CN104392237B - Fuzzy sign language identification method for data gloves - Google Patents
Fuzzy sign language identification method for data gloves Download PDFInfo
- Publication number
- CN104392237B CN104392237B CN201410655579.5A CN201410655579A CN104392237B CN 104392237 B CN104392237 B CN 104392237B CN 201410655579 A CN201410655579 A CN 201410655579A CN 104392237 B CN104392237 B CN 104392237B
- Authority
- CN
- China
- Prior art keywords
- represent
- mrow
- mtr
- mtd
- state
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012545 processing Methods 0.000 claims abstract description 10
- 230000006870 function Effects 0.000 claims description 25
- 238000005452 bending Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 230000009471 action Effects 0.000 abstract description 2
- 230000006872 improvement Effects 0.000 description 16
- 210000003811 finger Anatomy 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000011109 contamination Methods 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- VAYOSLLFUXYJDT-RDTXWAMCSA-N Lysergic acid diethylamide Chemical compound C1=CC(C=2[C@H](N(C)C[C@@H](C=2)C(=O)N(CC)CC)C2)=C3C2=CNC3=C1 VAYOSLLFUXYJDT-RDTXWAMCSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 210000005224 forefinger Anatomy 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 210000004932 little finger Anatomy 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 210000003813 thumb Anatomy 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
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
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a fuzzy sign language identification method of a data glove, which comprises the following steps: acquiring hand motion data and carrying out fuzzy processing on the hand motion data to obtain a gesture frame sequence; and according to the hand language database and the probability database, carrying out recognition processing on the obtained gesture frame sequence to obtain a gesture frame sequence recognition result. According to the invention, the problem of low recognition rate caused by different sizes of palms is effectively avoided by carrying out fuzzy processing on hand action data, and the optimal recognition of the current gesture can be selected according to the front and back gestures by combining the hand language database and the probability database, so that the gesture recognition accuracy is greatly improved. The fuzzy sign language identification method of the data glove can be widely applied to sign language identification products.
Description
Technical field
The present invention relates to the fuzzy sign Language Recognition Method of gesture identification field, more particularly to a kind of data glove.
Background technology
The domestic and international scientist of gesture identification carried out numerous studies.1994, Ramon M S and Dannil T were ground
Control and grasping system that a kind of manual work of the hand crawl process based on physical constraint is synthesized are made.Nineteen ninety-five, Lee J
Intae and Kunii Tosiyasv L researchs obtain the motion image data of hand with video camera come automatic analyzing three-dimensional gesture, real
Existing three-dimension gesture reconstruct.1997, the Glove TalkII systems of the Sidney S F researchs of University of Toronto were mesh
Preceding most influential gesture interface system, user gesture is converted into sign language parameter using neutral net, passes through language by him
Synthesizer synthesizes language output.China Gao Wen et al., the sign language for also having carried out the behavior act identification based on gesture and people is closed
Into the research of technology.
The gesture identification for being currently based on sensing data gloves is to directly obtain finger motion characteristic from sensor, so
Afterwards by the algorithm of matching be transcribed into people can Direct Recognition word or sound.But at present sign language interpreter technology it is most by
It is limited to the identification of word, and as increasing for sign language storehouse easily causes translation and obscured, and it is not of uniform size due to human hand,
It is easier to cause that the gesture identification efficiency difference between different people is larger, recognition accuracy is relatively low.
The content of the invention
In order to solve the above-mentioned technical problem, it is an object of the invention to provide the one of a kind of accuracy rate that can improve gesture identification
Plant the fuzzy sign Language Recognition Method of data glove.
The technical solution adopted in the present invention is：
A kind of fuzzy sign Language Recognition Method of data glove, comprises the following steps：
A, acquisition hand motion data simultaneously carry out Fuzzy Processing to it, obtain gesture frame sequence；
B, according to sign language database and probability database, processing is identified to obtained gesture frame sequence, gesture is obtained
Frame sequence recognition result.
As a kind of further improvement of the fuzzy sign Language Recognition Method of described data glove, described step A includes：
A1, each finger obtained in hand motion data angle of bend, and according to default bending membership function,
Draw the case of bending of each corresponding finger；
A2, the palm angle of pitch obtained in hand motion data, and calculated according to default pitching membership function,
The maximum as corresponding pitch attitude of value of obtaining a result；
A3, the palm inclination angle obtained in hand motion data, and calculated according to default inclination membership function,
The maximum as corresponding heeling condition of value of obtaining a result；
A4, the palm yaw angle obtained in hand motion data, and calculated according to default driftage membership function,
The maximum as corresponding driftage state of value of obtaining a result；
A5, pitch attitude, heeling condition and the driftage state obtained according to calculating, with reference to default rule, draw correspondence
Palm direction；
A6, the case of bending according to palm direction and each finger, draw gesture frame, and and then draw gesture frame sequence.
It is used as a kind of further improvement of the fuzzy sign Language Recognition Method of described data glove, it is characterised in that：It is described
Step B include：
B1, acquisition gesture frame sequence, gesture frame is extracted according to order from the beginning to the end；
B2, the gesture frame of extraction is sequentially placed into corresponding node respectively；
B3, the corresponding all words of each gesture frame are extracted from sign language database successively, and added into corresponding
In node, until all gesture frames complete the retrieval of sign language database on gesture frame sequence；
B4, by the incidental words of two neighboring node according to node order distinguish combination of two, by upper one in combination
The words of individual node points to the words of next node；
B5, all combine indexed out into the probability of each combination in probability database respectively；
B6, a sentence for finding out probability in the sentence that each group is combined into and maximum, draw gesture frame sequence identification knot
Really.
As a kind of further improvement of the fuzzy sign Language Recognition Method of described data glove, in described step A1
Bending membership function is：
Wherein, X ∈ U0, U0Represent digital flexion angle, U0=[0,120], in U0On set up three of digital flexion angle
Fuzzy set A0Represent the state that case of bending is " stretching ", A1=represent state of the case of bending for " half bends ", A2=represent curved
Curved state is the state of " holding ".
As a kind of further improvement of the fuzzy sign Language Recognition Method of described data glove, in described step A2
Pitching membership function is：
Wherein, x ∈ U1, U1Represent the palm angle of pitch, U1=[- 90,90], in U1On set up three fuzzy set B of the angle of pitch0
Represent the state that the angle of pitch is " bowing ", B1=represent the state that the angle of pitch is " level ", B2=represent the shape that the angle of pitch is " facing upward "
State.
As a kind of further improvement of the fuzzy sign Language Recognition Method of described data glove, in described step A3
Tilting membership function is：
Wherein, y ∈ U2, U2Represent palm inclination angle, U2=[- 180,180], in U2On set up three of inclination angle and obscure
Collect C0Represent the state that inclination angle is " "Left"-deviationist ", C1=represent the state that inclination angle is " level ", C2=represent that inclination angle is the " right side
Incline " state, C3=represent the state that inclination angle is " upset level ".
As a kind of further improvement of the fuzzy sign Language Recognition Method of described data glove, in described step A3
Driftage membership function be：
Wherein, z ∈ U3, U3Represent palm yaw angle, U3=[0,360], in U3On set up three fuzzy set D of yaw angle0
Represent the state that yaw angle is " preceding ", D1=represent the state that yaw angle is " right side ", D2=state that yaw angle is " rear " is represented,
D3=represent the state that yaw angle is " left side ".
As a kind of further improvement of the fuzzy sign Language Recognition Method of described data glove, the sign language database with
Digital flexion state and palm are towards the gesture frame formed as index, and the corresponding words of gesture is used as the content being indexed.
As a kind of further improvement of the fuzzy sign Language Recognition Method of described data glove, in the probability database
Words combination probability to be obtained using language model training tool SRILM.
The beneficial effects of the invention are as follows：
A kind of fuzzy sign Language Recognition Method of data glove of the present invention has by carrying out Fuzzy Processing to hand action data
Effect is avoided the problem of the discrimination caused by hand size differs is relatively low, and by combining sign language database and probability data
Storehouse so that the present invention can choose the optimal identification of current gesture according to front and rear gesture, greatly improve the accuracy rate of gesture identification.
Brief description of the drawings
The embodiment to the present invention is described further below in conjunction with the accompanying drawings：
Fig. 1 is a kind of step flow chart of the fuzzy sign Language Recognition Method of data glove of the invention；
Fig. 2 is a kind of fuzzy sign Language Recognition Method step A of data glove of the invention step flow chart；
Fig. 3 is a kind of fuzzy sign Language Recognition Method step B of data glove of the invention step flow chart；
Fig. 4 be a kind of data glove of the invention fuzzy sign Language Recognition Method in gesture frame composition schematic diagram.
Embodiment
With reference to Fig. 1, a kind of fuzzy sign Language Recognition Method of data glove of the invention comprises the following steps：
A, acquisition hand motion data simultaneously carry out Fuzzy Processing to it, obtain gesture frame sequence；
B, according to sign language database and probability database, processing is identified to obtained gesture frame sequence, gesture is obtained
Frame sequence recognition result.
With reference to Fig. 2, a kind of further improvement of the fuzzy sign Language Recognition Method of described data glove, described step are used as
Rapid A includes：
A1, each finger obtained in hand motion data angle of bend, and according to default bending membership function,
Draw the case of bending of each corresponding finger；
A2, the palm angle of pitch obtained in hand motion data, and calculated according to default pitching membership function,
The maximum as corresponding pitch attitude of value of obtaining a result；
A3, the palm inclination angle obtained in hand motion data, and calculated according to default inclination membership function,
The maximum as corresponding heeling condition of value of obtaining a result；
A4, the palm yaw angle obtained in hand motion data, and calculated according to default driftage membership function,
The maximum as corresponding driftage state of value of obtaining a result；
A5, pitch attitude, heeling condition and the driftage state obtained according to calculating, with reference to default rule, draw correspondence
Palm direction；
A6, the case of bending according to palm direction and each finger, draw gesture frame, and and then draw gesture frame sequence.
With reference to Fig. 3, as a kind of further improvement of the fuzzy sign Language Recognition Method of described data glove, its feature exists
In：Described step B includes：
B1, acquisition gesture frame sequence, gesture frame is extracted according to order from the beginning to the end；
B2, the gesture frame of extraction is sequentially placed into corresponding node respectively；
B3, the corresponding all words of each gesture frame are extracted from sign language database successively, and added into corresponding
In node, until all gesture frames complete the retrieval of sign language database on gesture frame sequence；
B4, by the incidental words of two neighboring node according to node order distinguish combination of two, by upper one in combination
The words of individual node points to the words of next node；
B5, all combine indexed out into the probability of each combination in probability database respectively；
B6, a sentence for finding out probability in the sentence that each group is combined into and maximum, draw gesture frame sequence identification knot
Really.
Such as, gesture sequence S has two gesture frames to be followed successively by A and B, it is assumed that gesture A has words " you " and " that ", gesture B
Have words " good " and " just ", it is assumed that the probability of " hello " is 0.0052, the probability of " you just " is " 0.00045 ", " OK " it is general
Rate is 0.0078, and the probability of " that just " is 0.00032, then gesture sequence S recognition result is that sentence of maximum probability, i.e.,
Recognition result is " OK ".
As a kind of further improvement of the fuzzy sign Language Recognition Method of described data glove, in described step A1
Bending membership function is：
Wherein, X ∈ U0, U0Represent digital flexion angle, U0=[0,120], in U0On set up three of digital flexion angle
Fuzzy set A0Represent the state that case of bending is " stretching ", A1=represent state of the case of bending for " half bends ", A2=represent curved
Curved state is the state of " holding ".
As a kind of further improvement of the fuzzy sign Language Recognition Method of described data glove, in described step A2
Pitching membership function is：
Wherein, x ∈ U1, U1Represent the palm angle of pitch, U1=[- 90,90], in U1On set up three fuzzy set B of the angle of pitch0
Represent the state that the angle of pitch is " bowing ", B1=represent the state that the angle of pitch is " level ", B2=represent the shape that the angle of pitch is " facing upward "
State.
If the palm angle of pitch is 42, the membership function that x=42 is substituted into formula two is calculated, and draws B0(42)=0.1,
B1(42)=0.3, B2(42)=0, B1>B0>B2, then the angle of pitch of the x values of this input is level.
As a kind of further improvement of the fuzzy sign Language Recognition Method of described data glove, in described step A3
Tilting membership function is：
Wherein, y ∈ U2, U2Represent palm inclination angle, U2=[- 180,180], in U2On set up three of inclination angle and obscure
Collect C0Represent the state that inclination angle is " "Left"-deviationist ", C1=represent the state that inclination angle is " level ", C2=represent that inclination angle is the " right side
Incline " state, C3=represent the state that inclination angle is " upset level ".
As a kind of further improvement of the fuzzy sign Language Recognition Method of described data glove, in described step A3
Driftage membership function be：
Wherein, z ∈ U3, U3Represent palm yaw angle, U3=[0,360], in U3On set up three fuzzy set D of yaw angle0
Represent the state that yaw angle is " preceding ", D1=represent the state that yaw angle is " right side ", D2=state that yaw angle is " rear " is represented,
D3=represent the state that yaw angle is " left side ".
As a kind of further improvement of the fuzzy sign Language Recognition Method of described data glove, the sign language database with
Digital flexion state and palm are towards the gesture frame formed as index, and the corresponding words of gesture is used as the content being indexed.
As a kind of further improvement of the fuzzy sign Language Recognition Method of described data glove, in the probability database
Words combination probability to be obtained using language model training tool SRILM.
With reference to Fig. 4, wherein, a gesture frame sequence in the present invention refers to a complete sign language sentence, includes N number of hand
Gesture frame.One gesture frame is made up of 4 bytes (32), wherein the 32nd reservation, the 26th~30 and the 11st~15 point
Not Wei left hand and the right hand " palm direction " state, the 16th~25 and the 1st~the 10th is respectively storage left hand and the right hand
Digital flexion state, one of digital flexion state accounts for 2 positions, thumb, forefinger, middle finger, the third finger and little finger of toe respectively from
A high position is to low level sequence, and the 0th is check bit.
Sign language frame sequence is arranged in chronological order by multiple sign language frames, the multiple words of sign language frame correspondence or
Word, because a gesture represents the different meanings in different linguistic context scapes, and is carried out to gesture in the method
It is abstract, the gesture of some only slight differences is abstracted into identical sign language frame.And gesture identification part is exactly by sign language frame sequence
The statistical probability of sign language frame based on context in row by most suitable words extract and with other in sign language frame sequence
Sign language frame forms optimal sentence.
Good hand's language database and probability database are must be set up before Sign Language Recognition.
The foundation of sign language database refers to reference《Chinese Sign Language》Upper volume two, Part I introduction is utilized by the content of the inside
Method proposes to remove the case of bending of finger and the state orientation of palm and form sign language frame, and with this 4 byte (32)
Sign language frame is as index, and the corresponding words of gesture, as the content being indexed, the corresponding words of identical gesture is placed on one
Under index, when with the indexed search, the full content of the index will be drawn.Such as：As " you " be with the gesture of " that ", then
Their index is the same, it is assumed that the index is A, will draw " you " during search A, " that ".
Probability database refers to that the frequency of words appearance of single words in corpus, and each word are followed by
There is the set of the frequency of another word；So-called corpus refers to works and expressions for everyday use sentence or article in terms of sign language.For single
The probability of words and a word with living to occur another word is obtained using language model training tool SRILM.And by it
Stored with following form.The probability of the words or words combination, such as " greenery " rope are drawn with words or words synthetic rope
It is 0.000000147332 to draw probability, and probability " 0.000145517086 " is indexed out with " as " " appearance ".Probability database
Index be based on two words, if 2-gram in can not find the two contaminations, 1-gram difference
The single probability of the two words is found, P1 and P2 is set to, then two contamination probability are P=P1*P2*e, e is that nature is normal
Number about 2.71828182845905.
Above is the preferable implementation to the present invention is illustrated, but the invention is not limited to the implementation
Example, those skilled in the art can also make a variety of equivalent variations or replace on the premise of without prejudice to spirit of the invention
Change, these equivalent deformations or replacement are all contained in the application claim limited range.
Claims (7)
1. the fuzzy sign Language Recognition Method of a kind of data glove, it is characterised in that comprise the following steps：
A, acquisition hand motion data simultaneously carry out Fuzzy Processing to it, obtain gesture frame sequence；
B, according to sign language database and probability database, processing is identified to obtained gesture frame sequence, gesture frame sequence is obtained
Row recognition result；
Described step A includes：
A1, each finger obtained in hand motion data angle of bend, and according to default bending membership function, draw
The case of bending of each corresponding finger；
A2, the palm angle of pitch obtained in hand motion data, and calculated according to default pitching membership function, draw
The maximum as corresponding pitch attitude of end value；
A3, the palm inclination angle obtained in hand motion data, and calculated according to default inclination membership function, draw
The maximum as corresponding heeling condition of end value；
A4, the palm yaw angle obtained in hand motion data, and calculated according to default driftage membership function, draw
The maximum as corresponding driftage state of end value；
A5, pitch attitude, heeling condition and the driftage state obtained according to calculating, with reference to default rule, draw corresponding hand
Slap direction；
A6, the case of bending according to palm direction and each finger, draw gesture frame, and and then draw gesture frame sequence；
Bending membership function in described step A1 is：
<mrow>
<msub>
<mi>A</mi>
<mn>0</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mn>1</mn>
<mo>,</mo>
<mi>x</mi>
<mo>&le;</mo>
<mn>35</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>0</mn>
<mo>,</mo>
<mi>x</mi>
<mo>></mo>
<mn>35</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
<mrow>
<msub>
<mi>A</mi>
<mn>2</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mn>1</mn>
<mo>,</mo>
<mi>x</mi>
<mo>&GreaterEqual;</mo>
<mn>85</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>0</mn>
<mo>,</mo>
<mi>x</mi>
<mo><</mo>
<mn>85</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
Wherein, x ∈ U0, U0Represent digital flexion angle, U0=[0,120], in U0On set up three of digital flexion angle and obscure
Collection, A0Represent the state that case of bending is " stretching ", A1Represent state of the case of bending for " half bends ", A2Represent case of bending
For the state of " holding ".
2. a kind of fuzzy sign Language Recognition Method of data glove according to claim 1, it is characterised in that：Described step
B includes：
B1, acquisition gesture frame sequence, gesture frame is extracted according to order from the beginning to the end；
B2, the gesture frame of extraction is sequentially placed into corresponding node respectively；
B3, the corresponding all words of each gesture frame are extracted from sign language database successively, and added into corresponding node
In, until all gesture frames complete the retrieval of sign language database on gesture frame sequence；
B4, by the incidental words of two neighboring node according to node order distinguish combination of two, in combination by upper one knot
The words of point points to the words of next node；
B5, all combine indexed out into the probability of each combination in probability database respectively；
B6, a sentence for finding out probability in the sentence that each group is combined into and maximum, draw gesture frame sequence recognition result.
3. a kind of fuzzy sign Language Recognition Method of data glove according to claim 1, it is characterised in that：Described step
Pitching membership function in A2 is：
<mrow>
<msub>
<mi>B</mi>
<mn>0</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mn>0</mn>
<mo>,</mo>
<mo>-</mo>
<mn>90</mn>
<mo>&le;</mo>
<mi>x</mi>
<mo>&le;</mo>
<mn>40</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mfrac>
<mrow>
<mi>x</mi>
<mo>-</mo>
<mn>40</mn>
</mrow>
<mn>20</mn>
</mfrac>
<mo>,</mo>
<mn>40</mn>
<mo><</mo>
<mi>x</mi>
<mo><</mo>
<mn>60</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>1</mn>
<mo>,</mo>
<mn>60</mn>
<mo>&le;</mo>
<mi>x</mi>
<mo>&le;</mo>
<mn>90</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
<mrow>
<msub>
<mi>B</mi>
<mn>2</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mn>0</mn>
<mo>,</mo>
<mo>-</mo>
<mn>40</mn>
<mo>&le;</mo>
<mi>x</mi>
<mo>&le;</mo>
<mn>90</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mfrac>
<mrow>
<mo>-</mo>
<mn>40</mn>
<mo>-</mo>
<mi>x</mi>
</mrow>
<mn>20</mn>
</mfrac>
<mo>,</mo>
<mo>-</mo>
<mn>60</mn>
<mo><</mo>
<mi>x</mi>
<mo><</mo>
<mo>-</mo>
<mn>40</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>1</mn>
<mo>,</mo>
<mo>-</mo>
<mn>90</mn>
<mo>&le;</mo>
<mi>x</mi>
<mo>&le;</mo>
<mo>-</mo>
<mn>60</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
Wherein, x ∈ U1, U1Represent the palm angle of pitch, U1=[- 90,90], in U1On set up three fuzzy sets of the angle of pitch, B0Table
Show the state that the angle of pitch is " bowing ", B1Represent the state that the angle of pitch is " level ", B2Represent the state that the angle of pitch is " facing upward ".
4. a kind of fuzzy sign Language Recognition Method of data glove according to claim 1, it is characterised in that：Described step
Inclination membership function in A3 is：
Wherein, y ∈ U2, U2Represent palm inclination angle, U2=[- 180,180], in U2On set up three fuzzy sets at inclination angle, C0
Represent the state that inclination angle is " "Left"-deviationist ", C1Represent the state that inclination angle is " level ", C2Represent the shape that inclination angle is " Right deviation "
State, C3Represent the state that inclination angle is " upset level ".
5. a kind of fuzzy sign Language Recognition Method of data glove according to claim 1, it is characterised in that：Described step
Driftage membership function in A4 is：
Wherein, z ∈ U3, U3Represent palm yaw angle, U3=[0,360], in U3On set up three fuzzy sets of yaw angle, D0Represent
Yaw angle is the state of " preceding ", D1Represent the state that yaw angle is " right side ", D2Represent the state that yaw angle is " rear ", D3Represent inclined
Boat angle is the state on " left side ".
6. a kind of fuzzy sign Language Recognition Method of data glove according to claim 1, it is characterised in that：The sign language number
According to storehouse using digital flexion state and palm towards the gesture frame formed as index, the corresponding words of gesture as being indexed in
Hold.
7. a kind of fuzzy sign Language Recognition Method of data glove according to claim 1, it is characterised in that：The probability number
It is to be obtained using language model training tool SRILM according to the probability of the words combination in storehouse.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410655579.5A CN104392237B (en) | 2014-11-17 | 2014-11-17 | Fuzzy sign language identification method for data gloves |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410655579.5A CN104392237B (en) | 2014-11-17 | 2014-11-17 | Fuzzy sign language identification method for data gloves |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104392237A CN104392237A (en) | 2015-03-04 |
| CN104392237B true CN104392237B (en) | 2017-10-10 |
Family
ID=52610138
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410655579.5A Active CN104392237B (en) | 2014-11-17 | 2014-11-17 | Fuzzy sign language identification method for data gloves |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104392237B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2020514841A (en) * | 2017-03-03 | 2020-05-21 | シンバイオシス インターナショナル ユニバーシティーＳｙｍｂｉｏｓｉｓ Ｉｎｔｅｒｎａｔｉｏｎａｌ Ｕｎｉｖｅｒｓｉｔｙ | System and method enabling interactive wearables as an educational aid for the deaf |
| CN109558826B (en) * | 2018-11-23 | 2021-04-20 | 武汉灏存科技有限公司 | Gesture recognition method, system, equipment and storage medium based on fuzzy clustering |
| CN110362195A (en) * | 2019-06-10 | 2019-10-22 | 东南大学 | Gesture identification and interactive system based on bistable state coding and Flexiable angular transducer |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0777186A1 (en) * | 1995-11-28 | 1997-06-04 | Nec Corporation | Language data storage and reproduction apparatus |
| CN102193633A (en) * | 2011-05-25 | 2011-09-21 | 广州畅途软件有限公司 | dynamic sign language recognition method for data glove |
| CN103175502A (en) * | 2013-02-07 | 2013-06-26 | 广州畅途软件有限公司 | Attitude angle detecting method based on low-speed movement of data glove |
| CN103309448A (en) * | 2013-05-31 | 2013-09-18 | 华东师范大学 | Gesture recognition method with symbol sequence matching based on three-dimensional acceleration |
| CN103488287A (en) * | 2013-09-06 | 2014-01-01 | 广州畅途软件有限公司 | Glove-based data input method |
-
2014
- 2014-11-17 CN CN201410655579.5A patent/CN104392237B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0777186A1 (en) * | 1995-11-28 | 1997-06-04 | Nec Corporation | Language data storage and reproduction apparatus |
| CN102193633A (en) * | 2011-05-25 | 2011-09-21 | 广州畅途软件有限公司 | dynamic sign language recognition method for data glove |
| CN103175502A (en) * | 2013-02-07 | 2013-06-26 | 广州畅途软件有限公司 | Attitude angle detecting method based on low-speed movement of data glove |
| CN103309448A (en) * | 2013-05-31 | 2013-09-18 | 华东师范大学 | Gesture recognition method with symbol sequence matching based on three-dimensional acceleration |
| CN103488287A (en) * | 2013-09-06 | 2014-01-01 | 广州畅途软件有限公司 | Glove-based data input method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104392237A (en) | 2015-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110046656B (en) | Multi-mode scene recognition method based on deep learning | |
| Zhang et al. | Chinese sign language recognition with adaptive HMM | |
| CN108764031B (en) | Method, device, computer equipment and storage medium for recognizing human face | |
| CN107730458A (en) | A kind of fuzzy facial reconstruction method and system based on production confrontation network | |
| CN104463250B (en) | A kind of Sign Language Recognition interpretation method based on Davinci technology | |
| CN106295476B (en) | Face key point localization method and device | |
| CN102567716B (en) | Face synthetic system and implementation method | |
| CN110032954A (en) | A kind of reinforcing bar intelligent recognition and method of counting and system | |
| CN110728220A (en) | Gymnastics auxiliary training method based on human body action skeleton information | |
| CN104392237B (en) | Fuzzy sign language identification method for data gloves | |
| CN103186774A (en) | Semi-supervised learning-based multi-gesture facial expression recognition method | |
| WO2023151237A1 (en) | Face pose estimation method and apparatus, electronic device, and storage medium | |
| CN110633004B (en) | Interaction method, device and system based on human body posture estimation | |
| CN111680550B (en) | Emotion information identification method and device, storage medium and computer equipment | |
| WO2017116879A1 (en) | Recognition of hand poses by classification using discrete values | |
| CN104331523B (en) | A kind of question sentence search method based on conceptual object model | |
| CN109558855B (en) | A kind of space gesture recognition methods combined based on palm contour feature with stencil matching method | |
| CN112183198A (en) | Gesture recognition method for fusing body skeleton and head and hand part profiles | |
| CN109299650B (en) | Nonlinear online expression pre-detection method and device based on video | |
| CN116189311B (en) | Protective clothing wears standardized flow monitoring system | |
| CN112347991B (en) | Method for analyzing skiing motion sequence based on hidden Markov | |
| CN108537109B (en) | OpenPose-based monocular camera sign language identification method | |
| CN105354532A (en) | Hand motion frame data based gesture identification method | |
| CN108154156A (en) | Image Ensemble classifier method and device based on neural topic model | |
| CN107909003A (en) | A kind of gesture identification method for large vocabulary |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20190211 Address after: 523808 Room 224, Building D-1, Innovation City, Xincheng Road University, Songshan Lake High-tech Industrial Development Zone, Dongguan City, Guangdong Province Patentee after: DONGGUAN YILIAN INTERATION INFORMATION TECHNOLOGY Co.,Ltd. Address before: 510663 Colorful Frequency Road No. 9, 801C, 801D, Guangzhou High-tech Industrial Development Zone, Guangdong Province Patentee before: GUANGZHOU CHANGTU SOFTWARE Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231011 Address after: Room 2430, building 526, Songhu Park, Dongguan Province Patentee after: DONGGUAN YILIAN INTERATION INFORMATION TECHNOLOGY Co.,Ltd. Patentee after: Fantasy (Zhuhai) Technology Co.,Ltd. Address before: 523808 Room 224, Building D-1, Innovation City, Xincheng Road University, Songshan Lake High-tech Industrial Development Zone, Dongguan City, Guangdong Province Patentee before: DONGGUAN YILIAN INTERATION INFORMATION TECHNOLOGY Co.,Ltd. |