METHOD AND APPARATUS FOR IMPROVING ACCURACY OF TOUCH SCREEN EVENT ANALYSIS BY USE OF EDGE CLASSIFICATION

• US 20160085372A1
• Filed: 09/22/2014
• Published: 03/24/2016
• Est. Priority Date: 09/22/2014
• Status: Active Grant

• Current Assignee: Qeexo Co. (TDK Corporation)
• Original Assignee: Qeexo Co. (TDK Corporation)
• Inventors: SCHWARZ, JULIA, MUNEMOTO, TAIHEI, HARRISON, CHRIS
• Granted Patent: US 9,864,453 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 2203/04106 Multi-sensing digitiser, i.e. digitiser using at least two different sensing technologies simultaneously or alternatively, e.g. for detecting pen and finger, for saving power or for improving position detection
• CPC Class Codes: G06F 3/0416 Control or interface arrangements specially adapted for digitisers
• CPC Class Codes: G06F 3/04186 Touch location disambiguation
• CPC Class Codes: G06F 3/043 using propagating acoustic waves

Abstract

Methods and apparatus of embodiments of the present invention include a classification system configured to treat edge contact of a touch screen as a separate class of touch events such that any touches occurring near the edge of the touch screen are to be processed by a classifier that is configured to process edge contacts as compared to a classifier that is configured to process other contacts that may occur in the approximate middle of the touch screen which may be wholly digitized. An apparatus may employ two separate and distinct classifiers, including a full touch classifier and an edge touch classifier. The touch screen may be configured to have two different sensing regions to determine which of the two classifiers is appropriate for a touch event.

Claims

1. An apparatus for analyzing touch screen users based on characterization of features derived from a touch event, the apparatus comprising:

a touch sensitive screen for detecting a touch event from at least one user, said touch sensitive screen having at least two touch regions;

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

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

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

a plurality of classification units which use the distinguishing features of said extractor to analyze the features of the domain signal, at least one such classification unit associated with at least one such touch region and another such classification unit associated with another such touch region.

2. The apparatus recited in claim 1 wherein said at least one such classification unit is associated with an edge region of said touch sensitive screen.

3. The apparatus recited in claim 1 wherein said at least one such classification unit is associated with a central region of said touch sensitive screen.

4. The apparatus recited in claim 1 wherein said touch sensitive screen comprises an edge region and a central region.

5. The apparatus recited in claim 1 wherein said touch sensitive screen enables one said classification unit depending upon which of said at least two distinct touch regions is touched during a touch event.

6. The apparatus recited in claim 1 wherein one of said distinct touch regions comprises a region proximate to the edge of said touch sensitive screen.

7. The apparatus recited in claim 1 wherein said touch sensitive screen comprises a region forming the central area of said touch sensitive screen.

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 Fourier transform content.

11. A method of analyzing touch screen users based on characterization of features derived from a touch event the method comprising:

detecting a touch event on a touch sensitive screen, said touch sensitive screen having at least two touch regions;

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

converting the waveform signal into a domain signal;

extracting distinguishing features from said domain signal; and

classifying said features to analyze the features of the domain signal by employing one of at least two different classification processes depending on which of the two distinct touch regions was touched during the touch event.

12. The method recited in claim 11 wherein said classifying uses a first such classification process when such touch region that is touched is proximate an edge of said touch sensitive screen.

13. The method recited in claim 11 wherein said classifying uses a second such classification process when such touch region that is touched is proximate a central area of said touch sensitive screen.

14. The method recited in claim 11 wherein said touch sensitive screen comprises an edge region and a central region.

15. The method recited in claim 11 wherein said touch sensitive screen enables one of two different said classification processes depending upon which of said at least two distinct touch regions is touched during a touch event.

16. The method recited in claim 11 wherein one of said distinct touch regions comprises a region proximate to the edge of said touch sensitive screen.

17. The method recited in claim 11 wherein said one of said distinct touch regions comprises a region forming the central area of said touch sensitive screen.

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 non-transitory computer readable medium containing instructions for using detected touch screen events to analyze touch screen users where there are at least two touch screen regions, wherein execution of the 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 a touch event;

converting the waveform signal into a domain signal;

extracting distinguishing features from said domain signal; and

classifying said features to analyze the features of the domain signal by employing one of at least two different classification processes depending on which of the two distinct touch regions was touched during the touch event.