CN106569630A - Method for detecting number of touch control system screen contacts - Google Patents
Method for detecting number of touch control system screen contacts Download PDFInfo
- Publication number
- CN106569630A CN106569630A CN201610879429.1A CN201610879429A CN106569630A CN 106569630 A CN106569630 A CN 106569630A CN 201610879429 A CN201610879429 A CN 201610879429A CN 106569630 A CN106569630 A CN 106569630A
- Authority
- CN
- China
- Prior art keywords
- main frame
- screen
- control system
- contact
- video camera
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2203/00—Indexing scheme relating to G06F3/00 - G06F3/048
- G06F2203/041—Indexing scheme relating to G06F3/041 - G06F3/045
- G06F2203/04104—Multi-touch detection in digitiser, i.e. details about the simultaneous detection of a plurality of touching locations, e.g. multiple fingers or pen and finger
Abstract
The invention provides a method for detecting number of touch control system screen contacts. The method ingeniously and reasonably settles a k-value selection problem in a K-means algorithm and furthermore settles a problem in calculating finger contacts on the screen. The method is a practical operation method and has high reference value in settling similar problems by means of the K-means algorithm.
Description
Technical field
The present invention relates to image identification technical field, particularly a kind of method of detection touch-control system screen number of contacts.
Background technology
K-means algorithms be very typically based on distance clustering algorithm, using distance as similarity evaluation index,
Think that the distance of two objects is nearer, its similarity is bigger.The algorithm thinks cluster by constituting apart from close object,
Therefore using obtaining compact and independent cluster as final goal.
The selection of k initial classes cluster centre point has large effect to cluster result, because in the algorithm first step
In be any k object of random selection as the center of initial clustering, initially represent a cluster.The algorithm is in each iteration
In remaining each object is concentrated to data, each object is assigned to again according to itself and the distance at each cluster center nearest
Cluster.After all data objects have been investigated, an iteration computing is completed, and new cluster centre is computed.If once
Before and after iteration, the value of J does not change, and illustrates that algorithm has been restrained.
Algorithmic procedure is:From N number of document K document is randomly selected as barycenter;It is measured to remaining each document to arrive
The distance of each barycenter, and it is grouped into the class of nearest barycenter;Recalculate the barycenter of each class for having obtained;Iteration 2
Until new barycenter is equal with the protoplasm heart or less than specified threshold, algorithm terminates~3 steps.
In touch-control system, using the thought of K-means algorithms, the number for calculating finger contact on screen is removed, but
K is given in advance in K-means algorithms, many times, is not aware that given data set should be divided into how many classes in advance
Special talent is most suitable, therefore, the number of finger contact still there are problems that a lot on calculating screen.
The content of the invention
In order to solve the above problems, the present invention proposes a kind of method of detection touch-control system screen number of contacts.
The concrete scheme of the present invention is as follows:
A kind of method of detection touch-control system screen number of contacts, the touch-control system includes screen (1), video camera (2)
With main frame (3), video camera (2) is connected with main frame (3) by data wire, and main frame (3) is connected with screen (1) by video line, step
It is rapid as follows:
S1:Video camera (2) catches image of the contact on screen (1), is transferred to the main frame (3);
S2:The main frame (3) receives the image that the video camera (2) is transmitted, and the track of contact is detected, tracked,
Wherein, each contact selects 4 key points to represent its contour feature;
S3:The image that the main frame (3) is transmitted according to the video camera (2), calculates the distance between key point;
S4:The main frame (3) is ranked up according to above-mentioned result of calculation to the distance between key point, select it is maximum away from
From Di;
S5:The main frame (3) compares the size between Di and the distance threshold of setting, if Di according to above-mentioned result of calculation<
The distance threshold of setting, then illustrate that this frame contact is i, and k-means clusters are carried out to all key points by k=i, obtains poly-
The center of class central point, i.e. contact;
S6:The main frame (3) according to above-mentioned result of calculation, if Di>The distance threshold of setting, then by k=i+1 to all
Key point carries out k-means clusters, obtains i+1 cluster centre point, and i+1 cluster centre point and all key points are calculated respectively
Distance, all distances to calculating are ranked up, and select ultimate range D (i+1);
S7:The main frame (3) corrects parameter i=i+1 of initial state according to above-mentioned result of calculation, repeat step S5, S6,
When ultimate range Di<During the distance threshold of setting, repeat step terminates, and transmits the result to screen (1);
S8:The screen (1) shows the result that detecting and tracking is arrived.
Preferably, step S5 is also including the setting of distance threshold.
The present invention compared with prior art, has the advantages that:
A kind of method of detection touch-control system screen number of contacts proposed by the present invention is ingenious reasonably to solve K-
The On The Choice of k value in means algorithms, while also solve the problems, such as to calculate finger contact on screen, with conscientiously may be used
Capable operational approach, solves the problems, such as to be similar to very big reference value for follow-up using K-means algorithms.
Description of the drawings
Fig. 1 is a kind of flow chart of the method for detection touch-control system screen number of contacts proposed by the present invention;
Fig. 2 is that a kind of contact key point selection of the method for detection touch-control system screen number of contacts proposed by the present invention is shown
It is intended to;
Fig. 3 is the schematic diagram of the touch-control system of the present invention.
Description of the drawings:
The main frame of 1 screen, 2 video camera 3
Specific embodiment
Technical scheme is further described below in conjunction with specific embodiment.It should be appreciated that being described herein as
Specific embodiment only to explain the present invention, be not intended to limit the present invention.
Fig. 3 is the schematic diagram of the touch-control system of the present invention, and touch-control system includes screen (1), video camera (2) and main frame (3),
Video camera 2 is connected with main frame 3 by data wire, and main frame 3 is connected with screen 1 by video line.
Fig. 1 be it is proposed by the present invention it is a kind of detection touch-control system screen number of contacts method flow chart, video camera (2)
Image of the contact on screen (1) is caught, the main frame (3) is transferred to, the main frame (3) receives the video camera (2) and transmits
Image, the track of contact is detected, is tracked, wherein, as shown in Fig. 2 each contact select 4 key points (1,2,3,
4) its contour feature is represented, it is assumed that there are 3 contacts, each contact selects 4 key points for representing its contour feature, 12 altogether
Point, the coordinate of this 12 points be respectively A (X1, Y1), B (X2, Y2), C (X3, Y3), D (X4, Y4), E (X5, Y5), F (X6, Y6),
G (X7, Y7), H (X8, Y8), I (X9, Y9), J (X10, Y10), K (X11, Y11), L (X12, Y12), the main frame (3) is according to institute
The image that video camera (2) is transmitted is stated, the distance between key point is calculated, computing formula isNeed calculate AB, AC, AD, AE, AF, AG, AH, AI, AJ, AK, AL, BC, BD,
BE、BF、BG、BH、BI、BJ、BK、BL、CD、CE、CF、CG、CH、CI、CJ、CK、CL、DE、DF、DG、DH、DI、DJ、DK、DL、
EF、EG、EH、EI、EJ、EK、EL、FG、FH、FI、FJ、FK、FL、GH、GI、GJ、GK、GL、HI、HJ、HK、HL、IJ、IK、IL、
The distance between JK, JL, KL, the main frame (3) is selected according to above-mentioned result of calculation, above-mentioned 66 distances for calculating of comparison
Ultimate range D1=AB, the greatest radius formed in screen with a model finger-stall as the distance threshold that sets, the master
Machine (3) compares the size between AB and the distance threshold of setting according to above-mentioned result of calculation, if AB<The distance threshold of setting, then
Illustrate that this frame contact is 1, k-means clusters are carried out to all key points by k=1, obtain cluster centre point, i.e. finger and touch
The center of point, representative has a finger touch screen, and the main frame (3) is according to above-mentioned result of calculation, if AB>The distance threshold of setting,
Then k-means clusters are carried out to all key points by k=2, the method at the midpoint by seeking each two value by this obtains 2
Cluster centre point, calculates respectively the distance of 2 cluster centre points and all key points, and all distances to calculating are arranged
Sequence, selects ultimate range D2, and the main frame (3) calculates again D2 big with the distance threshold for setting up an office according to above-mentioned result of calculation
It is little, if D2<The distance threshold of setting, then illustrate that this frame contact is 2, all key points is carried out with k-means by k=2 and is gathered
Class, obtains cluster centre point, the i.e. center of finger contact, and representative has 2 finger touch screens, if D2>The distance threshold of setting, then need
Continue cluster, until cluster result reaches convergence, k is 3 during convergence, and the finger number on screen is just 3, then ties this
Fruit is transferred to screen (1), and the screen (1) shows the result that detecting and tracking is arrived.
In sum, the method for a kind of detection touch-control system screen number of contacts proposed by the present invention, ingenious rational solution
Determine the On The Choice of k value in K-means algorithms, while also solving the problems, such as to calculate finger contact on screen, had
Practicable operational approach, solves the problems, such as to be similar to very big reference value for follow-up using K-means algorithms.
Embodiment above is the preferred embodiment of the present invention, not thereby limits the patent protection model of the present invention
Enclose.Those skilled in the art belonging to any present invention, in the premise without departing from spirit and scope disclosed in this invention
Under, the equivalent structure done to present disclosure each falls within claimed the scope of the claims with the conversion of equivalent step
Within.
Claims (2)
1. it is a kind of detection touch-control system screen number of contacts method, the touch-control system include screen (1), video camera (2) and
Main frame (3), video camera (2) is connected with main frame (3) by data wire, and main frame (3) is connected with screen (1) by video line, and it is special
Levy and be, step is as follows:
S1:Video camera (2) catches image of the contact on screen (1), is transferred to the main frame (3);
S2:The main frame (3) receives the image that the video camera (2) is transmitted, and the track of contact is detected, tracked, wherein,
Each contact selects 4 key points to represent its contour feature;
S3:The image that the main frame (3) is transmitted according to the video camera (2), calculates the distance between key point;
S4:The main frame (3) is ranked up according to above-mentioned result of calculation to the distance between key point, selects ultimate range Di;
S5:The main frame (3) compares the size between Di and the distance threshold of setting, if Di according to above-mentioned result of calculation<Setting
Distance threshold, then illustrate that this frame contact is i, k-means clusters are carried out to all key points by k=i, in obtaining cluster
Heart point, the i.e. center of contact;
S6:The main frame (3) according to above-mentioned result of calculation, if Di>The distance threshold of setting, then by k=i+1 to all keys
Point carries out k-means clusters, obtains i+1 cluster centre point, respectively calculating i+1 cluster centre point and all key points away from
From all distances to calculating are ranked up, and select ultimate range D (i+1);
S7:The main frame (3) corrects parameter i=i+1 of initial state, repeat step S5, S6, when most according to above-mentioned result of calculation
Greatly apart from Di<During the distance threshold of setting, repeat step terminates, and transmits the result to screen (1);
S8:The screen (1) shows the result that detecting and tracking is arrived.
2. it is according to claim 1 it is a kind of detection touch-control system screen number of contacts method, it is characterised in that the step
Rapid S5 is also including the setting of distance threshold.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610879429.1A CN106569630B (en) | 2016-09-30 | 2016-09-30 | A method of detection touch-control system screen number of contacts |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610879429.1A CN106569630B (en) | 2016-09-30 | 2016-09-30 | A method of detection touch-control system screen number of contacts |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106569630A true CN106569630A (en) | 2017-04-19 |
CN106569630B CN106569630B (en) | 2019-01-22 |
Family
ID=58532687
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610879429.1A Active CN106569630B (en) | 2016-09-30 | 2016-09-30 | A method of detection touch-control system screen number of contacts |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106569630B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109656393A (en) * | 2017-10-10 | 2019-04-19 | 北京仁光科技有限公司 | Refer to tracking, device, equipment and the computer readable storage medium of contact more |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102693025A (en) * | 2011-03-21 | 2012-09-26 | 中国科学院软件研究所 | Touch finger identification method for multi-touch interaction system |
CN103186241A (en) * | 2013-04-03 | 2013-07-03 | 中国科学院软件研究所 | Method for recognizing contact left and right hands on interactive desktop |
CN104361340A (en) * | 2014-11-04 | 2015-02-18 | 西安电子科技大学 | SAR image target fast detecting method based on significance detecting and clustering |
US20150201298A1 (en) * | 2013-03-30 | 2015-07-16 | Tsinghua University | Method for positioning ip location and server |
-
2016
- 2016-09-30 CN CN201610879429.1A patent/CN106569630B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102693025A (en) * | 2011-03-21 | 2012-09-26 | 中国科学院软件研究所 | Touch finger identification method for multi-touch interaction system |
US20150201298A1 (en) * | 2013-03-30 | 2015-07-16 | Tsinghua University | Method for positioning ip location and server |
CN103186241A (en) * | 2013-04-03 | 2013-07-03 | 中国科学院软件研究所 | Method for recognizing contact left and right hands on interactive desktop |
CN104361340A (en) * | 2014-11-04 | 2015-02-18 | 西安电子科技大学 | SAR image target fast detecting method based on significance detecting and clustering |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109656393A (en) * | 2017-10-10 | 2019-04-19 | 北京仁光科技有限公司 | Refer to tracking, device, equipment and the computer readable storage medium of contact more |
Also Published As
Publication number | Publication date |
---|---|
CN106569630B (en) | 2019-01-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110020620B (en) | Face recognition method, device and equipment under large posture | |
Maltezos et al. | Building extraction from LiDAR data applying deep convolutional neural networks | |
EP4167130A1 (en) | Neural network training method and related device | |
US9588621B2 (en) | Touch screen controller and method for controlling thereof | |
WO2021017303A1 (en) | Person re-identification method and apparatus, computer device and storage medium | |
US9020264B2 (en) | Image management device, image management method, program, recording medium, and integrated circuit | |
CN107169922B (en) | Image registration method for maintaining topological structure based on tensor sparse representation | |
WO2019109793A1 (en) | Human head region recognition method, device and apparatus | |
WO2023016007A1 (en) | Method and apparatus for training facial recognition model, and computer program product | |
WO2023051369A1 (en) | Neural network acquisition method, data processing method and related device | |
CN115311730B (en) | Face key point detection method and system and electronic equipment | |
CN108805174A (en) | clustering method and device | |
JP6153561B2 (en) | Method, apparatus, and computer program for adjusting hyperlink layout size (adjusting hyperlink layout size) | |
US9734434B2 (en) | Feature interpolation | |
CN111444802B (en) | Face recognition method and device and intelligent terminal | |
CN114170688B (en) | Character interaction relation identification method and device and electronic equipment | |
Serikbay et al. | Accurate surface condition classification of high voltage insulators based on deep convolutional neural networks | |
CN106569630A (en) | Method for detecting number of touch control system screen contacts | |
CN114519306A (en) | Decentralized terminal node network model training method and system | |
CN111222534A (en) | Single-shot multi-frame detector optimization method based on bidirectional feature fusion and more balanced L1 loss | |
CN108509537B (en) | System and method for forecasting galloping probability of power transmission line | |
CN114928721B (en) | Switching method and system of football shooting lens, computer equipment and storage medium | |
CN106650916B (en) | A kind of mesh segmentation method based on ant group optimization | |
CN113486881B (en) | Text recognition method, device, equipment and medium | |
US20120293432A1 (en) | Method for touch device to transmit coordinates, method for touch device to transmit displacement vector and computer-readable medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |