METHOD AND APPARATUS FOR CLASSIFYING CONTACTS WITH A TOUCH SENSITIVE DEVICE

• US 20160299615A1
• Filed: 04/12/2015
• Published: 10/13/2016
• Est. Priority Date: 09/25/2014
• Status: Active Grant

• Current Assignee: Qeexo Co. (TDK Corporation)
• Original Assignee: Qeexo Co. (TDK Corporation)
• Inventors: SCHWARZ, JULIA, XIAO, ROBERT BO, HARRISON, CHRIS
• Granted Patent: US 10,712,858 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06F 2200/1636 Sensing arrangement for detection of a tap gesture on the housing
• CPC Class Codes: G06F 2203/04104 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
• CPC Class Codes: G06F 3/01 Input arrangements or combined input and output arrangements for interaction between user and computer G06F3/16 takes precedence
• CPC Class Codes: G06F 3/04186 Touch location disambiguation
• CPC Class Codes: G06F 3/0433 in which the acoustic waves are either generated by a movable member and propagated within a surface layer or propagated within a surface layer and captured by a movable member

Abstract

Touch sensitive devices, methods and computer readable recording mediums are provided that allow for improved classification of objects against a touch sensitive surface of a touch sensitive device based upon analysis of subdivisions of data representing contact with the touch sensitive surface during a period of time.

Claims

1. A method for classifying an object in contact with a touch sensitive surface, the method comprising:

receiving frame data;

analyzing characteristics of the frame data to determine descriptive features for a subdivision of the frame data that are indicative of the object;

and

determining a frame contact classification for the object in contact with the touch sensitive surface according to the descriptive features and the locations of the subdivisions.

2. The method of claim 1, further comprising comparing the frame contact classification for the object with previous frame contact classifications to determine a current contact state.

3. The method of claim 1, wherein the frame data is converted into a frequency domain representation and wherein the subdivisions are defined in the frequency domain representation.

4. The method of claim 3, wherein the subdivision analysis comprises extracting at least one of a spectral centroid, spectral density, spherical harmonics, total average spectral energy, and log spectral band ratios using the frequency domain representation and using the extractions to classify any contact within each subdivision.

5. The method of claim 1, further comprising determining a current contact state for the object based upon frame contact classifications determined for the object in previously received frame data obtained previously.

6. The method of claim 1, further comprising comparing the frame contact classification for the object with frame contact classifications determined for the object in previously receive frame data and changing a current classification only when a majority of the compared frame contact classifications differs from the frame contact classification.

7. The method of claim 1, further comprising determining a classification confidence based upon the descriptive features for at least one subdivision and switching a mode of touch sensitive device from an existing mode only when the classification confidence reaches a threshold level.

8. The method of claim 1, further comprising performing a pattern classification for the frame data to determine a pattern classification wherein a frame contact classification determined according to the descriptive features is not used to determine an event when the frame contact determination is not consistent with the pattern analysis.

9. The method of claim 1, further comprising determining a classification using at least two others methods for making a classification and determining a classification for an object based upon a vote of the methods.

10. A touch sensitive device comprising:

a touch sensitive surface having an array of sensors that can sense contact with another object; and

a processor cooperating with the touch sensitive surface to receive frame data representing contact of an object with the touch sensitive surface, analyze characteristics of the frame data to determine descriptive features for a subdivision of the frame data that are indicative of the object, and determine a frame contact classification for the object in contact with the touch sensitive surface according to the descriptive features and the locations of the subdivisions.

11. The touch sensitive device of claim 10, further comprising comparing the frame contact classification for the object with previous frame contact classifications to determine a current contact state.

12. The touch sensitive device of claim 10, wherein the frame data is converted into a frequency domain representation and wherein the subdivisions are defined in the frequency domain representation.

13. The touch sensitive device of claim 12, wherein the subdivision analysis comprises extracting at least one of a spectral centroid, spectral density, spherical harmonics, total average spectral energy, and log spectral band ratios using the frequency domain representation and using the extractions to classify any contact within each subdivision.

14. The touch sensitive device of claim 10, wherein the processor determines a current contact state for the object based upon frame contact classifications determined for the object in previously received frame data obtained previously.

15. The touch sensitive device of claim 10, wherein the processor further compares the frame contact classification for the object with frame contact classifications determined for the object in previously receive frame data and changing a current classification only when a majority of the compared frame contact classifications differs from the frame contact classification.

16. The touch sensitive device of claim 10, wherein the processor further determines a classification confidence based upon the descriptive features for at least one subdivision and switching a mode of touch sensitive device from an existing mode only when the classification confidence reaches a threshold level.

17. The touch sensitive device of claim 10, wherein the processor further performs a pattern classification for the frame data to determine a pattern classification wherein a frame contact classification determined according to the descriptive features is not used to determine an event when the frame contact determination is not consistent with the pattern analysis.

18. The touch sensitive device of claim 10, wherein the processor further determines a classification using at least two others methods for making a classification and determining a classification for an object based upon a vote of the methods.

19. A computer-readable recording medium having program instructions that can be executed by various computer components to perform a method comprising:

receiving frame data;

analyzing characteristics of the frame data to determine descriptive features for a subdivision of the frame data that are indicative of the object;

and

determining a frame contact classification for the object in contact with the touch sensitive surface according to the descriptive features and the locations of the subdivisions.

20. The computer-readable recording medium of claim 19, further comprising comparing the frame contact classification for the object with previous frame contact classifications to determine a current contact state.

21. The computer-readable recording medium of claim 19, wherein the frame data is converted into a frequency domain representation and wherein the subdivisions are defined in the frequency domain representation.

22. The computer-readable recording medium of claim 21, wherein the subdivision analysis comprises extracting at least one of a spectral centroid, spectral density, spherical harmonics, total average spectral energy, and log spectral band ratios using the frequency domain representation and using the extractions to classify any contact within each subdivision.

23. The computer-readable recording medium of claim 19, further comprising determining a current contact state for the object based upon frame contact classifications determined for the object in previously received frame data obtained previously.

24. The computer-readable recording medium of claim 19, further comprising comparing the frame contact classification for the object with frame contact classifications determined for the object in previously receive frame data and changing a current classification only when a majority of the compared frame contact classifications differs from the frame contact classification.

25. The computer-readable recording medium of claim 19, further comprising determining a classification confidence based upon the descriptive features for at least one subdivision and switching a mode of touch sensitive device from an existing mode only when the classification confidence reaches a threshold level.

26. The computer-readable recording medium of claim 19, further comprising performing a pattern classification for the frame data to determine a pattern classification wherein a frame contact classification determined according to the descriptive features is not used to determine an event when the frame contact determination is not consistent with the pattern analysis.

27. The computer-readable recording medium of claim 19, further comprising the step of determining a classification using at least two others methods for making a classification and determining a classification for an object based upon a vote of the methods.