CN106708317A - Method and apparatus for judging touch point - Google Patents
Method and apparatus for judging touch point Download PDFInfo
- Publication number
- CN106708317A CN106708317A CN201611113912.5A CN201611113912A CN106708317A CN 106708317 A CN106708317 A CN 106708317A CN 201611113912 A CN201611113912 A CN 201611113912A CN 106708317 A CN106708317 A CN 106708317A
- Authority
- CN
- China
- Prior art keywords
- touch point
- training
- data
- area
- screen
- 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.)
- Withdrawn
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
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/041—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
- G06F3/0416—Control or interface arrangements specially adapted for digitisers
- G06F3/0418—Control or interface arrangements specially adapted for digitisers for error correction or compensation, e.g. based on parallax, calibration or alignment
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a method and an apparatus for judging a touch point. The method comprises the steps of performing calibration operation on a device; performing data acquisition, stopping acquisition when it is judged that acquired data covers a screen of the device in a preset threshold, and defining the data acquired at the moment as training data; performing stipulating and cleaning operations on the training data, and generating a training sample; selecting a one-class classifier, defining an input, an output and a kernel function, performing value assignment and training on a parameter of the kernel function, and generating a classifier; classifying touch points, obtained by the device through the screen, by the generated classifier to generate a classification result; and finishing the judgment of the touch points through the classification result. According to the method, the problem of insufficiently accurate judgment on the touch points in a conventional technology is solved and the operation of effectively identifying noisy points in the touch points or the effective touch points is realized; and the method has relatively high accuracy, flexibility and usability.
Description
Technical field
The present invention relates to touch control device detection technique field, more particularly to a kind of method and apparatus for judging touch point.
Background technology
It is well known that can be in touch-control interactive mode large screen system, touch point be identified as key problem.It is wherein most simple
Method be that fixed area, perimeter threshold is set, the hot spot of all positions in photo is taken the photograph to camera all by the threshold value
To differentiate, in the range of is effective touch point, otherwise invalid.But in actual use, this mode can be by many noise bags
Include wherein, such as strip noise.More seriously, by light that near big and far smaller problem caused by camera is near apart from camera
Spot shows bigger in photo；What the lasing area got by laser had that the near hot spot of distance lasers shows greatly asks
Topic.Under the influence of both factors, following situation becomes urgently to be resolved hurrily：Be difficult to determine one group of fixation suitable for the whole circumstances
Threshold value；Determining for the suitable threshold value of a certain particular system, you can include minimum light spot in photo with maximum hot spot
After threshold value tight wherein and enough, some apart from camera farther out, its noise meeting that position caustic surface is weaker but area is larger
Become to be difficult to differentiate.
The content of the invention
In consideration of it, being necessary the problem existed for conventional art, there is provided a kind of method and apparatus of judgement touch point,
The operation of effective identification of noise or effective touch point can be realized, and with accuracy higher, flexibility and ease for use.
To reach goal of the invention, there is provided a kind of method of judgement touch point, methods described includes：Calibration behaviour is carried out to equipment
Make, wherein, the equipment is can touch control device；The collection of data is carried out, judges to be covered in predetermined threshold value when the data of collection
During the screen of the equipment, stop collection, and the data definition that will now gather is training data, wherein, the screen is
The building block of the equipment, for receiving user's operation behavior；Stipulations and cleaning operation are carried out with data to the training, it is raw
Into training sample；Selection one-class classifier, is defined to input, output and kernel function, and to the parameter of the kernel function
Carry out assignment and perform training, generate grader；The grader of generation is to the equipment by touching that the screen is obtained
Control point is classified, and generates classification results；By the classification results, the judgement to the touch point is completed.
Wherein in one embodiment, the data definition that will now gather be training data the step of after wrap
Include：The training is obtained with multiple characteristic parameters of data, wherein, the multiple characteristic parameter includes the touch point
The transverse and longitudinal coordinate position of the hot spot of formation, area and axial length long.
Wherein in one embodiment, the judgement covers the screen of the equipment when the data of collection in predetermined threshold value
When, stopping collection including：Judge whether the training data are reduced with transverse and longitudinal coordinate and covering entirely for the screen is met after 4 times
Lid；If meeting, it is determined that all standing that training data complete the screen is operated.
It is described to carry out stipulations and cleaning operation, generation training sample with data to the training wherein in one embodiment
Originally include：For transverse and longitudinal coordinate position described in the touch point identical, the maximum of area and axial length long is chosen, and to area
Whether it is zero to be judged；If area is zero, presently described training data are deleted, otherwise, by (4x+1,4y+1,2*
Area, 50*axis) stored；Assignment adjustment is carried out to alpha again, will (4x+1,4y+1,2*alpha*alpha*area,
50*alpha*axis) stored, generated the training sample；Wherein, x is touch point abscissa in the picture, y
It is touch point ordinate in the picture, area is the touch point shared pixel sum in the picture, is defined as face
Product, axis is the axial length polygonal long that the touch point is formed, and alpha is the adjustment touch point sampling parameters, alpha value
It is all numerical value between 0-1.
It is described by the classification results wherein in one embodiment, complete to include the judgement of the touch point；When
When the classification results are 0, then judge that the touch point is noise；When the classification results are 1, then the touch point is judged
It is effective touch point.
A kind of device of the judgement touch point based on same inventive concept, described device includes：Calibration module, sets for Dui
It is standby to carry out calibration operation, wherein, the equipment is can touch control device；Training data acquisition module, for carrying out adopting for data
Collection, judges, when the data of collection cover the screen of the equipment in predetermined threshold value, to stop collection, and the number that will now gather
According to being defined as training data, wherein, the screen is the building block of the equipment, for receiving user's operation behavior；Instruction
Practice sample generation module, for carrying out stipulations and cleaning operation with data to the training, generate training sample；Grader is generated
Module, for selecting one-class classifier, is defined to input, output and kernel function, and parameter to the kernel function is entered
Row assignment with performs training, generation grader；Sort module, the grader for generating is obtained to the screen of the equipment
Touch point classified, generate classification results；Touch point judge module, for by the classification results, completing to described
The judgement of touch point.
Wherein in one embodiment, the training is included with data generation module：Extraction unit, for the training
Obtained with multiple characteristic parameters of data, wherein, the multiple characteristic parameter includes the hot spot that the touch point is formed
Transverse and longitudinal coordinate position, area and axial length long.
Wherein in one embodiment, the training data generation module also includes：Judging unit, it is described for judging
Whether training data reduce all standing that screen is met after 4 times with transverse and longitudinal coordinate；Determining unit, if for meeting, really
The all standing that fixed training data complete screen is operated.
Wherein in one embodiment, the training sample generation module includes：Choose and identifying unit, for for institute
Transverse and longitudinal coordinate position described in touch point identical is stated, the maximum of area and axial length long is chosen；Execution unit, if being for area
When zero, then presently described training data are deleted, otherwise, (4x+1,4y+1,2*area, 50*axis) is stored；Assignment
Adjustment unit, for carrying out assignment adjustment to alpha, by (4x+1,4y+1,2*alpha*alpha*area, 50*alpha*
Axis) stored, generated the training sample；Wherein, x is touch point abscissa in the picture, and y is the touch-control
Point ordinate in the picture, area is the touch point shared pixel sum in the picture, is defined as area, and axis is institute
The axial length polygonal long of touch point formation is stated, alpha is the adjustment touch point sampling parameters, and alpha value is between 0-1
All numerical value.
Wherein in one embodiment, the touch point judge module includes；Noise determining unit, for when the classification
When result is 0, then judge that the touch point is noise；Effective touch point determining unit, for when the classification results are 1,
Then judge that the touch point is effective touch point.
A kind of method and apparatus of judgement touch point that the present invention is provided.Calibration operation is carried out to equipment, wherein, equipment is
Can touch control device；The collection of data is carried out, judges, when data screen of overlay device in predetermined threshold value of collection, to stop adopting
Collection, and the data definition that will now gather is training data, wherein, screen is the building block of equipment, for receiving user
Operation behavior；Stipulations and cleaning operation are carried out with data to training, training sample is generated；Selection one-class classifier, to input, it is defeated
Go out and kernel function is defined, and assignment is carried out to the parameter of kernel function and performs training, generation grader；The classification of generation
Device is classified to equipment by the touch point that screen is obtained, and generates classification results；By classification results, complete to touch point
Judge.The not accurate enough problem judged touch point in conventional art is this method solve, is realized in touch point
Noise or effective touch point effective identification operation, and with accuracy higher, flexibility and ease for use.
Brief description of the drawings
The step of Fig. 1 is a kind of method of the judgement touch point in one embodiment of the invention flow chart；
The step of Fig. 2 is a kind of method of the judgement touch point in another embodiment of the present invention flow chart；
Fig. 3 is a kind of structural representation of the device of the judgement touch point in one embodiment of the invention；And
Fig. 4 is a kind of structural representation of the device of the judgement touch point 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, below in conjunction with drawings and Examples pair
The present invention judges that the method and apparatus of touch point are further elaborated.It should be appreciated that specific implementation described herein
Example is only used to explain the present invention, is not intended to limit the present invention.
As shown in figure 1, a kind of the step of method of judgement touch point in for one embodiment flow chart.Specifically include with
Lower step：
Step 101, calibration operation is carried out to equipment, wherein, equipment is can touch control device.
Step 102, carries out the collection of data, judges when data screen of overlay device in predetermined threshold value of collection,
Stop collection, and the data definition that will now gather is training data, wherein, screen is the building block of equipment, for connecing
Receive user's operation behavior.
In the present embodiment, the data definition that will now gather be training data the step of after include：To training number
According to multiple characteristic parameters obtained, wherein, multiple characteristic parameters include touch point formed hot spot transverse and longitudinal coordinate position,
Area and axial length long.
Further, judge that, when data screen of overlay device in predetermined threshold value of collection, stopping collection including：Sentence
Whether disconnected training data reduce all standing that screen is met after 4 times with transverse and longitudinal coordinate；If meeting, it is determined that training data
Complete all standing operation of screen.
Step 103, stipulations and cleaning operation are carried out to training with data, generate training sample.
In the present embodiment, stipulations and cleaning operation are carried out with data to training, generation training sample includes：For touch point
Whether identical transverse and longitudinal coordinate position, chooses the maximum of area and axial length long, and be zero to judge to area；If area is
When zero, then current training data are deleted, otherwise, (4x+1,4y+1,2*area, 50*axis) is stored；Again to alpha
Assignment adjustment is carried out, (4x+1,4y+1,2*alpha*alpha*area, 50*alpha*axis) is stored, generation training
Sample.
Wherein, x is touch point abscissa in the picture, and y is touch point ordinate in the picture, and area is touch point
Shared pixel sum, is defined as area in the picture, and axis is the axial length polygonal long that touch point is formed, and alpha is tune
Whole touch point sampling parameters, alpha value is all numerical value between 0-1.
Step 104, selects one-class classifier, and input, output and kernel function are defined, and to the parameter of kernel function
Carry out assignment and perform training, generate grader.
Step 105, the grader of generation is classified to the touch point that the screen of equipment is obtained, and generates classification results.
Step 106, by classification results, completes the judgement to touch point.
In the present embodiment, by classification results, complete to include the judgement of touch point；When classification results are 0, then judge
Touch point is noise；When classification results are 1, then judge that touch point is effective touch point.
For the method for clearer understanding judgement touch point proposed by the present invention with application, the example below is carried out.Need
Illustrate, protection scope of the present invention does not limit to the example below.
As shown in Fig. 2 a kind of the step of method of judgement touch point in for another embodiment flow chart.Specifically include
Following steps：
Step 201, calibration operation is carried out to equipment.
, it is necessary to explanation, disposable to complete the whole of training data during except being calibrated to equipment in the present embodiment
Outside body acquisition operations, the acquisition operations of training data can also be in actual use completed.
Step 202, user's any stroke on screen obtains different touch points as training data, and obtain not
With the information of touch point.
In the present embodiment, the position of hot spot that is formed to each touch point, area, major axis is long is obtained and stored, structure
Into a four dimensional vector w=(x, y, area, axis).Wherein x, y are spot center transverse and longitudinal coordinate in the picture；Area is
Hot spot shared pixel, i.e. area in the picture；Axis polygonal axial lengths long for hot spot is formed.It should be noted that storage
When 4 are set to the transverse and longitudinal coordinate mould of each touch point.
Step 203, whether after user finishes to touch point collection, checking the data of the touch point of above-mentioned collection can cover
Transverse and longitudinal coordinate reduces 4 times of screen, if can not cover, points out user to continue executing with touch control operation in unlapped position,
Untill being completely covered.
Step 204, stipulations and cleaning operation are carried out to training with data, generate training sample.
It should be noted that the touch point same for transverse and longitudinal coordinate, takes the area and major axis long value of maximum, and judge face
Whether product is zero.This data is deleted if area area=0, otherwise (4x+1,4y+1,2*area, 50*axis) is stored in
Enter the sample set after cleaning；Alpha=0.8 is made again, by (4x+1,4y+1,2*alpha*alpha*area, 50*alpha*
Axis) sample set that storage enters after cleaning, obtains final training sample.Wherein, x is touch point horizontal seat in the picture
Mark, y is touch point ordinate in the picture, and area is touch point shared pixel sum in the picture, is defined as area,
Axis is the axial length polygonal long that touch point is formed, and alpha is adjustment touch point sampling parameters, and alpha value is between 0-1
All numerical value.
Step 205, select one-class classifier, using obtain four dimensional vector sample sets as input, effective touch point conduct
Output, the default kernel function of selection, and parameter to presetting kernel function carry out assignment and perform training, generation grader.
In the present embodiment, default kernel function includes but is not limited to RBF, mapping function.To the kernel function chosen
Parameter carries out assignment, for example, gamma=0.0002, nu=0.001, then perform and are trained, the classification for being trained
Device, then stored.
Step 206, the grader for training is classified to the touch point that the screen of equipment is obtained, and generates classification results,
And by classification results, complete the judgement to touch point.
In the present embodiment, for it is actually used when touch point, the test set for grader can be regarded as, if classification
Result is 0, then be considered as noise, if classification results are 1, is considered as effective touch point.By aforesaid operations, effective differentiation has been reached
The purpose of touch point.
A kind of method of judgement touch point that the present invention is provided.Calibration operation is carried out to equipment, wherein, equipment is can touch-control
Equipment；The collection of data is carried out, judges, when data screen of overlay device in predetermined threshold value of collection, to stop collection, and
The data definition that will now gather is training data, wherein, screen is the building block of equipment, for receiving user's operation row
For；Stipulations and cleaning operation are carried out with data to training, training sample is generated；Selection one-class classifier, to input, output and
Kernel function is defined, and assignment is carried out to the parameter of kernel function and performs training, generation grader；The grader pair of generation sets
The standby touch point obtained by screen is classified, and generates classification results；By classification results, the judgement to touch point is completed.
The not accurate enough problem judged touch point in conventional art is this method solve, is realized to the noise in touch point
Or the effectively operation of effective identification of touch point, and with accuracy higher, flexibility and ease for use.
Based on same inventive concept, a kind of device for judging touch point is additionally provided, due to the original of this device solve problem
Manage similar to a kind of foregoing method for judging touch point, therefore, the implementation of the device can be according to the specific steps of preceding method
Realize, repeat part and repeat no more.
As shown in figure 3, a kind of structural representation of the device of judgement touch point in for one embodiment.The judgement touch-control
The device 10 of point includes：Calibration module 100, training data acquisition module 200, training sample generation module 300, grader are given birth to
Into module 400, sort module 500 and touch point judge module 600.
Wherein, calibration module 100 is used to carry out calibration operation to equipment, wherein, equipment is can touch control device；Training number
It is used to carry out the collection of data according to acquisition module 200, judges when data screen of overlay device in predetermined threshold value of collection,
Stop collection, and the data definition that will now gather is training data, wherein, screen is the building block of equipment, for connecing
Receive user's operation behavior；Training sample generation module 300 is used to carry out training with data stipulations and cleaning operation, generation training
Sample；Grader generation module 400 is used to select one-class classifier, and input, output and kernel function are defined, and to core
The parameter of function carries out assignment and performs training, generates grader；Sort module 500 is used for the screen of the grader to equipment of generation
The touch point that curtain is obtained is classified, and generates classification results；Touch point judge module 600 is used for by classification results, and it is right to complete
The judgement of touch point.
In the present embodiment, as shown in figure 4, training data acquisition module 200 includes：Extraction unit 210 is used for training
Obtained with multiple characteristic parameters of data, wherein, multiple characteristic parameters include the transverse and longitudinal coordinate of the hot spot that touch point is formed
Position, area and axial length long；Whether judging unit 220 meets after reducing 4 times with transverse and longitudinal coordinate for training of judgement data
The all standing of screen；If determining unit 230 is used to meet, it is determined that all standing that training data complete screen is operated.
Further, as shown in figure 4, training sample generation module 300 includes：Choose with identifying unit 310 be used for for
Touch point identical transverse and longitudinal coordinate position, chooses the maximum of area and axial length long；If execution unit 320 is zero for area
When, then current training data are deleted, otherwise, (4x+1,4y+1,2*area, 50*axis) is stored；Assignment adjustment is single
Unit 330 is used to carry out assignment adjustment to alpha, and (4x+1,4y+1,2*alpha*alpha*area, 50*alpha*axis) is entered
Row storage, generates training sample.Wherein, x is touch point abscissa in the picture, and y is touch point ordinate in the picture,
Area is touch point shared pixel sum in the picture, is defined as area, and axis is the polygonal major axis that touch point is formed
Long, alpha is adjustment touch point sampling parameters, and alpha value is all numerical value between 0-1.
Further, as shown in figure 4, touch point judge module 600 includes：Noise determining unit 610 is used for when classification
When result is 0, then judge that touch point is noise；Effective touch point determining unit 620 is used to when classification results are 1, then judge
Touch point is effective touch point.
A kind of device of judgement touch point that the present invention is provided.Calibration operation is carried out to equipment by calibration module 100, its
In, equipment is can touch control device；Carry out the collection of data with data acquisition module 200 by training again, judge when the number of collection
According to the overlay device in predetermined threshold value screen when, stop collection, and the data definition that will now gather is training data, its
In, screen is the building block of equipment, for receiving user's operation behavior；Again by the 300 pairs of training of training sample generation module
Stipulations and cleaning operation are carried out with data, training sample is generated；One-class classifier is selected by grader generation module 400, it is right
Input, output and kernel function are defined, and assignment are carried out to the parameter of kernel function and performs training, generation grader；After
And pass through the grader that sort module 500 generates and the touch point that the screen of equipment is obtained is classified, generate classification results；Most
The judgement to touch point is completed by classification results by touch point judge module 600 eventually.Which solves in conventional art
The not accurate enough problem judged touch point, realizes the effective knowledge to the noise in touch point or effective touch point
Other operation, and with accuracy higher, flexibility and ease for use.
One of ordinary skill in the art will appreciate that all or part of flow in realizing above-described embodiment method, can be
The hardware of correlation is instructed to complete by computer program, described program can be stored in a computer read/write memory medium
In, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, described 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
Apply 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, the scope of this specification record is all considered to be.
Embodiment described above only expresses several embodiments of the invention, and its description is more specific and detailed, but simultaneously
Therefore the limitation to the scope of the claims of the present invention can not be interpreted as.It should be pointed out that for one 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 guarantor of the invention
Shield scope.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. it is a kind of judge touch point method, it is characterised in that methods described includes：
Calibration operation is carried out to equipment, wherein, the equipment is can touch control device；
The collection of data is carried out, judges, when the data of collection cover the screen of the equipment in predetermined threshold value, to stop collection,
And the data definition that will now gather is training data, wherein, the screen is the building block of the equipment, for receiving
User's operation behavior；
Stipulations and cleaning operation are carried out with data to the training, training sample is generated；
Selection one-class classifier, is defined to input, output and kernel function, and parameter to the kernel function carries out assignment
With perform training, generate grader；
The grader of generation is classified to the equipment by the touch point that the screen is obtained, and generates classification results；
By the classification results, the judgement to the touch point is completed.
2. judgement touch-control point methods according to claim 1, it is characterised in that the data definition that will now gather is
Include after the step of training data：
The training is obtained with multiple characteristic parameters of data, wherein, the multiple characteristic parameter includes the touch-control
Put transverse and longitudinal coordinate position, area and the axial length long of the hot spot for being formed.
3. it is according to claim 1 judge touch point method, it is characterised in that the judgement when collection data pre-
If in threshold value during the screen of the covering equipment, stopping collection including：
Judge whether the training data reduce all standing that the screen is met after 4 times with transverse and longitudinal coordinate；
If meeting, it is determined that all standing that training data complete the screen is operated.
4. it is according to claim 1 and 2 judge touch point method, it is characterised in that it is described to the training data
Stipulations and cleaning operation are carried out, generation training sample includes：
For transverse and longitudinal coordinate position described in the touch point identical, the maximum of area and axial length long is chosen, and be to area
No is zero to be judged；
If area is zero, presently described training data are deleted, otherwise, by (4x+1,4y+1,2 × area, 50 × axis)
Stored；
Assignment adjustment is carried out to alpha again, by (4x+1,4y+1,2 × alpha × alpha × area, 50 × alpha × axis)
Stored, generated the training sample；
Wherein, x is touch point abscissa in the picture, and y is touch point ordinate in the picture, and area is institute
Touch point shared pixel sum in the picture is stated, area is defined as, axis is the polygonal major axis that the touch point is formed
Long, alpha is the adjustment touch point sampling parameters, and alpha value is all numerical value between 0-1.
5. it is according to claim 1 judge touch point method, it is characterised in that it is described by the classification results, it is complete
The judgement of the paired touch point includes；
When the classification results are 0, then judge that the touch point is noise；
When the classification results are 1, then judge that the touch point is effective touch point.
6. it is a kind of judge touch point device, it is characterised in that described device includes：
Calibration module, for carrying out calibration operation to equipment, wherein, the equipment is can touch control device；
Training data acquisition module, the collection for carrying out data judges to cover institute in predetermined threshold value when the data of collection
When stating the screen of equipment, stop collection, and the data definition that will now gather is training data, wherein, the screen is institute
The building block of equipment is stated, for receiving user's operation behavior；
Training sample generation module, for carrying out stipulations and cleaning operation with data to the training, generates training sample；
Grader generation module, for selecting one-class classifier, is defined to input, output and kernel function, and to described
The parameter of kernel function carries out assignment and performs training, generates grader；
Sort module, the grader for generating is classified to the touch point that the screen of the equipment is obtained, generation point
Class result；
Touch point judge module, for by the classification results, completing the judgement to the touch point.
7. it is according to claim 6 to judge touch point device, it is characterised in that training data acquisition module bag
Include：
Extraction unit, for being obtained with multiple characteristic parameters of data to the training, wherein, the multiple characteristic parameter
The transverse and longitudinal coordinate position of hot spot, area and the axial length long formed including the touch point.
8. it is according to claim 6 judge touch point device, it is characterised in that training data acquisition module is also
Including：
Judging unit, for judging whether the training data reduce all standing that screen is met after 4 times with transverse and longitudinal coordinate；
Determining unit, if for meeting, it is determined that all standing that training data complete screen is operated.
9. the device for judging touch point according to claim 6 or 7, it is characterised in that the training sample generation module
Including：
Choose and identifying unit, for for transverse and longitudinal coordinate position described in the touch point identical, choosing area and axial length long
Maximum；
Execution unit, if be zero for area, deletes presently described training data, otherwise, will (4x+1,4y+1,2 ×
Area, 50 × axis) stored；
Assignment adjustment unit, for carrying out assignment adjustment to alpha, will (4x+1,4y+1,2 × alpha × alpha × area,
50 × alpha × axis) stored, generate the training sample；
Wherein, x is touch point abscissa in the picture, and y is touch point ordinate in the picture, and area is institute
Touch point shared pixel sum in the picture is stated, area is defined as, axis is the polygonal major axis that the touch point is formed
Long, alpha is the adjustment touch point sampling parameters, and alpha value is all numerical value between 0-1.
10. it is according to claim 6 judge touch point device, it is characterised in that the touch point judge module includes；
Noise determining unit, for when the classification results are 0, then judging that the touch point is noise；
Effective touch point determining unit, for when the classification results are 1, then judging that the touch point is effective touch point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611113912.5A CN106708317A (en) | 2016-12-07 | 2016-12-07 | Method and apparatus for judging touch point |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611113912.5A CN106708317A (en) | 2016-12-07 | 2016-12-07 | Method and apparatus for judging touch point |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106708317A true CN106708317A (en) | 2017-05-24 |
Family
ID=58936090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611113912.5A Withdrawn CN106708317A (en) | 2016-12-07 | 2016-12-07 | Method and apparatus for judging touch point |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106708317A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107894865A (en) * | 2017-11-28 | 2018-04-10 | 山东衡昊信息技术有限公司 | It is a kind of based on the icon fringe region dynamic fixing method for following optimization |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521611A (en) * | 2011-12-13 | 2012-06-27 | 广东威创视讯科技股份有限公司 | Touched object identification method based on touch screen |
| CN104160364A (en) * | 2011-10-18 | 2014-11-19 | 卡内基梅隆大学 | Method and apparatus for classifying touch events on a touch sensitive surface |
| CN104350728A (en) * | 2012-04-13 | 2015-02-11 | 诺基亚公司 | Operation control on multi-segment wearable accessory based on segment orientation change |
| CN104715170A (en) * | 2013-12-13 | 2015-06-17 | 中国移动通信集团公司 | Operating authorization determining method and user terminal |
| CN104765995A (en) * | 2015-04-24 | 2015-07-08 | 福建师范大学 | Intelligent device identity authentication method and client side based on touch screen operation |
| WO2016007450A1 (en) * | 2014-07-11 | 2016-01-14 | Microsoft Technology Licensing, Llc | Touch classification |
| CN106778805A (en) * | 2016-11-23 | 2017-05-31 | 朱兰英 | Touch point sorting technique and device based on device screen |
-
2016
- 2016-12-07 CN CN201611113912.5A patent/CN106708317A/en not_active Withdrawn
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104160364A (en) * | 2011-10-18 | 2014-11-19 | 卡内基梅隆大学 | Method and apparatus for classifying touch events on a touch sensitive surface |
| CN102521611A (en) * | 2011-12-13 | 2012-06-27 | 广东威创视讯科技股份有限公司 | Touched object identification method based on touch screen |
| CN104350728A (en) * | 2012-04-13 | 2015-02-11 | 诺基亚公司 | Operation control on multi-segment wearable accessory based on segment orientation change |
| CN104715170A (en) * | 2013-12-13 | 2015-06-17 | 中国移动通信集团公司 | Operating authorization determining method and user terminal |
| WO2016007450A1 (en) * | 2014-07-11 | 2016-01-14 | Microsoft Technology Licensing, Llc | Touch classification |
| CN104765995A (en) * | 2015-04-24 | 2015-07-08 | 福建师范大学 | Intelligent device identity authentication method and client side based on touch screen operation |
| CN106778805A (en) * | 2016-11-23 | 2017-05-31 | 朱兰英 | Touch point sorting technique and device based on device screen |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107894865A (en) * | 2017-11-28 | 2018-04-10 | 山东衡昊信息技术有限公司 | It is a kind of based on the icon fringe region dynamic fixing method for following optimization |
| CN107894865B (en) * | 2017-11-28 | 2020-06-26 | 广东嘉晖盛科技股份有限公司 | Function icon edge area dynamic construction method based on following optimization |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102043133B1 (en) | Computer-aided diagnosis supporting apparatus and method | |
| US9898819B2 (en) | System and method for detecting region of interest | |
| Ward | Simultaneous inference for fMRI data | |
| KR101870689B1 (en) | Method for providing information on scalp diagnosis based on image | |
| CN111914665B (en) | Face shielding detection method, device, equipment and storage medium | |
| US10073602B2 (en) | System and method for displaying a suggested luminance adjustment for an image | |
| US20100109998A1 (en) | System and method for sensing facial gesture | |
| CN109145931A (en) | object detecting method, device and storage medium | |
| KR102174658B1 (en) | Apparatus and method for recognizing activity and detecting activity duration in video | |
| US8811750B2 (en) | Apparatus and method for extracting edge in image | |
| CN110268440A (en) | Image analysis apparatus, method for analyzing image and image analysis program | |
| CN111814905A (en) | Target detection method, target detection device, computer equipment and storage medium | |
| US9317926B2 (en) | Automatic spinal canal segmentation using cascaded random walks | |
| CN105243356A (en) | Method of building pedestrian detection model and device and pedestrian detection method | |
| CN111860577A (en) | Artificial intelligence ethical method for identifying human being harmless to human being and robot | |
| US20140198963A1 (en) | Segmentation method of medical image and apparatus thereof | |
| CN102999900B (en) | Image processing equipment and image processing method | |
| CN111862040A (en) | Portrait picture quality evaluation method, device, equipment and storage medium | |
| CN103530646B (en) | The complex object cascaded using grader is detected | |
| CN106708317A (en) | Method and apparatus for judging touch point | |
| CN111126566B (en) | Abnormal furniture layout data detection method based on GAN model | |
| JP2020087463A (en) | Detection device and method, image processing device and system, and storage medium | |
| CN106778805A (en) | Touch point sorting technique and device based on device screen | |
| CN113160199B (en) | Image recognition method and device, computer equipment and storage medium | |
| US20190026890A1 (en) | Display control apparatus, display control method, and recording medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170524 |