CN108170260A - Gesture identification method and device - Google Patents
Gesture identification method and device Download PDFInfo
- Publication number
- CN108170260A CN108170260A CN201611114402.XA CN201611114402A CN108170260A CN 108170260 A CN108170260 A CN 108170260A CN 201611114402 A CN201611114402 A CN 201611114402A CN 108170260 A CN108170260 A CN 108170260A
- Authority
- CN
- China
- Prior art keywords
- gesture
- image
- gesture image
- generation
- identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
- G06F3/0488—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
- G06F3/04883—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures for inputting data by handwriting, e.g. gesture or text
Abstract
The present invention relates to a kind of gesture identification method and devices.It is handled by the point mark coordinate to touch point, generates first gesture image;The extraction of valid data is carried out to the sensitizing range of first gesture image, generates second gesture image;The second gesture image of generation is copied to the rectangular area center being pre-created;Identification operation performs second gesture image by default Gesture Recognition Algorithm.This method solve in traditional gesture identification, equipment can not realize the problem of independently acquiring various gestures, being accurately identified by various images of gestures, realize the high efficiency and ease for use being identified for different gestures, and with good autgmentability.
Description
Technical field
The present invention relates to image identification technical field, more particularly to a kind of gesture identification method and device.
Background technology
In traditional technology, equipment can not accomplish the identification of gesture, by independently acquiring various gestures, to realize variously-shaped
Gesture identification, which results in equipment to gesture identification have limitation.At the same time, equipment is as hand input by user
The image that gesture generates does not have normalization, without normalized, and leads to the identification to valid data caused by gesture
The low problem of rate, without good applicability.
Invention content
In consideration of it, it is necessary to be directed to traditional technology there are the problem of, provide a kind of gesture identification method and device, can
Realization independently acquire various gestures, realize the operation accurately identified of various images of gestures, have identification high efficiency with it is easy-to-use
Property.
To reach goal of the invention, a kind of gesture identification method is provided, the method includes:It is sat by the point mark to touch point
Mark is handled, and generates first gesture image;The extraction of valid data is carried out to the sensitizing range of the first gesture image, it is raw
Into second gesture image;The second gesture image of generation is copied to the rectangular area center being pre-created;By default
Gesture Recognition Algorithm performs the second gesture image identification operation.
The point mark coordinate by touch point is handled in one of the embodiments, generates first gesture figure
As including:Described mark coordinate of multiple touch points is obtained, and ID labels are performed to multiple touch points;Pass through terminal
The transformational relation of the screen proportion of equipment and images of gestures ratio to be generated generates the first gesture image.
The sensitizing range to the first gesture image carries out carrying for valid data in one of the embodiments,
It takes, generation second gesture image includes:The thickness characteristic parameter of the first gesture image is adjusted, completes to meet default
The operation of normalized image, wherein, the default normalized image is to be normalized into the image of 10*10.
It is described in one of the embodiments, that the second gesture image of generation is copied to the rectangle region being pre-created
Domain center includes:The second gesture image of generation is copied to the rectangular region center being pre-created;Or by generation
The second gesture image copies to the square area center being pre-created.
It is described in one of the embodiments, that identification is performed to the second gesture image by default Gesture Recognition Algorithm
Operation includes:Multiple feature extractions are carried out to the second gesture image;The multiple feature, which is performed, reduces dimension operation, obtains
Principal component data characteristics;Classification and Identification is performed to the principal component data characteristics.
A kind of gesture identifying device based on same inventive concept, described device include:First generation module, for passing through
The point mark coordinate of touch point is handled, generates first gesture image;Second generation module, for the first gesture figure
The sensitizing range of picture carries out the extraction of valid data, generates second gesture image;Replication module, for will generate described second
Images of gestures copies to the rectangular area center being pre-created;Identification module, for by presetting Gesture Recognition Algorithm to described
Second gesture image performs identification operation.
First generation module includes in one of the embodiments,:Acquiring unit, for obtaining multiple touches
Described mark coordinate of point, and ID labels are performed to multiple touch points;Conversion and generation unit, for passing through terminal device
Screen proportion and images of gestures ratio to be generated transformational relation, generate the first gesture image.
Second generation module includes in one of the embodiments,:Adjustment unit, for the first gesture figure
The thickness characteristic parameter of picture is adjusted, and completes the operation for meeting default normalized image, wherein, the default normalized image
To be normalized into the image of 10*10.
The replication module is additionally operable to copy to the second gesture image of generation pre- in one of the embodiments,
The rectangular region center first created;Or the second gesture image of generation is copied in the square area being pre-created
The heart.
The identification module includes in one of the embodiments,:Extraction unit, for the second gesture image into
The multiple feature extractions of row;Dimensionality reduction operating unit reduces dimension operation for being performed to the multiple feature, obtains number of principal components according to spy
Sign;Classification and Identification unit, for performing Classification and Identification to the principal component data characteristics.
A kind of gesture identification method and device provided by the invention.It is handled by the point mark coordinate to touch point, it is raw
Into first gesture image;The extraction of valid data is carried out to the sensitizing range of first gesture figure, generates second gesture image;It will
The second gesture image of generation copies to the rectangular area center being pre-created;By default Gesture Recognition Algorithm to second gesture
Image performs identification operation.Various gestures are independently acquired this method solve in traditional gesture identification, equipment can not be realized, are led to
The problem of various images of gestures are accurately identified is crossed, realizes the high efficiency and ease for use being identified for different gestures,
And with good autgmentability.
Description of the drawings
Fig. 1 is a kind of step flow chart of the method for gesture identification in one embodiment of the invention;
Fig. 2 is a kind of step flow chart of the method for gesture identification in another embodiment of the present invention;
Fig. 3 is a kind of structure diagram of the device of gesture identification in one embodiment of the invention;And
Fig. 4 is a kind of structure diagram of gesture identification volume device in another embodiment of the present invention.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right with reference to the accompanying drawings and embodiments
Gesture identification method and device of the present invention are further elaborated.It should be appreciated that specific embodiment described herein is only
To explain the present invention, it is not intended to limit the present invention.
As shown in Figure 1, the step flow chart for a kind of gesture identification method in one embodiment.Specifically include following step
Suddenly:
Step 102, it is handled by the point mark coordinate to touch point, generates first gesture image.
It in the present embodiment, is handled by the point mark coordinate to touch point, generation first gesture image includes:It obtains more
The point mark coordinate of a touch point, and multiple touch points are performed with ID labels;Screen proportion and hand to be generated by terminal device
The transformational relation of gesture image scaled generates first gesture image.
Step 104, the extraction of valid data is carried out to the sensitizing range of first gesture image, generates second gesture image.
In the present embodiment, the extraction of valid data is carried out to the sensitizing range of first gesture image, generates second gesture figure
As including:The thickness characteristic parameter of first gesture image is adjusted, completes the operation for meeting default normalized image,
In, default normalized image is to be normalized into the image of 10*10.
Step 106, the second gesture image of generation is copied to the rectangular area center being pre-created.
In the present embodiment, the second gesture image of generation is copied to the rectangular area center being pre-created and is included:It will be raw
Into second gesture image copy to the rectangular region center that is pre-created;Or the second gesture image of generation is copied to pre-
The square area center first created.
Step 108, identification operation performs second gesture image by default Gesture Recognition Algorithm.
In the present embodiment, identification operation is performed to second gesture image by default Gesture Recognition Algorithm and is included:To second
Images of gestures carries out multiple feature extractions;Multiple features, which are performed, reduces dimension operation, obtains principal component data characteristics;To principal component
Data characteristics performs Classification and Identification.
In order to be more clearly understood with using gesture identification method proposed by the present invention, carrying out the example below.It needs
Bright, protection scope of the present invention is not limited to the example below.
As shown in Fig. 2, the step flow chart for a kind of gesture identification method in another embodiment.It specifically includes following
Step:
Step 201, the point mark coordinate of multiple touch points is obtained, and multiple touch points are performed with ID labels.
Step 202, pass through the screen proportion of terminal device and the transformational relation of images of gestures ratio to be generated, generation first
Images of gestures.
Step 203, the thickness characteristic parameter of first gesture image is adjusted, completes to meet default normalized image
Operation.Wherein, default normalized image is to be normalized into the image of 10*10.
In the present embodiment, it is adjusted by the thickness characteristic parameter to first gesture image so that image-sensitive region
Prominent acquisition is obtained, in this way beneficial to the more valid data obtained in first gesture image as second gesture image.For example, work as
When the length of side numerical value of first gesture image is≤75 pixel, the line weight characteristic parameter of first gesture image is adjusted to 2;When
When the length of side data of first gesture image are [75-120] pixel, the line weight adjusting parameter of first gesture image is adjusted to
4;When the length of side data of first gesture image are [120-200] pixel, by the line weight adjusting parameter of first gesture image
It is adjusted to 10;When the length of side data of first gesture image are 200 pixels of >, the line weight of first gesture image is adjusted into ginseng
Number is adjusted to 16.
If aforesaid way solves operator when operating gesture amplitude is excessive, equipment is low to the efficiency of gesture identification
Problem.The size of the usability of range that adjustment gesture is inputted in equipment through the above way, is effectively guaranteed to be known
The accounting rate of the valid data of other image.
Step 204, the second gesture image of generation is copied to the rectangular region center being pre-created.
In the present embodiment, it should be noted that the second gesture image of generation can also be copied to and be pre-created just
Square region center.
Step 205, multiple feature extractions are carried out to second gesture image.
Step 206, multiple features are performed reduces dimension operation, obtains principal component data characteristics.
Step 207, Classification and Identification is performed to principal component data characteristics.
A kind of gesture identification method provided by the invention.It is handled by the point mark coordinate to touch point, generation first
Images of gestures;The extraction of valid data is carried out to the sensitizing range of first gesture figure, generates second gesture image;By generation
Second gesture image copies to the rectangular area center being pre-created;Second gesture image is held by default Gesture Recognition Algorithm
Row identification operation.Various gestures are independently acquired this method solve in traditional gesture identification, equipment can not be realized, by various
The problem of images of gestures is accurately identified realizes the high efficiency and ease for use being identified for different gestures, and has
Good autgmentability.
Based on same inventive concept, additionally provide a kind of gesture identifying device, the principle solved the problems, such as due to this device with
A kind of aforementioned gesture identification method is similar, and therefore, the implementation of the device can be realized according to the specific steps of preceding method, repeats
Part repeats no more.
As shown in figure 3, the structure diagram for a kind of gesture identifying device in one embodiment.The gesture identifying device
10 include:First generation module 200, the second generation module 400, replication module 600 and identification module 800.
Wherein, the first generation module 200 generates first gesture figure for being handled by the point mark coordinate to touch point
Picture;Second generation module 400 is used to carry out the sensitizing range of first gesture image the extraction of valid data, generates second gesture
Image;Replication module 600 is used to copying to the second gesture image of generation into the rectangular area center being pre-created;Identification module
800 are used to perform second gesture image identification operation by default Gesture Recognition Algorithm.
In the present embodiment, as shown in figure 4, the first generation module 200 includes:Acquiring unit 210, for obtaining multiple touches
The point mark coordinate of point, and multiple touch points are performed with ID labels;Conversion and generation unit 220, for passing through the screen of terminal device
The transformational relation of curtain ratio and images of gestures ratio to be generated generates first gesture image.
Further, as shown in figure 4, the second generation module 400 includes:Adjustment unit 410 is used for first gesture image
Thickness characteristic parameter be adjusted, complete the operation for meeting default normalized image, wherein, it is normalizing to preset normalized image
It is melted into the image of 10*10.
Further, as shown in figure 4, identification module 800 includes:Extraction unit 810 be used for second gesture image into
The multiple feature extractions of row;Dimensionality reduction operating unit 820, which is used to perform multiple features, reduces dimension operation, obtains number of principal components according to spy
Sign;Classification and Identification unit 830 is used to perform Classification and Identification to principal component data characteristics.
In addition it is also necessary to explanation, replication module 600 are additionally operable to the second gesture image of generation copying to advance wound
The rectangular region center built;Or the second gesture image of generation is copied to the square area center being pre-created.
A kind of gesture identifying device provided by the invention.It is sat by the first generation module 200 by the point mark to touch point
Mark is handled, and generates first gesture image;The sensitizing range of first gesture figure is carried out by the second generation module 400 again
The extraction of valid data generates second gesture image;Then the second gesture image of generation is copied to by replication module 600
The rectangular area center being pre-created;Eventually by identification module 800 by default Gesture Recognition Algorithm to second gesture image
Perform identification operation.Various gestures are independently acquired which solves in traditional gesture identification, equipment can not be realized, by each
The problem of kind images of gestures is accurately identified realizes the high efficiency and ease for use being identified for different gestures, and has
There is good autgmentability
One of ordinary skill in the art will appreciate that realizing all or part of flow in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer read/write memory medium
In, the program is when being executed, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
Each technical characteristic of embodiment described above can be combined arbitrarily, to make description succinct, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, it is all considered to be the range of this specification record.
Embodiment described above only expresses the several embodiments of the present invention, and description is more specific and detailed, but simultaneously
Cannot the limitation to the scope of the claims of the present invention therefore be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the guarantor of the present invention
Protect range.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. a kind of gesture identification method, which is characterized in that the method includes:
It is handled by the point mark coordinate to touch point, generates first gesture image;
The extraction of valid data is carried out to the sensitizing range of the first gesture image, generates second gesture image;
The second gesture image of generation is copied to the rectangular area center being pre-created;
Identification operation performs the second gesture image by default Gesture Recognition Algorithm.
2. gesture identification method according to claim 1, which is characterized in that the point mark coordinate by touch point into
Row processing, generation first gesture image include:
Described mark coordinate of multiple touch points is obtained, and ID labels are performed to multiple touch points;
By the screen proportion of terminal device and the transformational relation of images of gestures ratio to be generated, the first gesture figure is generated
Picture.
3. gesture identification method according to claim 1, which is characterized in that the sensitivity to the first gesture image
Region carries out the extraction of valid data, and generation second gesture image includes:
The thickness characteristic parameter of the first gesture image is adjusted, completes the operation for meeting default normalized image,
In, the default normalized image is to be normalized into the image of 10*10.
4. gesture identification method according to claim 1, which is characterized in that the second gesture image by generation
The rectangular area center being pre-created is copied to include:The second gesture image of generation is copied to be pre-created it is rectangular
Shape regional center;Or
The second gesture image of generation is copied to the square area center being pre-created.
5. gesture identification method according to claim 1, which is characterized in that described by presetting Gesture Recognition Algorithm to institute
It states second gesture image and performs identification and operate and include:
Multiple feature extractions are carried out to the second gesture image;
The multiple feature, which is performed, reduces dimension operation, obtains principal component data characteristics;
Classification and Identification is performed to the principal component data characteristics.
6. a kind of gesture identifying device, which is characterized in that described device includes:
First generation module for being handled by the point mark coordinate to touch point, generates first gesture image;
Second generation module, for carrying out the extraction of valid data, generation second to the sensitizing range of the first gesture image
Images of gestures;
Replication module, for the second gesture image generated to be copied to the rectangular area center being pre-created;
Identification module, for performing identification operation to the second gesture image by default Gesture Recognition Algorithm.
7. gesture identifying device according to claim 6, which is characterized in that first generation module includes:
Acquiring unit for obtaining described mark coordinate of multiple touch points, and performs ID marks to multiple touch points
Note;
Conversion and generation unit, for passing through the transformational relation of the screen proportion of terminal device and images of gestures ratio to be generated,
Generate the first gesture image.
8. gesture identifying device according to claim 6, which is characterized in that second generation module includes:
Adjustment unit is adjusted for the thickness characteristic parameter to the first gesture image, completes to meet default normalization
The operation of image, wherein, the default normalized image is to be normalized into the image of 10*10.
9. gesture identifying device according to claim 6, which is characterized in that the replication module is additionally operable to the institute of generation
It states second gesture image and copies to the rectangular region center being pre-created;Or the second gesture image of generation is copied to
The square area center being pre-created.
10. gesture identifying device according to claim 6, which is characterized in that the identification module includes:
Extraction unit, for carrying out multiple feature extractions to the second gesture image;
Dimensionality reduction operating unit reduces dimension operation for being performed to the multiple feature, obtains principal component data characteristics;
Classification and Identification unit, for performing Classification and Identification to the principal component data characteristics.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611114402.XA CN108170260A (en) | 2016-12-07 | 2016-12-07 | Gesture identification method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611114402.XA CN108170260A (en) | 2016-12-07 | 2016-12-07 | Gesture identification method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108170260A true CN108170260A (en) | 2018-06-15 |
Family
ID=62526403
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611114402.XA Pending CN108170260A (en) | 2016-12-07 | 2016-12-07 | Gesture identification method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108170260A (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080224836A1 (en) * | 2007-03-15 | 2008-09-18 | Carl Anthony Pickering | Security system for a motor vehicle |
CN106371614A (en) * | 2016-11-24 | 2017-02-01 | 朱兰英 | Gesture recognition optimizing method and device |
-
2016
- 2016-12-07 CN CN201611114402.XA patent/CN108170260A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080224836A1 (en) * | 2007-03-15 | 2008-09-18 | Carl Anthony Pickering | Security system for a motor vehicle |
CN106371614A (en) * | 2016-11-24 | 2017-02-01 | 朱兰英 | Gesture recognition optimizing method and device |
Non-Patent Citations (1)
Title |
---|
赵亚飞: "基于视觉的手势识别技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2945374B1 (en) | Positioning of projected augmented reality content | |
DE112011105171B4 (en) | Block user content based on location | |
US9082039B2 (en) | Method and apparatus for recognizing a character based on a photographed image | |
CN106485164A (en) | A kind of image processing method and mobile terminal | |
CN104598933A (en) | Multi-feature fusion based image copying detection method | |
CN105843516B (en) | It is a kind of for showing the method and device of information in original list rolling process | |
CN108647351A (en) | Processing method, device, storage medium and the terminal of text image | |
CN104902143A (en) | Resolution-ratio-based image de-noising method and device | |
CN106371614A (en) | Gesture recognition optimizing method and device | |
CN107103312A (en) | A kind of image processing method and device | |
US8130419B2 (en) | Embedding authentication data to create a secure identity document using combined identity-linked images | |
CN110867243B (en) | Image annotation method, device, computer system and readable storage medium | |
CN109241962A (en) | A kind of character identifying method and device | |
CN107886518A (en) | Picture detection method, device, electronic equipment and read/write memory medium | |
CN104216882B (en) | File mask method and device | |
TWI490818B (en) | Method and system for weighted image enhancement | |
CN108170260A (en) | Gesture identification method and device | |
CN104408736A (en) | Characteristic-similarity-based synthetic face image quality evaluation method | |
CN110705653A (en) | Image classification method, image classification device and terminal equipment | |
CN112633183B (en) | Automatic detection method and device for image shielding area and storage medium | |
WO2017041588A1 (en) | Eraser box range determination method and system | |
US20190377941A1 (en) | Character recognition apparatus and character recognition method | |
US20160124624A1 (en) | Electronic device and web page resizing method | |
Tiwari et al. | Performance improvement of image enhancement methods using statistical moving average histogram modification filter | |
CA2899139C (en) | Method and system for creating optimized images for data identification and extraction |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180615 |