METHOD AND APPARATUS FOR DIFFERENTIATING TOUCH SCREEN USERS BASED ON TOUCH EVENT ANALYSIS

• US 20160077615A1
• Filed: 09/11/2014
• Published: 03/17/2016
• Est. Priority Date: 09/11/2014
• Status: Active Grant

• Current Assignee: Qeexo Co. (TDK Corporation)
• Original Assignee: Qeexo Co. (TDK Corporation)
• Inventors: Schwarz, Julia, Harrison, Chris
• Granted Patent: US 9,329,715 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 2203/04105 Pressure sensors for measuring the pressure or force exerted on the touch surface without providing the touch position
• CPC Class Codes: G06F 3/041 Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
• CPC Class Codes: G06F 3/0416 Control or interface arrangements specially adapted for digitisers
• CPC Class Codes: G06F 3/043 using propagating acoustic waves

Abstract

Some embodiments of the present invention include a method of differentiating touch screen users based on characterization of features derived from the touch event acoustics and mechanical impact and includes detecting a touch event on a touch sensitive surface, generating a vibro-acoustic waveform signal using at least one sensor detecting such touch event, converting the waveform signal into at least a domain signal, extracting distinguishing features from said domain signal, and classifying said features to associate the features of the domain signal with a particular user.

Claims

1. An apparatus for differentiating touch screen users based on characterization of features derived from the touch event acoustics and mechanical impact;

the apparatus comprising;

a touch sensitive surface for detecting a touch event from at least one user;

at least one sensor generating a vibro-acoustic waveform signal from such touch event;

a converter for converting the waveform signal into at least a domain signal;

a feature extractor for extracting distinguishing features from said domain signal; and

a classification unit which uses the distinguishing features of said extractor to associate the features of the domain signal with a particular user.

2. The apparatus recited in claim 1 wherein said at least one sensor detects an acoustic effect of a touch event.

3. The apparatus recited in claim 1 wherein said at least one sensor detects a mechanical impact effect of a touch event.

4. The apparatus recited in claim 1 wherein said domain signal is a time domain signal.

5. The apparatus recited in claim 1 wherein said domain signal is a frequency domain signal.

6. The apparatus recited in claim 1 wherein said distinguishing features depend at least in part on the physical characteristics of a finger used to create a touch event.

7. The apparatus recited in claim 1 wherein said distinguishing features depend at least in part on the magnitude of the impact used to create a touch event.

8. The apparatus recited in claim 1 wherein said at least one sensor detects mechanical vibrations initiated by said touch event.

9. The apparatus recited in claim 1 wherein said at least one sensor comprises a sensor taken from the group of sensors consisting of impact sensors, vibration sensors, accelerometers, strain gauges, piezo-electric devices and acoustic sensors.

10. The apparatus recited in claim 1 wherein said distinguishing features are extracted based on at least one computation of a characteristic taken from the group consisting of average, standard deviation, variance, skewness, kurtosis, sum, root mean square, crest factor, dispersion, entropy, power sum, center of mass, coefficient of variation, cross-correlation, zero-crossings, seasonality, DC bias, spectral centroid, spectral density, spherical harmonics, spectral energy, band energy ratio, by spectral band ratios, cepstral coefficients and fast Fourier transform content.

11. A computer-implemented method for differentiating touch screen users based on characterization of features derived from the touch event acoustics and mechanical impact;

the method comprising the following steps;

detecting a touch event on a touch sensitive surface;

generating a vibro-acoustic waveform signal using at least one sensor detecting such touch event;

converting the waveform signal into at least a domain signal;

extracting distinguishing features from said domain signal; and

classifying said features to associate the features of the domain signal with a particular user.

12. The method recited in claim 11 wherein said generating step uses said at least one sensor for detecting an acoustic effect of a touch event.

13. The method recited in claim 11 wherein said generating step uses said at least one sensor for detecting a mechanical impact effect of a touch event.

14. The method recited in claim 11 wherein said domain signal is a time domain signal.

15. The method recited in claim 11 wherein said domain signal is a frequency domain signal.

16. The method recited in claim 11 wherein said distinguishing features depend at least in part on the physical characteristics of a finger used to create a touch event.

17. The method recited in claim 11 wherein said distinguishing features depend at least in part on the magnitude of the impact used to create a touch event.

18. The method recited in claim 11 wherein said at least one sensor detects mechanical vibrations initiated by said touch event.

19. The method recited in claim 11 wherein said at least one sensor comprises a sensor taken from the group of sensors consisting of impact sensors, vibration sensors, accelerometers, strain gauges, piezo-electric devices and acoustic sensors.

20. The method recited in claim 11 wherein said distinguishing features are extracted based on at least one computation of a characteristic taken from the group consisting of average, standard, deviation, variance, skewness, kurtosis, sum, root mean square, crest factor, dispersion, entropy, power sum, center of mass, coefficient variation, cross-correlation, zero-crossings, seasonality, DC bias, spectral centroid, spectral density, spherical harmonics, spectral energy, band energy ratio, log spectral band ratios, cepstral coefficients and fast Fourier transform content.

21. A computer readable medium containing instructions for using detected touch screen events to associate particular users with such events, wherein execution of the program instructions by a processor causes the processor to carry out the steps of:

generating a vibro-acoustic waveform signal using at least one sensor detecting such touch event;

converting the waveform signal into at least a domain signal;

extracting distinguishing features from said converted waveform signal; and

classifying said features to associate the features of the domain signal with a particular user.