CN110443113A - A kind of virtual reality Writing method, system and storage medium - Google Patents
A kind of virtual reality Writing method, system and storage medium Download PDFInfo
- Publication number
- CN110443113A CN110443113A CN201910524902.8A CN201910524902A CN110443113A CN 110443113 A CN110443113 A CN 110443113A CN 201910524902 A CN201910524902 A CN 201910524902A CN 110443113 A CN110443113 A CN 110443113A
- Authority
- CN
- China
- Prior art keywords
- user
- text
- signal
- pressure signal
- writing
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/32—Digital ink
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/30—Writer recognition; Reading and verifying signatures
- G06V40/37—Writer recognition; Reading and verifying signatures based only on signature signals such as velocity or pressure, e.g. dynamic signature recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a kind of virtual reality Writing method, system and storage mediums to improve the flexibility of Text region to enrich the application scenarios of Text region.The virtual reality Writing method, comprising: during first user's writing words, acquire the first electromyography signal and the first finger movement signals respectively；According to first electromyography signal and the first finger motion information, the text and/or pressure signal that the user writes are determined using Text region model, wherein, the Text region model is to be trained based on the relationship sample database pre-established using convolutional neural networks, and the corresponding relationship between the second electromyography signal and second finger motor message and text sample and/or pressure signal is included at least in the relationship sample database.
Description
Technical field
The present invention relates to human-computer interaction technique fields more particularly to a kind of virtual reality Writing method, system and storage to be situated between
Matter.
Background technique
With the continuous propulsion of artificial intelligence, character recognition technology is also contained therewith.Current character identification technology is mostly
Using the technology of image recognition, especially as convolutional neural networks (Convolutional Neural Networks, CNN)
Occur, substantially increasing leads to the identification for distorting the two dimensional image of invariance because the other forms such as being displaced, scaling, and image is known
Other accuracy is also higher and higher.
But this kind of deep learning algorithm is not suitable for all scenes, because this kind of algorithm needs when doing image recognition
Specific picture just can be carried out, and the recognition methods is just no longer suitable when being in certain scenes that can not provide specific picture or text
With to reduce the flexibility of Text region.
Summary of the invention
The embodiment of the present invention provides a kind of virtual reality Writing method, system and storage medium, to enrich Text region
Application scenarios, improve the flexibility of Text region.
In a first aspect, providing a kind of virtual reality Writing method, comprising:
During first user's writing words, the first electromyography signal and the first finger movement signals are acquired respectively；
According to first electromyography signal and the first finger motion information, user's book is determined using Text region model
The text and/or pressure signal write, wherein the Text region model is to utilize convolution based on the relationship sample database pre-established
What neural network was trained, the second electromyography signal and second finger motor message are included at least in the relationship sample database
With the corresponding relationship between text sample and/or pressure signal.
In a kind of possible embodiment, the relationship sample database is to obtain according to following below scheme:
During second user writing words, the second electromyography signal and the second motor message are acquired respectively；And
Record pressure signal, time series and the text of writing when the second user writing words；
Second electromyography signal and the second motor message are filtered respectively, noise reduction process；
Treated the second electromyography signal and the second motor message are split according to the time series of record；
Each text that the second electromyography signal and the second motor message and the second user after establishing segmentation are write and/or
Corresponding relationship between the corresponding pressure signal of the text obtains the relationship sample database.
In a kind of possible embodiment, based on the relationship sample database pre-established using convolutional neural networks according to
Lower process is trained to obtain the Text region model:
Initialize Text region model parameter；
From the second electromyography signal and the second movement after selection segmentation in the corresponding relationship for including in the relationship sample database
Signal inputs in the Text region model；
Compare the second electromyography signal selected in the text information and/or pressure signal and the relationship sample database of output
Text corresponding with the second motor message and/or pressure signal；
If comparison result is not more than preset threshold, terminate to train, otherwise, updates Text region model parameter and continue to instruct
Practice, until comparison result is not more than the preset threshold.
In a kind of possible embodiment, the virtual reality Writing method, further includes:
The pressure signal, which is exported, to first user forms touch feedback；And/or
The text determined to first user output forms visual feedback.
In a kind of possible embodiment, the first user of Xiang Suoshu exports the pressure signal and forms touch feedback, tool
Body includes:
Electrotactile stimulation electrode slice by being placed in first user's finger exports the pressure to first user
Signal forms touch feedback；And/or
The virtual reality device worn by first user is formed to the text that first user output is determined
Visual feedback.
In a kind of possible embodiment, the first electromyography signal is acquired, is specifically included:
Difference electromyographic electrode by being placed in the first user writing words arm acquires the first electromyography signal.
In a kind of possible embodiments, the first finger movement signals are acquired, are specifically included:
The multi-axial sensor at the second articulations digitorum manus by being placed in the first user writing words finger acquires first-hand
Refer to motor message.
In a kind of possible embodiment, in the text and/or pressure for determining user's writing using Text region model
Before force signal, further includes:
Detect the first handwriting trace of first user；And
The first handwriting trace confirmly detected is matched with the first desired guiding trajectory.
In a kind of possible embodiment, virtual reality Writing method provided in an embodiment of the present invention, further includes:
During the first user writing words, the second handwriting trace of first user is detected；
If it is determined that second handwriting trace is matched with the second desired guiding trajectory, then enter dormant state；
If second handwriting trace is matched with third desired guiding trajectory, current operation program is exited.
Second aspect provides a kind of virtual reality writing system, including central processing control module, electromyogram EMG module,
Micro-electromechanical system (MEMS) module, in which:
The EMG module, for acquiring the first electromyography signal, and be transferred to during first user's writing words
The central processing control module；
The MEMS module, for acquiring the first finger movement signals, and pass during first user's writing words
It is defeated by the central processing control module；
The central processing control module, for utilizing according to first electromyography signal and the first finger motion information
Text region model determines the text and/or pressure signal that the user writes, wherein the Text region model is based on pre-
What the relationship sample database first established was trained using convolutional neural networks, second is included at least in the relationship sample database
Corresponding relationship between electromyography signal and second finger motor message and text sample and/or pressure signal.
In a kind of possible embodiment, virtual reality writing system further includes logging modle, in which:
The EMG module is also used to during second user writing words, acquires the second electromyography signal, and transmit
To the central processing control module；
The MEMS module is also used to during second user writing words, acquires second finger motor message, and
It is transferred to the central processing control module；
The logging modle, for recording pressure signal, time series and book when the second user writing words
The text write；
The central processing control module is also used to respectively filter second electromyography signal and the second motor message
Wave, noise reduction process；Treated the second electromyography signal and the second motor message are split according to the time series of record；It builds
The second electromyography signal and the second motor message after vertical segmentation is corresponding with each text and/or the text that the second user is write
Pressure signal between corresponding relationship obtain the relationship sample database.
In a kind of possible embodiment, the central processing control module is specifically used for initialization Text region mould
Shape parameter；From the second electromyography signal and the second movement letter after selection segmentation in the corresponding relationship for including in the relationship sample database
In number input Text region model；Compare and is selected in the text information and/or pressure signal and the relationship sample database of output
The second electromyography signal and the corresponding text of the second motor message and/or pressure signal selected out；If comparison result is no more than pre-
If threshold value, then terminate to train, otherwise, updates Text region model parameter and continue to train, until comparison result is no more than described pre-
If threshold value.
In a kind of possible embodiment, virtual reality writing system provided in an embodiment of the present invention, further includes tactile
Feedback module and/or visual feedback module, in which:
The central processing control module is also used to export the pressure signal formation tactile to the haptic feedback module
Feedback and/or the text formation visual feedback determined to visual feedback module output.
In a kind of possible embodiment, the haptic feedback module includes electrotactile stimulation electrode slice, the vision
Feedback module includes virtual reality device, in which:
The central processing control module, specifically for the electrotactile stimulation electrode by being placed in first user's finger
Piece exports the pressure signal to first user and forms touch feedback；And/or it is worn by first user virtual
Real world devices form visual feedback to the text that first user output is determined.
In a kind of possible embodiment, the EMG module includes difference electromyographic electrode；And
The EMG module is adopted specifically for the difference electromyographic electrode by being placed in the first user writing words arm
Collect the first electromyography signal.
In a kind of possible embodiment, the EMES module includes multi-axial sensor；And
The EMES, specifically for the multiaxis at the second articulations digitorum manus by being placed in the first user writing words finger
Sensor acquires the first finger movement signals.
In a kind of possible embodiment, the central processing control module is also used to utilizing Text region model
Before determining the text and/or pressure signal that the user writes, the first handwriting trace of first user is detected；And really
The first handwriting trace that regular inspection measures is matched with the first desired guiding trajectory.
In a kind of possible embodiment, the central processing control module is also used to write in first user
During text, the second handwriting trace of first user is detected；If it is determined that second handwriting trace and second is in advance
If path matching, then controls current operation program and enter dormant state；If second handwriting trace and third desired guiding trajectory
Matching, then exit current operation program.
The third aspect provides a kind of computing device, including at least one processor and at least one processor, wherein
The memory is stored with computer program, when described program is executed by the processor, so that the processor executes
State either step described in virtual reality Writing method.
Fourth aspect provides a kind of computer-readable medium, is stored with the computer program that can be executed by computing device,
When described program is run on the computing device, appoint described in above-mentioned virtual reality Writing method so that the computing device executes
One step.
Virtual reality Writing method, system and storage medium provided in an embodiment of the present invention, by establish electromyography signal and
Corresponding relationship between pressure signal when finger movement signals and user's writing words and the text write obtains relationship
Sample database is trained to obtain Text region model using convolutional neural networks to the corresponding relationship for including in relationship sample database,
In this way, in user's writing process, it can be true using Text region model according to the electromyography signal and finger movement signals of acquisition
Determine the pressure generated when the text and writing words of user's writing, the above-mentioned method to Text region is situated between without relying on picture etc.
Matter improves the flexibility of Text region to enrich the application scenarios of Text region.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention can be by written explanation
Specifically noted structure is achieved and obtained in book, claims and attached drawing.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes a part of the invention, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 a is the structural schematic diagram according to the virtual reality writing system of embodiment of the present invention；
Fig. 1 b is a kind of possible hardware structural diagram according to the virtual reality writing system of embodiment of the present invention；
Fig. 2 is the first Text region model training flow diagram according to embodiment of the present invention；
Fig. 3 is according to the relation schematic diagram between the off-line training mode and online recognition mode of embodiment of the present invention；
Fig. 4 is the Establishing process schematic diagram according to the relationship sample database of embodiment of the present invention；
Fig. 5 is second of Text region model training flow diagram according to embodiment of the present invention；
Fig. 6 is the implementation process diagram according to the first virtual reality Writing method of embodiment of the present invention；
Fig. 7 is the implementation process diagram according to second of virtual reality Writing method of embodiment of the present invention；
Fig. 8 is the structural schematic diagram according to the computing device of embodiment of the present invention.
Specific embodiment
In order to enrich the application scenarios of character recognition method, the flexibility of Text region is improved, the embodiment of the present invention provides
A kind of virtual reality Writing method, system and storage medium.
Computing device in the present invention can be PC (full name in English: Personal Computer, PC), plate
Computer, personal digital assistant (Personal Digita l Assistant, PDA), personal communication service (full name in English:
Personal Communication Service, PCS) computing devices such as phone, notebook and mobile phone, it is also possible to have and moves
The computer of dynamic terminal, for example, it may be portable, pocket, hand-held, built-in computer or vehicle-mounted mobile dress
Set, the equipment that they can provide a user voice and/or data connectivity, and exchange with wireless access network language and/or
Data.
In addition, the specification and claims in the embodiment of the present invention and the term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so that the embodiments described herein can be in addition to illustrating herein or describing
Sequence other than appearance is implemented.
Referenced herein " multiple or several " refer to two or more."and/or" describes affiliated partner
Incidence relation, indicate may exist three kinds of relationships, for example, A and/or B, can indicate: individualism A exists simultaneously A and B,
These three situations of individualism B.Character "/" typicallys represent the relationship that forward-backward correlation object is a kind of "or".
Below in conjunction with Figure of description, preferred embodiment of the present invention will be described, it should be understood that described herein
Preferred embodiment only for the purpose of illustrating and explaining the present invention and is not intended to limit the present invention, and in the absence of conflict, this hair
The feature in embodiment and embodiment in bright can be combined with each other.
In the embodiment of the present invention, has the characteristics that correlation using text and myoelectricity characteristic, acceleration characteristic, by flesh
Electric signal and acceleration signal carry out feature extraction, determine that it establishes Text region model with contacting for specific text.Using this
The mode of sample can carry out text according to arm electromyography signal (EMG, electromyography, electromyogram) and MEMS signal
The prediction of word.
The generation process of electromyography signal is as follows: brain motor cortex generates action potential, via spinal cord and peripheral nervous system
System reaches meat fiber, finally acts on by the low-pass filtering of skin, electric potential field is formed in skin surface, because electromyography signal is super
It is preceding in muscular force, so muscle generate reaction when can be collected into.With the development of semiconductor technology, MEMS acceleration is passed
Sensor and the good characteristics such as myoelectric sensor high reliablity, high sensitivity, high reliablity, small in size, light-weight, low in energy consumption, In
Field of human-computer interaction has obtained so more and more that apply.
When user is in writing words, arm, the dynamics of finger, motion mode etc. determine written text and this text
The specific scheme structure of word；And dynamics, motion mode of arm, finger etc. can be passed by myoelectric sensor, MEMS acceleration
Sensor collects.It so just can be by the relationship between electromyography signal, MEMS acceleration signal and the text set up, by myoelectricity
Signal and acceleration signal just can obtain relevant information when write text and its specific writing.
Virtual reality (Virtual Reality, VR) technology is that a kind of artificial virtual environment is generated using computer,
Its real-time three-dimensional space expressive ability provides a kind of operating environment of man-machine interactive, is based on this, the present invention can be in void
It is applied under conditions of quasi- reality, to provide visual feedback when writing words for user.Electro photoluminescence touch feedback is when writing
Finger provides necessary feedback and is compensated for by the combination of vibratory sensation, feeling of stress, harsh feeling, tingling sensation etc. in virtual reality
The tactile that loses of people, touch feedback when writing words is provided for user.
Virtual reality Writing method provided in an embodiment of the present invention can be applied in virtual reality writing system, such as Fig. 1 a
It is shown, it is the structural schematic diagram of virtual reality writing system, including central processing control module 11, EMG (electromyogram) module
12 and MEMS (MEMS) module 13.When it is implemented, character identification system provided in an embodiment of the present invention, can also wrap
Include haptic feedback module 14 and visual feedback module 15.
In a kind of possible embodiment, character identification system provided in an embodiment of the present invention can also include record mould
Block 16, the pressure generated when for during Text region model training, recording text and writing words that user writes
Signal, and the text of record and its corresponding pressure signal are transferred to central processing control module, central processing control module
The finger movement signals and record mould of the electromyography signal, the acquisition of EMES module that are acquired according to EMG module when user's writing words
The corresponding relationship between text that the pressure signal of block record and user write obtains relationship sample database, using in relationship sample database
The sample data of record is trained Text region model.
In a kind of possible embodiment, central processing control module can be centralized storage processing controller, MEMS
Module can be MEMS acceleration transducer, and EMG module can be electromyographic electrode piece, and haptic feedback module can be pierced for electric touch
Swash electrode slice, generates haptic effect using electrical stimulation method, increase and immerse sense；Visual feedback module can set for virtual reality
It is standby, for example, virtual reality glasses, the signal that virtual implementing helmet etc., enough reception centralized storage processing controller transmit, and energy
Generate corresponding picture signal；Logging modle can be the intelligent terminal with touch screen, such as tablet computer etc. is used for
It is as shown in Figure 1 b this hair for it that pressure and written text information of the finger to plate are recorded under off-line training mode
A kind of possible hardware structural diagram for the virtual reality writing system that bright embodiment provides.
In character identification system provided in an embodiment of the present invention, myoelectricity module, acceleration module, central processing control mould
Block and the multi-modal interactive mode such as logging modle and tactile, visual feedback module, make people's book in the environment of virtual reality
Writing becomes simple, easy to operateization, and can be detached from specifically write (paper, pen, touch screen version, electronic writing plate in kind
Deng).
When it is implemented, central processing control module, can be used for receiving the multichannel of MEMS module and the acquisition of EMG module
Signal, and the signal received is handled.When it is implemented, MEMS module and the data of EMG module transfer can be warp
Cross pretreated digital signal, in this way, central processing control module can directly to the digital signal that receives carry out data segmentation,
Feature extraction is trained and obtains classifier, as shown in Figure 2.
It is data segmentation first, the effect of data segmentation is that the electromyography signal stream in a period of time that will be recorded is divided into
The small data block of numerous equal lengths, the convenient feature for being used to extract signal.Simultaneously data block length and signal processing time at
Direct ratio, but the shorter classification accuracy of data block length is lower, therefore has both needed data block length long enough to keep its accuracy rate,
It needs data are short to achieve the effect that synchronization process again, is accepted or rejected in length and discrimination so needing to divide in data.Specifically
When implementation, the signal length of segmentation can be set according to actual needs, and the embodiment of the present invention is to this without restriction, example
Such as, can choose signal length is 200ms-300ms.
For MEMS signal, for computational complexity and accuracy rate comprehensive consideration, the embodiment of the present invention can choose base
In the automatic segmentation algorithm of Threshold segmentation, specific algorithm is as follows:
(1) resultant acceleration signal is converted by three axis gesture acceleration signals: i.e.
(2) setting amplification threshold value, optimization resultant acceleration signal can be according to following in a kind of possible embodiment
Method optimizes:
If max (signal) < amplification threshold value, signal=4*signal
IfThen signal=3*signal
(3) the resultant acceleration signal after optimizing carries out straight line fitting with least square method；
(4) acceleration signal after fitting is subjected to cutting:
Slope>SlopeThreshold||seg_error>seg_errorThreshold。
Wherein, slope is fitting a straight line slope, and slopeThrehold table sets slope threshold value, and seg_error indicates fitting
The residual error of straight line, seg_errorThreshold indicate the threshold residual value of setting.
Followed by feature extraction, common feature extracting method specifically include that absolute value mean value (Mean Absolute
Value, MAV), root mean square (Root Mean Square, RMS), variance (Variance, VAR), zero passage count (Zero
Crossing, ZC), waveform length (Waveform Length, WL), slope sign variation (Slope Sign Change, SSC)
Deng, but electromyography signal also have the characteristics that a certain extent it is nonlinear, it is more accurate in order to extract the embodiment of the present invention
Double-spectrum analysis method can be used in the embodiment of the present invention in signal characteristic.It should be appreciated that the feature extracting method of above-mentioned offer
To obtain preferable training pattern, for ease of description, to feature extraction by taking double-spectrum analysis method as an example in the embodiment of the present invention
Detailed process is illustrated.
Higher-order spectrum is defined according to cumulant equation, so also referred to as cumulant spectrum.One steady machine of non-gaussian
The expression formula of the n rank cumulant equation of signal x (t) is as follows:
Wherein,It is the n rank moment equation of signal x (t),It is signal
The n rank moment equation of the equivalent Gaussian process of x (t), its mean value and autocorrelation sequence and signal x (t) are consistent.
Bispectrum B (ω1,ω2) be signal x (t) 3 rank cumulative amountsTwo-dimensional Fourier transform, formula is such as
Under:
Wherein,Meanwhile the power of a linear process can be by it
Double general transformation complete reconstructions come out, expression formula is as follows:
Wherein, H (ω) is the transmission function of the linear time invariant system, γ2And γ3It is scalar constant.
Therefore for treated acceleration signal, be with same processing mode it is feasible, details are not described herein again.
And in embodiments of the present invention, the method that direct estimation can be used calculates double general matrixes of electromyography signal.x(t)
It is the signal for having line length, is divided into K sections, then the direct estimation formula of signal bispectrum is as follows:
Wherein, Sk(ω1,ω2) be kth segment signal bispectrum transformation, calculation method is as follows:
Wherein, L indicates that the number of samples in kth section, X (ω) indicate the Fourier transformation of signal x (t), and * indicates plural number altogether
Yoke transformation.
Signal obtains double general matrixes of a nfft × nfft, wherein nfft is the length of FFT transform after bispectrum transformation
Degree.Meanwhile the integration method that both direction in higher order signal processing, can be used is transformed to original double general matrix datas
One reasonable range of dimension.For example Radial Integrals method is as follows:Wherein:
α indicates the slope value of integration direction, and range is from 0 to 1, BS (ω1,aω2) indicate the bispectrum matrix value inputted.In reality
During border calculates, above formula can be approached to obtain by following formula:
Wherein, Expression and the close max-int of y value, andIt indicates and the close minimum of y value
Integer value.
Axial integral is calculated along frequency axis direction, and calculation formula is as follows:
Therefore we can approach it with following formula:
BSIA(ω1)=∑ BS (ω1,ω2)
In conclusion double general integral feature extraction processes are to convert to form double general matrixes by bispectrum with original signal source,
One-dimensional integral is carried out again and forms integral bispectrum, converts to obtain double Pood's signs finally by Log.
When it is implemented, central processing control module also needs to handle when user is by touch screen writing words, plate
The pressure signal and text information that computer etc. is recorded.Due to being carried out in the embodiment of the present invention to the signal containing time variable
Processing, therefore also all having time variable should be with MEMS in order to preferably set up contrast relationship for pressure signal and text information
The minimum time length of signal and EMG signal divides the two.
Central processing control module can also use wireless communication means or the wire communication such as WiFi (Wireless Fidelity), bluetooth
Means are connect with haptic feedback module, visual feedback module.And treated characteristic signal can be utilized, in neural network
In be trained, obtain the higher classifier of accuracy, i.e. Text region model.
Virtual reality Writing method provided in an embodiment of the present invention includes off-line training mode and online recognition mode.Such as figure
Relation schematic diagram shown in 3, between two stages of off-line training and online recognition.
In off-line training step, participates in trained second user and wear MEMS acceleration transducer and EMG sensor, with just
Normal ways of writing is in text apparatus for writing, such as can be writing words on tablet computer.It, can be according to Fig. 4 institute based on this
The process opening relationships sample database shown:
S41, during second user writing words, acquire the second electromyography signal and the second motor message respectively.
Pressure signal, time series and the text of writing when S42, record second user writing words.
When it is implemented, pressure is believed on virtual reality writing system synchronous acquisition MEMS signal, EMG signal, tablet computer
Number, time signal and text sample.
S43, the second electromyography signal and the second motor message are filtered respectively, noise reduction process.
In this step, the MEMS signal and EMG signal acquire to MEMS module and EMG module be filtered, noise reduction etc.
Reason.
S44, treated the second electromyography signal and the second motor message are split according to the time series of record.
In step S44, step S33 treated EMG signal and MEMS signal compares recorded sequence of events in timing
It is split.
S45, each text for establishing the second electromyography signal after dividing and the second motor message and second user writing
And/or the corresponding relationship between the corresponding pressure signal of the text obtains relationship sample database.
In step S45, the relationship sample database between MEMS signal, EMG signal and pressure signal, text sample is built；
When it is implemented, the training of timing convolutional neural networks can be carried out with this relationship sample database, show that input is MEMS signal and EMG
Signal exports the Text region model for pressure signal and text.
As shown in figure 5, it is the relationship sample database based on building, using timing convolutional neural networks to Text region model
The flow diagram being trained, comprising the following steps:
S51, initialization Text region model parameter.
S52, it is moved from the second electromyography signal and second after selection segmentation in the corresponding relationship for including in relationship sample database
Signal inputs in Text region model.
The second electromyography signal selected in S53, the text information for comparing output and/or pressure signal and relationship sample database
Text corresponding with the second motor message and/or pressure signal.
When specific real-time, the MEMS signal that will save that treated in relationship sample database, EMG signal are input to be trained
In Text region model, pressure signal and Text region result and relationship sample that Text region model to be trained is exported
The MEMS signal and the corresponding pressure signal of EMG signal and text are compared to obtain comparison result in library.
S54, judge whether comparison result is not more than preset threshold, if so, process terminates, it is no to then follow the steps S55.
S55, Text region model parameter is updated, returns to step S52.
It by process shown in fig. 6, can train to obtain Text region model, be based on trained Text region model,
In the embodiment of the present invention Text region can be carried out according to process shown in fig. 6:
S61, during first user's writing words, acquire respectively the first electromyography signal and the first finger movement letter
Number.
When it is implemented, the first user for carrying out Text region wears MEMS acceleration transducer and EMG electromyography signal
Sensor.In a kind of possible embodiment, MEMS acceleration transducer is made of 9 axle sensors, is located substantially at and is write
At the second knuckle of word finger, it is mainly used for acquisition measurement user's finger motion information, motion information comes together in central processing control
Molding block；EMG electromyography signal sensor can be made of 8 pairs of difference electromyographic electrodes, and dispersion is placed in user and writes the small of that hand
On arm, for EMG module for acquiring user's forearm muscle activity signal, electromyography signal comes together in central processing control module.
In specific implementation, the first myoelectricity can be acquired by being placed in the difference electromyographic electrode of first user's writing words arm
Signal, the multi-axial sensor at the second articulations digitorum manus by being placed in first user's writing words finger acquire the first finger movement
Signal.Wherein, multi-axial sensor can be 9 axle sensors.
S62, according to the first electromyography signal and the first finger motion information, determine user's book using Text region model
The text and/or pressure signal write.
In specific implementation, virtual reality Writing method provided in an embodiment of the present invention can be the following steps are included: to
One user's output pressure signal forms touch feedback；And/or visual feedback is formed to the text that the first user output is determined.
In a kind of possible embodiment, by being placed in the electrotactile stimulation electrode slice of first user's finger to described
First user exports the pressure signal and forms touch feedback；And/or the virtual reality device worn by first user
The text determined to first user output forms visual feedback.In this embodiment, the first user's head needs to wear
The VR helmet or VR glasses are worn, the finger tip write wears electrotactile stimulation electrode slice, in this way, the output of Text region model
Pressure signal is handled by central processing control module and is transferred to electrotactile stimulation electrode slice, forms touch feedback in user's finger tip,
The VR helmet of the first user wearing is transferred to after the text that Text region model identifies is handled by central processing control module
Or in VR glasses, pictograph information is formed, as visual feedback.
In a kind of possible embodiment, before acquiring the first electromyography signal and the first finger movement signals respectively,
Further include: the first handwriting trace of the first user of detection；And the first handwriting trace and the first desired guiding trajectory confirmly detected
Matching.I.e. when the first handwriting trace and the first desired guiding trajectory monitored matches, it can trigger and start to carry out Text region.
For example, can detect whether the first user is picture circle clockwise according to the MEMS signal and EMG signal of acquisition, if it is,
Into Text region process, if it is not, then whether persistently detect the first user according to the MEMS signal of acquisition and EMG signal suitable
Hour hands draw circle, in this case, can also apply primary touch feedback to finger tip by electrotactile stimulation module, and prompt to use
Family can start writing words.
During user's writing words, the second handwriting trace of the first user can also be detected；If it is determined that second
Handwriting trace is matched with the second desired guiding trajectory, then enters dormant state；If the second handwriting trace is matched with third desired guiding trajectory,
Then exit current operation program.For example, the first user whether continuous two can be detected according to the MEMS signal and EMG signal of acquisition
Secondary picture circle counterclockwise, if it is, control current operation program enters dormant state, in another embodiment, if even
Continuous detect twice draws circle counterclockwise, then further determines whether to detect that picture is cupped one hand in the other before the chest gesture, if it is, jumping out all steps
Suddenly, exit current operation program, i.e., detect draw counterclockwise twice in succession circle add it is primary draw gesture of cupping one hand in the other before the chest, then exit current fortune
Line program draws circle if only detected counterclockwise twice in succession, controls current operation program and enter dormant state.Meanwhile
Electrotactile stimulation module can also be given according to the pressure signal transmission identified, complete synchronous touch feedback, the text that will identify that
This information passes virtual reality device back, completes synchronizing visual feedback.
Embodiment for a better understanding of the present invention is implemented the present invention below in conjunction with the specific implementation process of Text region
The virtual reality Writing method that example provides is described in detail.As shown in fig. 7, may comprise steps of:
S71, acquisition and the place for opening MEMS module and EMG module synchronization progress finger acceleration signal and electromyography signal
Reason, and identified using Text region model, electrotactile stimulation electrode slice and virtual implementing helmet are opened so as to output phase
Answer pressure signal and text information.
Whether S72, detection virtual reality device are opened, and detection MEMS module, EMG module, electric touch feedback module
Whether state is normal, if so, S73 is thened follow the steps, it is no to then follow the steps S75.
When it is implemented, if virtual reality device do not open, MEMS module or EMG module it is abnormal, be performed both by step
Rapid S75, i.e. prompt user error.When only three's detection passes through, step S73 is executed.
S73, prompt user can start to write.
In this step, if every detection passes through, prompt user that can start to write, for example, piercing by electric touch
Swash module and touch feedback is applied to finger tip, for example, applying short intermittent pressure feedback, three times continuously to prompt user that can start book
It writes.
S74, according to MEMS signal, EMG signal, detect whether finger draws circle clockwise, if so, execute step 76,
If not, thening follow the steps S73.
S75, prompt error, and execute step S71.
When it is implemented, can prompt to report an error by flashing light.
S76, user write during, acquisition MEMS signal and EMG signal as input end signal, be input to text
In identification model, pressure signal and text information are obtained.
When it is implemented, drawing a circle counterclockwise if there is detecting twice in succession, controls current operation program and enter suspend mode
State, while S74 is jumped to walk, if occurring drawing a circle counterclockwise twice in succession plus once drawing gesture of cupping one hand in the other before the chest, directly closes and respectively set
It is standby, and jump out all steps.
S77, the pressure information of acquisition is passed to electrotactile stimulation module, completes synchronous touch feedback；The text that will be obtained
This information passes to virtual reality device, completes synchronizing visual feedback.
S78, detect whether user's finger draws a circle counterclockwise twice in succession according to the MEMS signal and EMG signal of acquisition, such as
Fruit is to then follow the steps S79, if not, executing step S76.
S79, judge whether to detect and once draw gesture of cupping one hand in the other before the chest, if so, executing step S710, otherwise, execute step S711.
S710, current operation program is exited, process terminates.
S711, control current operation program enter dormant state, and execute step S74.
Based on the same inventive concept, a kind of virtual reality writing system is additionally provided in the embodiment of the present invention, due to above-mentioned
The principle that system solves the problems, such as is similar to virtual reality Writing method, therefore the implementation of above system may refer to the reality of method
It applies, overlaps will not be repeated.
Virtual reality writing system provided in an embodiment of the present invention, including central processing control module, electromyogram EMG mould
Block, micro-electromechanical system (MEMS) module, in which:
The EMG module, for acquiring the first electromyography signal, and be transferred to during first user's writing words
The central processing control module；
The MEMS module, for acquiring the first finger movement signals, and pass during first user's writing words
It is defeated by the central processing control module；
The central processing control module, for utilizing according to first electromyography signal and the first finger motion information
Text region model determines the text and/or pressure signal that the user writes, wherein the Text region model is based on pre-
What the relationship sample database first established was trained using convolutional neural networks, second is included at least in the relationship sample database
Corresponding relationship between electromyography signal and second finger motor message and text sample and/or pressure signal.
In a kind of possible embodiment, virtual reality writing system further includes logging modle, in which:
The EMG module is also used to during second user writing words, acquires the second electromyography signal, and transmit
To the central processing control module；
The MEMS module is also used to during second user writing words, acquires second finger motor message, and
It is transferred to the central processing control module；
The logging modle, for recording pressure signal, time series and book when the second user writing words
The text write；
The central processing control module is also used to respectively filter second electromyography signal and the second motor message
Wave, noise reduction process；Treated the second electromyography signal and the second motor message are split according to the time series of record；It builds
The second electromyography signal and the second motor message after vertical segmentation is corresponding with each text and/or the text that the second user is write
Pressure signal between corresponding relationship obtain the relationship sample database.
In a kind of possible embodiment, the central processing control module is specifically used for initialization Text region mould
Shape parameter；From the second electromyography signal and the second movement letter after selection segmentation in the corresponding relationship for including in the relationship sample database
In number input Text region model；Compare and is selected in the text information and/or pressure signal and the relationship sample database of output
The second electromyography signal and the corresponding text of the second motor message and/or pressure signal selected out；If comparison result is no more than pre-
If threshold value, then terminate to train, otherwise, updates Text region model parameter and continue to train, until comparison result is no more than described pre-
If threshold value.
In a kind of possible embodiment, virtual reality writing system provided in an embodiment of the present invention, further includes tactile
Feedback module and/or visual feedback module, in which:
The central processing control module is also used to export the pressure signal formation tactile to the haptic feedback module
Feedback and/or the text formation visual feedback determined to visual feedback module output.
In a kind of possible embodiment, the haptic feedback module includes electrotactile stimulation electrode slice, the vision
Feedback module includes virtual reality device, in which:
The central processing control module, specifically for the electrotactile stimulation electrode by being placed in first user's finger
Piece exports the pressure signal to first user and forms touch feedback；And/or it is worn by first user virtual
Real world devices form visual feedback to the text that first user output is determined.
In a kind of possible embodiment, the EMG module includes difference electromyographic electrode；And
The EMG module is adopted specifically for the difference electromyographic electrode by being placed in the first user writing words arm
Collect the first electromyography signal.
In a kind of possible embodiment, the EMES module includes multi-axial sensor；And
The EMES, specifically for the multiaxis at the second articulations digitorum manus by being placed in the first user writing words finger
Sensor acquires the first finger movement signals.
In a kind of possible embodiment, the central processing control module is also used to utilizing Text region model
Before determining the text and/or pressure signal that the user writes, the first handwriting trace of first user is detected；And really
The first handwriting trace that regular inspection measures is matched with the first desired guiding trajectory.
In a kind of possible embodiment, the central processing control module is also used to write in first user
During text, the second handwriting trace of first user is detected；If it is determined that second handwriting trace and second is in advance
If path matching, then controls current operation program and enter dormant state；If second handwriting trace and third desired guiding trajectory
Matching, then exit current operation program.
For convenience of description, above each section is divided by function describes respectively for each module (or unit).Certainly, In
Implement to realize the function of each module (or unit) in same or multiple softwares or hardware when the present invention.
After the virtual reality Writing method and system for describing exemplary embodiment of the invention, next, introducing
The computing system of another exemplary embodiment according to the present invention.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
In some possible embodiments, computing device according to the present invention can include at least at least one processing
Device and at least one processor.Wherein, the memory is stored with program code, when said program code is by the processing
When device executes, so that the processor executes the void of the illustrative embodiments various according to the present invention of this specification foregoing description
Step in quasi- reality Writing method.For example, the processor can execute step S61 as shown in Figure 6, in the first user
During writing words, the first electromyography signal and the first finger movement signals and step S62 are acquired respectively, according to the first flesh
Electric signal and the first finger motion information determine the text and/or pressure signal that the user writes using Text region model.
The computing device 80 of this embodiment according to the present invention is described referring to Fig. 8.The calculating dress that Fig. 8 is shown
Setting 80 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 8, computing device 80 is showed in the form of universal computing device.The component of computing device 80 may include
But it is not limited to: at least one above-mentioned processor 81, above-mentioned at least one processor 82, (including the storage of the different system components of connection
Device 82 and processor 81) bus 83.
Bus 83 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, processor or the local bus using any bus structures in a variety of bus structures.
Memory 82 may include the readable medium of form of volatile memory, such as random access memory (RAM) 821
And/or cache memory 822, it can further include read-only memory (ROM) 823.
Memory 82 can also include program/utility 825 with one group of (at least one) program module 824, this
The program module 824 of sample includes but is not limited to: operating system, one or more application program, other program modules and journey
It may include the realization of network environment in ordinal number evidence, each of these examples or certain combination.
Computing device 80 can also be communicated with one or more external equipments 84 (such as keyboard, sensing equipment etc.), may be used also
Enable a user to the equipment interacted with computing device 80 communication with one or more, and/or with enable the computing device 80
Any equipment (such as router, modem etc.) communicated with one or more of the other calculating equipment communicates.This
Kind communication can be carried out by input/output (I/O) interface 85.Also, computing device 80 can also pass through network adapter 86
With one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet) communication.
As shown, network adapter 86 is communicated by bus 83 with other modules for computing device 80.It will be appreciated that though figure
In be not shown, can in conjunction with computing device 80 use other hardware and/or software module, including but not limited to: microcode, equipment
Driver, redundant processor, external disk drive array, RAID system, tape drive and data backup storage system etc..
In some possible embodiments, the various aspects of virtual reality Writing method provided by the invention can also be real
It is now a kind of form of program product comprising program code, it is described when described program product is run on a computing device
The exemplary embodiment party various according to the present invention that program code is used to that the computer equipment to be made to execute this specification foregoing description
Step in the virtual reality Writing method of formula, for example, the computer equipment can execute step S61 as shown in Figure 6,
During first user's writing words, acquire respectively the first electromyography signal and the first finger movement signals and step S62,
According to the first electromyography signal and the first finger motion information, using Text region model determine text that the user writes and/
Or pressure signal.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example may be-but not limited to-electricity, magnetic, optical, electromagnetic, red
The system of outside line or semiconductor, device or device, or any above combination.The more specific example of readable storage medium storing program for executing
(non exhaustive list) includes: the electrical connection with one or more conducting wires, portable disc, hard disk, random access memory
(RAM), read-only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc
Read memory (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The program product for Text region of embodiments of the present invention can use the read-only storage of portable compact disc
Device (CD-ROM) and including program code, and can run on the computing device.However, program product of the invention is not limited to
This, in this document, readable storage medium storing program for executing can be any tangible medium for including or store program, which can be commanded
Execution system, device or device use or in connection.
Readable signal medium may include in a base band or as the data-signal that carrier wave a part is propagated, wherein carrying
Readable program code.The data-signal of this propagation can take various forms, including --- but being not limited to --- electromagnetism letter
Number, optical signal or above-mentioned any appropriate combination.Readable signal medium can also be other than readable storage medium storing program for executing it is any can
Read medium, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or
Program in connection.
The program code for including on readable medium can transmit with any suitable medium, including --- but being not limited to ---
Wirelessly, wired, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind --- including local area network (LAN) or extensively
Domain net (WAN)-be connected to user calculating equipment, or, it may be connected to external computing device (such as utilize Internet service
Provider is connected by internet).
It should be noted that although being referred to several unit or sub-units of system in the above detailed description, this stroke
It point is only exemplary not enforceable.In fact, embodiment according to the present invention, it is above-described two or more
The feature and function of unit can embody in a unit.Conversely, the feature and function of an above-described unit can
It is to be embodied by multiple units with further division.
In addition, although describing the operation of the method for the present invention in the accompanying drawings with particular order, this do not require that or
Hint must execute these operations in this particular order, or have to carry out shown in whole operation be just able to achieve it is desired
As a result.Additionally or alternatively, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/or by one
Step is decomposed into execution of multiple steps.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The system for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications can be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (10)
1. a kind of virtual reality Writing method characterized by comprising
During first user's writing words, the first electromyography signal and the first finger movement signals are acquired respectively；
According to first electromyography signal and the first finger motion information, determine what the user write using Text region model
Text and/or pressure signal, wherein the Text region model is to utilize convolutional Neural based on the relationship sample database pre-established
What network was trained, the second electromyography signal and second finger motor message and text are included at least in the relationship sample database
Corresponding relationship between printed words sheet and/or pressure signal.
2. the method as described in claim 1, which is characterized in that the relationship sample database is to obtain according to following below scheme:
During second user writing words, the second electromyography signal and the second motor message are acquired respectively；And
Record pressure signal, time series and the text of writing when the second user writing words；
Second electromyography signal and the second motor message are filtered respectively, noise reduction process；
Treated the second electromyography signal and the second motor message are split according to the time series of record；
Each text and/or this article that the second electromyography signal and the second motor message and the second user after establishing segmentation are write
Corresponding relationship between the corresponding pressure signal of word obtains the relationship sample database.
3. method according to claim 2, which is characterized in that utilize convolutional Neural net based on the relationship sample database pre-established
Network is trained to obtain the Text region model according to following below scheme:
Initialize Text region model parameter；
From the second electromyography signal and the second motor message after selection segmentation in the corresponding relationship for including in the relationship sample database
It inputs in the Text region model；
Compare the second electromyography signal selected in the text information and/or pressure signal and the relationship sample database of output and the
The corresponding text of two motor messages and/or pressure signal；
If comparison result is not more than preset threshold, terminate to train, otherwise, update Text region model parameter and continue to train,
Until comparison result is not more than the preset threshold.
4. method as claimed in claim 1,2 or 3, which is characterized in that further include:
The pressure signal, which is exported, to first user forms touch feedback；And/or
The text determined to first user output forms visual feedback.
5. method as claimed in claim 4, which is characterized in that the first user of Xiang Suoshu exports the pressure signal and forms tactile
Feedback, specifically includes:
Electrotactile stimulation electrode slice by being placed in first user's finger exports the pressure signal to first user
Form touch feedback；And/or
The virtual reality device worn by first user forms vision to the text that first user output is determined
Feedback.
6. method as claimed in claim 1,2 or 3, which is characterized in that determining user's book using Text region model
Before the text and/or pressure signal write, further includes:
Detect the first handwriting trace of first user；And
The first handwriting trace confirmly detected is matched with the first desired guiding trajectory.
7. method as claimed in claim 1,2 or 3, which is characterized in that further include:
During the first user writing words, the second handwriting trace of first user is detected；
If it is determined that second handwriting trace is matched with the second desired guiding trajectory, then enter dormant state；
If second handwriting trace is matched with third desired guiding trajectory, current operation program is exited.
8. a kind of virtual reality writing system, which is characterized in that including central processing control module, electromyogram EMG module, microcomputer
Electric system MEMS module, in which:
The EMG module for acquiring the first electromyography signal during first user's writing words, and is transferred to described
Central processing control module；
The MEMS module, for acquiring the first finger movement signals, and be transferred to during first user's writing words
The central processing control module；
The central processing control module, for utilizing text according to first electromyography signal and the first finger motion information
Identification model determines the text and/or pressure signal that the user writes, wherein the Text region model is based on building in advance
What vertical relationship sample database was trained using convolutional neural networks, the second myoelectricity is included at least in the relationship sample database
Corresponding relationship between signal and second finger motor message and text sample and/or pressure signal.
9. a kind of computing device, which is characterized in that including at least one processor and at least one processor, wherein described
Memory is stored with computer program, when described program is executed by the processor, so that the processor perform claim is wanted
The step of seeking 1~7 any claim the method.
10. a kind of computer-readable medium, which is characterized in that it is stored with the computer program that can be executed by computing device, when
When described program is run on the computing device, so that the computing device perform claim requires the step of 1~7 any the method
Suddenly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910524902.8A CN110443113A (en) | 2019-06-18 | 2019-06-18 | A kind of virtual reality Writing method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910524902.8A CN110443113A (en) | 2019-06-18 | 2019-06-18 | A kind of virtual reality Writing method, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110443113A true CN110443113A (en) | 2019-11-12 |
Family
ID=68428274
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910524902.8A Pending CN110443113A (en) | 2019-06-18 | 2019-06-18 | A kind of virtual reality Writing method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110443113A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111158476A (en) * | 2019-12-25 | 2020-05-15 | 中国人民解放军军事科学院国防科技创新研究院 | Key identification method, system, equipment and storage medium of virtual keyboard |
| CN111783056A (en) * | 2020-07-06 | 2020-10-16 | 诺百爱（杭州）科技有限责任公司 | Method and device for identifying user identity based on electromyographic signal and electronic equipment |
| CN113190161A (en) * | 2021-04-25 | 2021-07-30 | 无锡乐骐科技有限公司 | Electronic writing exercise method based on convolutional neural network |
| CN113616395A (en) * | 2021-08-10 | 2021-11-09 | 长春理工大学 | Prosthesis control method, device, prosthesis equipment and computer readable storage medium |
| EP4160615A1 (en) * | 2021-10-01 | 2023-04-05 | Société BIC | Methods and systems for administering cognitive state cues |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101930285A (en) * | 2009-11-23 | 2010-12-29 | 上海交通大学 | Handwriting recognition method based on surface electromyographic signal |
| WO2015148578A2 (en) * | 2014-03-24 | 2015-10-01 | Alghazi Ahmad Alsayed M | Multi-functional smart mobility aid devices and methods of use |
| CN106227339A (en) * | 2016-08-16 | 2016-12-14 | 西安中科比奇创新科技有限责任公司 | wearable device, virtual reality human-computer interaction system and method |
| CN109634439A (en) * | 2018-12-20 | 2019-04-16 | 中国科学技术大学 | Intelligent text input method |
-
2019
- 2019-06-18 CN CN201910524902.8A patent/CN110443113A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101930285A (en) * | 2009-11-23 | 2010-12-29 | 上海交通大学 | Handwriting recognition method based on surface electromyographic signal |
| WO2015148578A2 (en) * | 2014-03-24 | 2015-10-01 | Alghazi Ahmad Alsayed M | Multi-functional smart mobility aid devices and methods of use |
| CN106227339A (en) * | 2016-08-16 | 2016-12-14 | 西安中科比奇创新科技有限责任公司 | wearable device, virtual reality human-computer interaction system and method |
| CN109634439A (en) * | 2018-12-20 | 2019-04-16 | 中国科学技术大学 | Intelligent text input method |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111158476A (en) * | 2019-12-25 | 2020-05-15 | 中国人民解放军军事科学院国防科技创新研究院 | Key identification method, system, equipment and storage medium of virtual keyboard |
| CN111783056A (en) * | 2020-07-06 | 2020-10-16 | 诺百爱（杭州）科技有限责任公司 | Method and device for identifying user identity based on electromyographic signal and electronic equipment |
| CN111783056B (en) * | 2020-07-06 | 2024-05-14 | 诺百爱（杭州）科技有限责任公司 | Method and device for identifying user identity based on electromyographic signals and electronic equipment |
| CN113190161A (en) * | 2021-04-25 | 2021-07-30 | 无锡乐骐科技有限公司 | Electronic writing exercise method based on convolutional neural network |
| CN113616395A (en) * | 2021-08-10 | 2021-11-09 | 长春理工大学 | Prosthesis control method, device, prosthesis equipment and computer readable storage medium |
| CN113616395B (en) * | 2021-08-10 | 2023-04-14 | 长春理工大学 | Prosthesis control method, device, prosthesis equipment and computer readable storage medium |
| EP4160615A1 (en) * | 2021-10-01 | 2023-04-05 | Société BIC | Methods and systems for administering cognitive state cues |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110443113A (en) | A kind of virtual reality Writing method, system and storage medium | |
| Li et al. | Deep Fisher discriminant learning for mobile hand gesture recognition | |
| Savur et al. | Real-time american sign language recognition system using surface emg signal | |
| Abreu et al. | Evaluating sign language recognition using the myo armband | |
| US9720515B2 (en) | Method and apparatus for a gesture controlled interface for wearable devices | |
| Savur et al. | American Sign Language Recognition system by using surface EMG signal | |
| Li et al. | Automatic recognition of sign language subwords based on portable accelerometer and EMG sensors | |
| CN104134060A (en) | Sign language interpreting, displaying and sound producing system based on electromyographic signals and motion sensors | |
| Shin et al. | Korean sign language recognition using EMG and IMU sensors based on group-dependent NN models | |
| CN109634439B (en) | Intelligent text input method | |
| CN104484644A (en) | Gesture identification method and device | |
| Luo et al. | Wearable air-writing recognition system employing dynamic time warping | |
| Li et al. | Hand gesture recognition and real-time game control based on a wearable band with 6-axis sensors | |
| Pereira-Montiel et al. | Automatic sign language recognition based on accelerometry and surface electromyography signals: A study for Colombian sign language | |
| Sharma et al. | Trbaggboost: An ensemble-based transfer learning method applied to Indian Sign Language recognition | |
| Amor et al. | Toward sign language handshapes recognition using Myo armband | |
| Zea et al. | Real-time hand gesture recognition: a long short-term memory approach with electromyography | |
| Young et al. | Pattern recognition for prosthetic hand user’s intentions using EMG data and machine learning techniques | |
| Singh et al. | A reliable and efficient machine learning pipeline for american sign language gesture recognition using EMG sensors | |
| CN107766773A (en) | Various dimensions control method and control device based on gesture | |
| Salim et al. | A review on hand gesture and sign language techniques for hearing impaired person | |
| Derr et al. | Signer-independent classification of American sign language word signs using surface EMG | |
| CN110413106B (en) | Augmented reality input method and system based on voice and gestures | |
| Matei et al. | Engineering a digital twin for manual assembling | |
| Al-Qaisy et al. | AI-based portable gesture recognition system for hearing impaired people using wearable sensors |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191112 |
|
| RJ01 | Rejection of invention patent application after publication |