CN110414473A - A kind of data glove Gesture Recognition Algorithm based on mathematical statistics - Google Patents
A kind of data glove Gesture Recognition Algorithm based on mathematical statistics Download PDFInfo
- Publication number
- CN110414473A CN110414473A CN201910721419.9A CN201910721419A CN110414473A CN 110414473 A CN110414473 A CN 110414473A CN 201910721419 A CN201910721419 A CN 201910721419A CN 110414473 A CN110414473 A CN 110414473A
- Authority
- CN
- China
- Prior art keywords
- gesture
- data glove
- standard deviation
- calculated
- recognition algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- User Interface Of Digital Computer (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of data glove Gesture Recognition Algorithm based on mathematical statistics, is related to field of artificial intelligence.The same gesture is divided into nature and stretched condition to distinguish collecting sensor angle value, numerical value is stored in respectively in two this paper documents by the data glove including that will wear using sensor.getData () method.The numerical value in text document is read, is stored in array a1 and b1, in a2 and b2 ..., a20 and b20, in ai=(ai, 1, ai, 2, ai, 3 .., ai, 24), bi=(bi, 1, bi, 2, bi, 3 .., bi, 24).The invention is by calculating standard deviation and related coefficient, judging to obtain the degrees of offset and linear relationship between the gesture in gesture and template library at random, finding out in template library and obtaining the most similar gesture of gesture at random.By screening twice, screening value precision is gradually increased, so that gesture identification is very accurate.And the gesture identification based on data glove can exclude the interference of external environment.
Description
Technical field
The present invention relates to field of artificial intelligence, specially a kind of data glove gesture identification based on mathematical statistics is calculated
Method.
Background technique
Gesture Recognition can be usually used in Sign Language Recognition and human-computer interaction.The process of gesture identification is exactly by the mould of hand
Tracing point in shape parameter space is categorized into the process of some subset in space, and static gesture corresponds in model parameter space
One point, and dynamic gesture then corresponds to a track in model parameter space, therefore their recognition methods is different.It is existing
Some Gesture Recognitions mainly have template matching method, neural network, and hidden Markov model method etc..Wherein neural network
It is the gesture identification method of view-based access control model.Hidden Markov model method is suitable for dynamic hand gesture recognition, and artificial neural network is more
It is suitble to static gesture identification.But these technologies are due to some inherent characteristics such as timeliness, the spatialities of gesture, and manpower is multiple
Miscellaneous deformable body, visible sensation method itself has unstability in addition, increases the difficulty of the gesture identification of view-based access control model, so that hand
The discrimination of gesture is not high, largely affects the effect and performance of gesture identification, interactivity is also and bad, and gesture is not achieved
The purpose of high efficiency identification.
Specifically, common gesture identification method in the prior art are as follows:
By using gesture mathematical model, with ten tuples, (K1, K2 ..., K10) indicates the bending of ten finger-joints
State, by describing gesture to element entry value is -1,1 or 0.In drawing template establishment, using " template training " thought, needle
To the gesture sample of standard gesture acquisition user, gesture is calibrated automatically.By prompting user to hold with a firm grip or open one's hand, compare data hand
Cover each sub-value of sensor, so record it is current until each sensor maximum value and minimum value, then use following public affairs
Formula is corrected response, to define different gestures, so that template set be made to be suitable for relatively more users.
Range；=Maxq-Min
Range；=Maxq-Min
Rect；=(Angle-Min) * 4095/Range；
Rect；=(Angle-Min) * 4095Range；
Wherein, Range indicates the dynamic range of No. 1 sensor response, Rect；Refer to the sensor response
4ngle is to 0,4095] corrected values of Interval Maps.
But in the method: since to bend and stretch degree different for the finger-joint of different user, so that when matching, template
It is still limited to collect target user's quantity, can not accomplish perfectly to match relatively, accurately degree be not achieved, error is still deposited
In；And independence is poor, and flexibility is not high, and gesture identification rate is not also high.
Summary of the invention
In view of the deficiencies of the prior art, the present invention provides a kind of, and the data glove gesture identification based on mathematical statistics is calculated
Method solves the problems, such as that different user finger-joint bends and stretches that degree is different to be caused to accomplish perfectly to match relatively.
In order to achieve the above object, the present invention is achieved by the following technical programs: a kind of data based on mathematical statistics
Gloves Gesture Recognition Algorithm, method includes the following steps:
Step 1: the data glove of wearing is used sensor.getData () method, the same gesture is divided into nature
State and stretched condition distinguish collecting sensor angle value, numerical value are stored in respectively in two this paper documents.Read text
Numerical value in document, is stored in array a1 and b1, in a2 and b2 ..., a20 and b20, ai=(ai, 1, ai, 2, ai, 3 ..,
Ai, 24), in bi=(bi, 1, bi, 2, bi, 3 .., bi, 24).
Step 2: data glove in operator's wearing, and the side the sensor.getData () by being mentioned in the first step
Method obtains the bending angle angle value of each sensor in real time, is stored in array data.
Step 3: calculating standard deviation, standard deviation is smaller, it was demonstrated that the degrees of offset between data and its average is smaller, says
Bright data=(c1, c2 ..., c24) more connect ai=(ai, 1, ai, 2, ai, 3 ..., ai, 24) and bi=(bi, 1, bi, 2, bi,
3 ..., bi, 24), the gesture done is more close with the gesture that ai and bi is indicated.
Step 4: standard deviation calculates after completing, needs to be screened according to standard deviation, that is, filter out the smallest standard
Difference.
Step 5: carrying out the second wheel screening, before screening, related coefficient is first calculated.
Step 6: related coefficient (r) calculates after completing, from r=(r1,...,rnm) in filter out maximum phase relation
Number.
Preferably, in the third step step, the calculation of standard deviation is calculated are as follows:
(1) for arbitrary i (1≤i≤20), average is calculated:
(2) standard deviation is calculated:
Preferably, the described 4th it is step by step rapid in screening minimum sandards difference mode it is as follows:
(1) if there is some ui, so that (ui, r)=0, then retain ui；
If (ui, r) ≠ 0, there are ui to be considered whether to all ui, so that (ui, r)=1；
(2) if there is some ui, so that (ui, r)=1, then retain ui；
If (ui, r) ≠ 1, there are ui to be considered whether to all ui, so that (ui, r)=2；
And so on.
5. preferred, the calculation of the 5th step related coefficient is as follows:
(1) standard deviation is calculated:
……
With
……
(4) covariance is calculated:
……
(5) related coefficient is calculated:
……
Preferably, the 6th it is step by step rapid in screening process it is as follows, the second wheel screening is to be compared with " 0.01 " for unit
Accurately, feasibility is strong.
(1) if there is some ri, so that ri=1, then retain ri；
If ri≠ 1, to all riConsider whether that there are ri, so that ri=0.99；
(2) if there is some ri, so that ri=0.99, then retain ri；
If ri≠ 0.99, to all riConsider whether that there are ri, so that ri=0.98；Analogized with this.
The present invention provides a kind of data glove Gesture Recognition Algorithm based on mathematical statistics.The invention passes through calculating standard
Difference and related coefficient, to judge to obtain the degrees of offset and linear relationship between the gesture in gesture and template library at random, in template
It is found out in library and obtains the most similar gesture of gesture at random.By screening twice, screening value precision is gradually increased, so that hand
Gesture identification is very accurate.And the gesture identification based on data glove can exclude the interference of external environment.
Detailed description of the invention
Fig. 1 is flow chart of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.
Examples of the embodiments are shown in the accompanying drawings, and in which the same or similar labels are throughly indicated identical or classes
As element or element with the same or similar functions.The embodiments described below with reference to the accompanying drawings are exemplary, purport
It is being used to explain the present invention, and is being not considered as limiting the invention.
Referring to Fig. 1, being flow chart of the invention.
It is as follows in the process of this programme:
Step 1:, by wearing data glove, using Vizard using 20 kinds of hearing-impaired people singlehanded mathematics gestures as standard
The same gesture is divided into nature and stretched condition to collect biography respectively by sensor.getData () method under platform
Numerical value is stored in two this paper documents by sensor angle value respectively.The numerical value in text document is read, is stored in array respectively
In a1 and b1, a2 and b2 ..., a20 and b20, ai=(ai, 1, ai, 2, ai, 3 .., ai, 24), bi=(bi, 1, bi, 2, bi,
3,..,bi,24)。
Step 2: the data glove in operator's wearing, obtains each biography by sensor.getData () method in real time
The bending angle angle value of sensor, is stored in array data, data=(c1, c2, c3 ..., c24).
Step 3: according to the following formula, calculating standard deviation.Variance is the quadratic sum of each data and the difference of its average
Average, and standard deviation is the square root that counts of variance.Standard deviation is smaller, it was demonstrated that the degrees of offset between data and its average
It is smaller, illustrate data=(c1,c2,...,c24) more meet ai=(ai,1,ai,2,ai,3,...,ai,24) and bi=(bi,1,bi,2,
bi,3,...,bi,24), the gesture and a doneiAnd biThe gesture of expression is more close.
(1) for arbitrary i (1≤i≤20), average is calculated:
(2) standard deviation is calculated:
Step 4: standard deviation calculates after completing, needing to be screened according to standard deviation, screening process is as follows,
Filter out the smallest standard deviation.
(1) if there is some ui, so that (ui, r)=0, then retain ui；
If (ui, r) ≠ 0, there are ui to be considered whether to all ui, so that (ui, r)=1；
(2) if there is some ui, so that (ui, r)=1, then retain ui；
If (ui, r) ≠ 1, there are ui to be considered whether to all ui, so that (ui, r)=2；Analogized with this.
It is not very accurately, if encountered several step 5: being that unit is screened since first round screening is with " 1 "
The standard deviation of gesture is equal, it is necessary to carry out the second wheel screening, before screening, first to calculate related coefficient, calculation method is such as
Shown in lower.Wherein nm is the gesture number that first round screening meets condition.Covariance is the collaborative variation to two stochastic variables
Measurement.Related coefficient is the index for measuring linearly related degree between two stochastic variables, when related coefficient is " 1 ", card
There is linear relationships with probability " 1 " for the two bright stochastic variables.When related coefficient is larger, then linearly related degree is preferable,
Conversely, linearly related degree is poor.
(1) standard deviation is calculated:
......
With
......
(2) covariance is calculated:
......
(3) related coefficient is calculated:
......
It is last: after related coefficient (r) calculates completion, from r=(r1,...,rnm) in filter out maximum related coefficient,
Screening process is as follows, and the second wheel screening is with " 0.01 " for unit, and more accurate, feasibility is strong.
(1) if there is some ri, so that ri=1, then retain ri；
If ri≠ 1, to all riConsider whether that there are ri, so that ri=0.99；
(2) if there is some ri, so that ri=0.99, then retain ri；
If ri≠ 0.99, to all riConsider whether that there are ri, so that ri=0.98；And analogized with this.
By screening twice, screening value precision is gradually increased, so that gesture identification is very accurate.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Anyone skilled in the art in the technical scope disclosed by the present invention, according to the technique and scheme of the present invention and its
Inventive concept is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (5)
1. a kind of data glove Gesture Recognition Algorithm based on mathematical statistics, it is characterised in that: include the following steps
Step 1: the data glove of wearing is used sensor.getData () method, the same gesture is divided into nature
Collecting sensor angle value is distinguished with stretched condition, numerical value is stored in respectively in two this paper documents.Read text document
In numerical value, be stored in array a1 and b1, in a2 and b2 ..., a20 and b20, ai=(ai, 1, ai, 2, ai, 3 .., ai,
24), in bi=(bi, 1, bi, 2, bi, 3 .., bi, 24)；
Step 2: data glove in operator's wearing, and sensor.getData () method by being mentioned in the first step, it is real
When obtain the bending angle angle value of each sensor, be stored in array data；
Step 3: calculating standard deviation；
Step 4: standard deviation calculates after completing, is screened according to standard deviation, that is, filter out the smallest standard deviation；
Step 5: carrying out the second wheel screening, before screening, related coefficient is first calculated；
Step 6: related coefficient (r) calculates after completing, from r=(r1,...,rnm) in filter out maximum related coefficient.
2. a kind of data glove Gesture Recognition Algorithm based on mathematical statistics according to claim 1, it is characterised in that: institute
It states in third step step, calculates the calculation of standard deviation are as follows:
(1) for arbitrary i (1≤i≤20), average is calculated:
(2) standard deviation is calculated:
3. a kind of data glove Gesture Recognition Algorithm based on mathematical statistics according to claim 1, it is characterised in that: institute
Stating the 4th, the mode of middle screening minimum sandards difference is as follows suddenly step by step:
(1) if there is some ui, so that (ui, r)=0, then retain ui；
If (ui, r) ≠ 0, there are ui to be considered whether to all ui, so that (ui, r)=1；
(2) if there is some ui, so that (ui, r)=1, then retain ui；
If (ui, r) ≠ 1, there are ui to be considered whether to all ui, so that (ui, r)=2；And so on.
4. a kind of data glove Gesture Recognition Algorithm based on mathematical statistics according to claim 1, it is characterised in that: institute
The calculation for stating the 5th step related coefficient is as follows:
(1) standard deviation is calculated:
……
With
……
(2) covariance is calculated:
……
(3) related coefficient is calculated:
……
5. a kind of data glove Gesture Recognition Algorithm based on mathematical statistics according to claim 1, it is characterised in that: institute
Stating the 6th, middle screening process is as follows suddenly step by step, and the second wheel screening is with " 0.01 " for unit.
(1) if there is some ri, so that ri=1, then retain ri；
If ri≠ 1, to all riConsider whether that there are ri, so that ri=0.99；
(2) if there is some ri, so that ri=0.99, then retain ri；
If ri≠ 0.99, to all riConsider whether that there are ri, so that ri=0.98；Analogized with this.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910721419.9A CN110414473B (en) | 2019-08-06 | 2019-08-06 | Data glove gesture recognition algorithm based on mathematical statistics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910721419.9A CN110414473B (en) | 2019-08-06 | 2019-08-06 | Data glove gesture recognition algorithm based on mathematical statistics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110414473A true CN110414473A (en) | 2019-11-05 |
| CN110414473B CN110414473B (en) | 2022-02-25 |
Family
ID=68366080
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910721419.9A Active CN110414473B (en) | 2019-08-06 | 2019-08-06 | Data glove gesture recognition algorithm based on mathematical statistics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110414473B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120225719A1 (en) * | 2011-03-04 | 2012-09-06 | Mirosoft Corporation | Gesture Detection and Recognition |
| US20150346828A1 (en) * | 2014-05-28 | 2015-12-03 | Pegatron Corporation | Gesture control method, gesture control module, and wearable device having the same |
| CN105868715A (en) * | 2016-03-29 | 2016-08-17 | 苏州科达科技股份有限公司 | Hand gesture identifying method, apparatus and hand gesture learning system |
| CN106097835A (en) * | 2016-06-03 | 2016-11-09 | 西安理工大学 | A kind of deaf mute exchanges the method for intelligent assistance system and exchange |
| CN107678550A (en) * | 2017-10-17 | 2018-02-09 | 哈尔滨理工大学 | A kind of sign language gesture recognition system based on data glove |
| CN108268132A (en) * | 2017-12-26 | 2018-07-10 | 北京航空航天大学 | A kind of gesture identification method and human-computer interaction device based on gloves acquisition |
| CN109543644A (en) * | 2018-06-28 | 2019-03-29 | 济南大学 | A kind of recognition methods of multi-modal gesture |
| CN109885166A (en) * | 2019-02-25 | 2019-06-14 | 浙江工商大学 | Intelligent sign language translation gloves and its gesture identification method |
-
2019
- 2019-08-06 CN CN201910721419.9A patent/CN110414473B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120225719A1 (en) * | 2011-03-04 | 2012-09-06 | Mirosoft Corporation | Gesture Detection and Recognition |
| US20150346828A1 (en) * | 2014-05-28 | 2015-12-03 | Pegatron Corporation | Gesture control method, gesture control module, and wearable device having the same |
| CN105868715A (en) * | 2016-03-29 | 2016-08-17 | 苏州科达科技股份有限公司 | Hand gesture identifying method, apparatus and hand gesture learning system |
| CN106097835A (en) * | 2016-06-03 | 2016-11-09 | 西安理工大学 | A kind of deaf mute exchanges the method for intelligent assistance system and exchange |
| CN107678550A (en) * | 2017-10-17 | 2018-02-09 | 哈尔滨理工大学 | A kind of sign language gesture recognition system based on data glove |
| CN108268132A (en) * | 2017-12-26 | 2018-07-10 | 北京航空航天大学 | A kind of gesture identification method and human-computer interaction device based on gloves acquisition |
| CN109543644A (en) * | 2018-06-28 | 2019-03-29 | 济南大学 | A kind of recognition methods of multi-modal gesture |
| CN109885166A (en) * | 2019-02-25 | 2019-06-14 | 浙江工商大学 | Intelligent sign language translation gloves and its gesture identification method |
Non-Patent Citations (3)
| Title |
|---|
| P. D. S. H. GUNAWARDANE等: "Comparison of hand gesture inputs of leap motion controller & data glove in to a soft finger", 《2017 IEEE INTERNATIONAL SYMPOSIUM ON ROBOTICS AND INTELLIGENT SENSORS》 * |
| VIJAY KUMARI THAKUR等: "Robust Hand Gesture Recognition for Human Machine Interaction System", 《JOURNAL OF GLOBAL RESEARCH IN COMPUTER SCIENCE》 * |
| 王赋攀 等: "一种视觉信息融合数据手套设计研究", 《计算机研究与发展》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110414473B (en) | 2022-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10339371B2 (en) | Method for recognizing a human motion, method for recognizing a user action and smart terminal | |
| CN105631439B (en) | Face image processing process and device | |
| CN108182433A (en) | A kind of meter reading recognition methods and system | |
| CN107123027A (en) | A kind of cosmetics based on deep learning recommend method and system | |
| CN106971130A (en) | A kind of gesture identification method using face as reference | |
| CN108665120A (en) | The foundation of scoring model, the appraisal procedure of user credit and device | |
| CN116226691B (en) | Intelligent finger ring data processing method for gesture sensing | |
| CN107219924A (en) | A kind of aerial gesture identification method based on inertial sensor | |
| CN109101938A (en) | A kind of multi-tag age estimation method based on convolutional neural networks | |
| CN105719328A (en) | Normalizing method and system of hand drawing geometric figures | |
| CN104049874A (en) | Touch chirography generation method and system of touch pen | |
| CN109190698B (en) | Classification and identification system and method for network digital virtual assets | |
| CN104484644A (en) | Gesture identification method and device | |
| CN111700718A (en) | Holding posture identifying method, holding posture identifying device, artificial limb and readable storage medium | |
| CN106971131A (en) | A kind of gesture identification method based on center | |
| CN106778491B (en) | The acquisition methods and equipment of face 3D characteristic information | |
| CN106339460A (en) | Online drawing processing system and online drawing processing method | |
| CN114384999B (en) | User-independent myoelectric gesture recognition system based on self-adaptive learning | |
| CN109916350A (en) | A kind of method, apparatus and terminal device generating three-dimensional coordinates measurement program | |
| CN106529480A (en) | Finger tip detection and gesture identification method and system based on depth information | |
| CN113762401A (en) | Self-adaptive classification task threshold adjusting method, device, equipment and storage medium | |
| CN109657527B (en) | Painting brush touch identification system and method | |
| CN113724838B (en) | Emotion identification system based on big data | |
| CN104850225A (en) | Activity identification method based on multi-level fusion | |
| CN106250890A (en) | A kind of fingerprint identification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |