence rapidly inputs.
Fig. 2 is the system structure diagram that a kind of present invention phrase sentence rapidly inputs.
Specific embodiment
All features disclosed in this specification, or disclosed all methods or during step, except mutually exclusive
Feature and/or step beyond, all can combine by any way.
Any feature disclosed in this specification (including any accessory claim, summary), unless specifically stated otherwise,
Replaced by other alternative features equivalent or that there is similar purpose.I.e., unless specifically stated otherwise, each feature is a series of
One of equivalent or similar characteristics example.
Embodiment one:
The method rapidly inputting as Fig. 1, a kind of present invention phrase sentence, including following step:
Step one: coding collecting unit obtains the coding of input through keyboard, and utilizes index file, finds correlation in data base
The character of connection, the stronger character set of output dependency；
Step 2: touch screen sensing unit obtains the glyph image sensing, and carries out Image semantic classification, then carries out font synthesis and spy
Levy extraction, be identified according to the font master in data base, output character collection；
Step 3: voice collecting unit collection voice signal, carry out pretreatment and feature extraction, further according to the voice in data base
Template, as with reference to being identified, finds corresponding character set；
Step 4: the character set that will obtain in step one, two, three, according to the order of input, using the phase between kinds of characters collection
Mutually mate and screen, find most preferred combination, and export corresponding character string；
Step 5: directly pass through camera head, the picture of collection input, through image procossing, find contrast mould from data base
Plate, image exports；
Step 6: by scanning means, input object is scanned, and combines the template in data base, according to scanogram
Feature be identified, export corresponding character or image；
Step 7: gas collecting device is provided with input method configuration equipment, the gas of collection is detected, and by testing result
It is converted into corresponding character, exported；
Step 8: described input method configuration equipment is carried out data transmission with human body thinking sensor by radio transmitting device, adopts
The nerve information of collection human brain, is converted into character, realizes thinking input, and according to collection information, input value is carried out judge identification.
Enforcement two:
Compared with embodiment one, embodiment two increased the technical characteristic of font synthetic method: the method for described font synthesis: right
Image is scanned, and the stepping of scanning is changed into three, finds current pixel point, judges the previous point of current point and a rear point
Whether it is pixel, three positions of stepping；Find the point that the corresponding coordinate distance of pixel in image is equal to 1, regard a sample as
This collection, as the initial value of first cluster centre；Calculate next pixel to the distance of cluster centre, when distance is less than pre-
If during value, being included into the cluster at center；Pixel point analysiss are carried out with this, until pixel point analysiss complete；By cluster synthesis, by poly-
Connection track between class is it is possible to obtain the font synthesizing.
Enforcement three:
Compared with embodiment one, embodiment three increased the technical characteristic of the method for pretreatment: the method for described pretreatment: carries out
Speech terminals detection, to noise and quiet be sampled respectively and analyze, obtain noise and the upper limit of quiet energy, by two energy
The amount upper limit, as the threshold values of voice signal, has been crossed threshold values and has then been entered voice segments, determined the original position of voice segments；Carry out pre-add
Weight, speech data framing and adding window.
Example IV:
As Fig. 2, disclose the system that phrase sentence rapidly inputs, the system that described phrase sentence rapidly inputs includes gathering mould
Block, identification module；Described acquisition module includes acquisition module, identification module；Described acquisition module includes encoding collecting unit, touches
Screen sensing unit and voice collecting unit；Described coding collecting unit, for gathering the coding of input through keyboard, as the spy of identification
Levy；Described touch screen sensing unit, for obtaining hand-written image；Described voice collecting unit, gathers voice signal, for voice
The extraction of feature；It is single that described identification module includes code identification unit, touch screen recognition unit, voice recognition unit and comprehensive identification
Unit；Described code identification unit, for encoding as feature, based on index file, finds corresponding character from data base
Collection；Described touch screen recognition unit, for carrying out Image semantic classification, font synthesis, feature extraction by the image of collection, and according to number
It is identified according to font master in storehouse, obtain corresponding character set；Described voice recognition unit, pre- for carrying out voice signal
Process and feature extraction, be identified further according to the sound template in data base, find corresponding character set；Described comprehensive identification is single
Unit, the character for identifying multiple recognition units is combined according to input sequence, finds optimal character combination, output is just
True character string.
Embodiment five:
Compared with example IV, increased technical characteristic image input module, described image input module include image unit and
Scanning element, described image unit, collection image carries out image procossing, and according to template, input picture；Described scanning element,
The image of scanning is converted into character through identification, thus exporting.
Embodiment six:
Compared with example IV, increased technical characteristic thinking input system, it includes passing for the thinking gathering nerve information
Sensor and the radio transmission apparatus for carrying out data transfer between thinking and equipment, and carry out course and character conversion
Device.
Embodiment seven:
Compared with example IV, increased technical characteristic gas detecting input system, it includes gas-detecting device, for detecting
The gas componant of input, and testing result is exported in the way of character.
The invention is not limited in aforesaid specific embodiment.The present invention expands to and any discloses in this manual
New feature or any new combination, and the arbitrary new method of disclosure or the step of process or any new combination.
Claims (7)
1. a kind of phrase sentence rapidly inputs method it is characterised in that: include following step:
Step one: coding collecting unit obtains the coding of input through keyboard, and utilizes index file, finds correlation in data base
The character of connection, the stronger character set of output dependency；
Step 2: touch screen sensing unit obtains the glyph image sensing, and carries out Image semantic classification, then carries out font synthesis and spy
Levy extraction, be identified according to the font master in data base, output character collection；
Step 3: voice collecting unit collection voice signal, carry out pretreatment and feature extraction, further according to the voice in data base
Template, as with reference to being identified, finds corresponding character set；
Step 4: the character set that will obtain in step one, two, three, according to the order of input, using the phase between kinds of characters collection
Mutually mate and screen, find most preferred combination, and export corresponding character string；
Step 5: directly pass through camera head, the picture of collection input, through image procossing, find contrast mould from data base
Plate, image exports；
Step 6: by scanning means, input object is scanned, and combines the template in data base, according to scanogram
Feature be identified, export corresponding character or image；
Step 7: gas collecting device is provided with input method configuration equipment, the gas of collection is detected, and by testing result
It is converted into corresponding character, exported；
Step 8: described input method configuration equipment is carried out data transmission with human body thinking sensor by radio transmitting device, adopts
The nerve information of collection human brain, is converted into character, realizes thinking input, and according to collection information, input value is carried out judge identification.
2. phrase sentence as claimed in claim 1 rapidly inputs method it is characterised in that: the font in described step 2 is closed
The method becoming: image is scanned, the stepping of scanning is changed into three, find current pixel point, judge the previous of current point
Whether point and a rear point are pixel, three positions of stepping；Find the corresponding coordinate distance of pixel in image and be equal to 1
Point, regards a sample set as, as the initial value of first cluster centre；Calculate next pixel to cluster centre away from
From when distance is less than preset value, being included into the cluster at center；Pixel point analysiss are carried out with this, until pixel point analysiss complete；Will
Cluster synthesis, by the connection track between cluster it is possible to obtain the font synthesizing.
3. phrase sentence as claimed in claim 1 rapidly inputs method it is characterised in that: the pretreatment in described step 3
Method: carry out speech terminals detection, to noise and quiet be sampled respectively and analyze, obtain the upper of noise and quiet energy
Limit, using two upper energy limit as the threshold values of voice signal, has crossed threshold values and has then entered voice segments, determined the start bit of voice segments
Put；Carry out preemphasis, speech data framing and adding window.
4. phrase sentence as claimed in claim 1 rapidly inputs method it is characterised in that: also include phrase sentence quickly defeated
The system entering, the system that described phrase sentence rapidly inputs includes acquisition module, identification module；Described acquisition module includes encoding
Collecting unit, touch screen sensing unit and voice collecting unit；
Described coding collecting unit, for gathering the coding of input through keyboard, as knowledge another characteristic；
Described touch screen sensing unit, for obtaining hand-written image；
Described voice collecting unit, gathers voice signal, for the extraction of phonetic feature；
Described identification module includes code identification unit, touch screen recognition unit, voice recognition unit and comprehensive recognition unit；
Described code identification unit, for encoding as feature, based on index file, finds corresponding character from data base
Collection；
Described touch screen recognition unit, for the image of collection is carried out Image semantic classification, font synthesis, feature extraction, and according to
In data base, font master is identified, and obtains corresponding character set；
Described voice recognition unit, for voice signal is carried out pretreatment and feature extraction, further according to the voice in data base
Template is identified, and finds corresponding character set；
Described comprehensive recognition unit, the character for identifying multiple recognition units is combined according to input sequence, finds
Good character combination, exports correct character string.
5. as claimed in claim 4 senior input system it is characterised in that: also include image input module, described image is defeated
Enter module and include image unit and scanning element, described image unit, collection image carries out image procossing, and according to template, defeated
Enter image；Described scanning element, the image of scanning is converted into character through identification, thus exporting.
6. phrase sentence as claimed in claim 4 rapidly inputs method it is characterised in that: also include thinking input system,
It is included for gathering nerve information, and carries out the thinking sensor of course and character conversion and be used for carrying out thinking and setting
The radio transmission apparatus of data transfer between standby.
7. phrase sentence as claimed in claim 4 rapidly inputs method it is characterised in that: also include gas detecting input system
System, it includes gas-detecting device, for the gas componant of detection input, and testing result is exported in the way of character.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610837379.0A CN106354277A (en) | 2016-09-21 | 2016-09-21 | Method and system for rapidly inputting phrases and sentences |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610837379.0A CN106354277A (en) | 2016-09-21 | 2016-09-21 | Method and system for rapidly inputting phrases and sentences |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106354277A true CN106354277A (en) | 2017-01-25 |
Family
ID=57858385
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610837379.0A Pending CN106354277A (en) | 2016-09-21 | 2016-09-21 | Method and system for rapidly inputting phrases and sentences |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106354277A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4149716A (en) * | 1977-06-24 | 1979-04-17 | Scudder James D | Bionic apparatus for controlling television games |
| CN1416041A (en) * | 2002-11-07 | 2003-05-07 | 白世宾 | Information process of graphics symbols and input method |
| CN1120442C (en) * | 1997-11-18 | 2003-09-03 | 富士通株式会社 | Document image processing apparatus and method |
| CN1740950A (en) * | 2005-07-21 | 2006-03-01 | 高春平 | Module type non-hand operated control method and apparatus thereof |
| CN101158881A (en) * | 2006-10-08 | 2008-04-09 | 张国成 | Human brain and computer connecting method |
| CN100565395C (en) * | 2007-12-06 | 2009-12-02 | 上海交通大学 | The autonomy field system of reconfigurable digital controller |
| CN101934111A (en) * | 2010-09-10 | 2011-01-05 | 李隆 | Music chromatic light physical factor physical and mental health system based on computer |
| CN101197130B (en) * | 2006-12-07 | 2011-05-18 | 华为技术有限公司 | Sound activity detecting method and detector thereof |
| CN102841681A (en) * | 2006-03-10 | 2012-12-26 | 吉田健治 | Input processing system for information processing device |
| CN101403947B (en) * | 2008-11-19 | 2013-08-21 | 黄庆传 | Computer word input method, its keyboard and mouse |
| CN104156067A (en) * | 2014-07-31 | 2014-11-19 | 上海闻泰电子科技有限公司 | Camera based handwriting inputting method |
| CN104331173A (en) * | 2012-04-16 | 2015-02-04 | 宗刚 | Computer processing method and system for character information |
| CN103093235B (en) * | 2012-12-30 | 2016-01-20 | 北京工业大学 | A kind of Handwritten Numeral Recognition Method based on improving distance core principle component analysis |
-
2016
- 2016-09-21 CN CN201610837379.0A patent/CN106354277A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4149716A (en) * | 1977-06-24 | 1979-04-17 | Scudder James D | Bionic apparatus for controlling television games |
| CN1120442C (en) * | 1997-11-18 | 2003-09-03 | 富士通株式会社 | Document image processing apparatus and method |
| CN1416041A (en) * | 2002-11-07 | 2003-05-07 | 白世宾 | Information process of graphics symbols and input method |
| CN1740950A (en) * | 2005-07-21 | 2006-03-01 | 高春平 | Module type non-hand operated control method and apparatus thereof |
| CN102841681A (en) * | 2006-03-10 | 2012-12-26 | 吉田健治 | Input processing system for information processing device |
| CN101158881A (en) * | 2006-10-08 | 2008-04-09 | 张国成 | Human brain and computer connecting method |
| CN101197130B (en) * | 2006-12-07 | 2011-05-18 | 华为技术有限公司 | Sound activity detecting method and detector thereof |
| CN100565395C (en) * | 2007-12-06 | 2009-12-02 | 上海交通大学 | The autonomy field system of reconfigurable digital controller |
| CN101403947B (en) * | 2008-11-19 | 2013-08-21 | 黄庆传 | Computer word input method, its keyboard and mouse |
| CN101934111A (en) * | 2010-09-10 | 2011-01-05 | 李隆 | Music chromatic light physical factor physical and mental health system based on computer |
| CN104331173A (en) * | 2012-04-16 | 2015-02-04 | 宗刚 | Computer processing method and system for character information |
| CN103093235B (en) * | 2012-12-30 | 2016-01-20 | 北京工业大学 | A kind of Handwritten Numeral Recognition Method based on improving distance core principle component analysis |
| CN104156067A (en) * | 2014-07-31 | 2014-11-19 | 上海闻泰电子科技有限公司 | Camera based handwriting inputting method |
Non-Patent Citations (4)
| Title |
|---|
| 宓超，等编著；: "《装卸机器视觉及其应用2016年1月第1版》", 31 January 2016 * |
| 张少白，等；: "汉语神经分析系统研究现状与展望", 《中国科学：信息科学》 * |
| 张明龙，等著，: "《国外电子信息领域的创新进展 2013年11月第1版》", 30 November 2013 * |
| 朱巧明，等编著；: "《中文信息处理技术教程 2005年9月第1版》", 30 September 2005 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xiong et al. | A pursuit of temporal accuracy in general activity detection | |
| CN107305541B (en) | Method and device for segmenting speech recognition text | |
| CN104361276B (en) | A kind of multi-modal biological characteristic identity identifying method and system | |
| CN106297776B (en) | A kind of voice keyword retrieval method based on audio template | |
| CN111709358A (en) | Teacher-student behavior analysis system based on classroom video | |
| CN106096662B (en) | Human motion state identification based on acceleration transducer | |
| KR101157073B1 (en) | Method for finger language recognition using emg and gyro sensor and apparatus thereof | |
| CN105999670A (en) | Shadow-boxing movement judging and guiding system based on kinect and guiding method adopted by same | |
| CN105976809A (en) | Voice-and-facial-expression-based identification method and system for dual-modal emotion fusion | |
| CN103092329A (en) | Lip reading technology based lip language input method | |
| CN110991238A (en) | Speech auxiliary system based on speech emotion analysis and micro-expression recognition | |
| CN110110580B (en) | Wi-Fi signal-oriented sign language isolated word recognition network construction and classification method | |
| CN106650605A (en) | Morse signal automatic detection decoding method based on machine learning | |
| CN105869658B (en) | A kind of sound end detecting method using nonlinear characteristic | |
| CN105448291A (en) | Parkinsonism detection method and detection system based on voice | |
| CN110031827B (en) | Gesture recognition method based on ultrasonic ranging principle | |
| CN111523317B (en) | Voice quality inspection method and device, electronic equipment and medium | |
| CN109872714A (en) | A kind of method, electronic equipment and storage medium improving accuracy of speech recognition | |
| CN112768070A (en) | Mental health evaluation method and system based on dialogue communication | |
| CN111126280A (en) | Gesture recognition fusion-based aphasia patient auxiliary rehabilitation training system and method | |
| US10971148B2 (en) | Information providing device, information providing method, and recording medium for presenting words extracted from different word groups | |
| CN110163142B (en) | Real-time gesture recognition method and system | |
| CN113300750A (en) | Personnel identity authentication and handwritten letter identification method based on WIFI signal | |
| Li et al. | Interpreting sign components from accelerometer and sEMG data for automatic sign language recognition | |
| CN106354277A (en) | Method and system for rapidly inputting phrases and sentences |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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: 20170125 |
|
| RJ01 | Rejection of invention patent application after publication |