Touch sensor gesture recognition for operation of mobile devices

• US 9,524,041 B2
• Filed: 12/22/2010
• Issued: 12/20/2016
• Est. Priority Date: 12/22/2010
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Phulwani, Praem, Yukich, Rudy
• Primary Examiner(s): Ghebretinsae, Temesghen
• Assistant Examiner(s): Karki, Paras D
• Application Number:
  US13/993,057
• Publication Number:
  US 20130257781A1
• Time in Patent Office: 2,190 Days
• US Class Current: 1/1
• 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 3/042 by opto-electronic means
• CPC Class Codes: G06F 3/044 by capacitive means
• CPC Class Codes: G06F 3/04847 Interaction techniques to control parameter settings, e.g. interaction with sliders or dials
• CPC Class Codes: G06F 3/04883 for inputting data by handwriting, e.g. gesture or text
• CPC Class Codes: G06F 3/04886 by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus

Abstract

Touch sensor gesture recognition for operation of mobile devices. An embodiment of a mobile device may include a touch sensor for the detection of gestures, the touch sensor including sensor elements to generate touch sensor data for a detected gesture, and a processor to process the touch sensor data produced by the sensor elements of the touch sensor. In some embodiments the processor is to process the touch sensor data using a hybrid touch sensor algorithm, the hybrid touch sensor algorithm including a plurality of touch sensor algorithms, the plurality of touch sensor algorithms including a first algorithm and a second algorithm, where the processor dynamically changes between the plurality of algorithms depending on of the nature of the received touch sensor data. In some embodiments the processor utilizes a support vector machine with a radial basis function kernel in the interpretation of detected gestures. In some embodiments, the processor is to determine an alignment between a first input sequence of sensor data and a second input sequence of sensor data using dynamic time warping.

Claims

1. A mobile device comprising:

a touch sensor for the detection of gestures, the touch sensor including a plurality of sensor elements to generate touch sensor data for a first detected gesture performed by a thumb or other finger of a user on the touch sensor; and

a processor, the processor to process the touch sensor data produced by the sensor elements of the touch sensor to calculate a motion of the first detected gesture;

wherein the processor is to process the touch sensor data for the first detected gesture using a hybrid touch sensor algorithm, the hybrid touch sensor algorithm including a plurality of touch sensor algorithms to calculate motion of gestures detected by the touch sensor, the plurality of touch sensor algorithms including a first touch sensor algorithm and a second touch sensor algorithm, wherein the processor dynamically changes from utilizing results generated by the first touch sensor algorithm for the first detected gesture to utilizing results generated by the second touch sensor algorithm for the first detected gesture in response to the processor detecting rank skipping between the plurality of sensor elements in data produced by the first touch sensor algorithm for the motion of the first detected gesture;

wherein the first touch sensor algorithm is a slider algorithm, the first touch sensor algorithm to treat the plurality of sensor elements as being physically arranged in a plurality of sensor ranks located in relation to a first axis, and the second touch sensor algorithm is a centroid algorithm, and wherein detecting rank skipping includes detecting a discontinuity in sensing of sensor rank positions for the calculated motion of the first detected gesture.

2. The mobile device of claim 1, wherein:

the second touch sensor algorithm is to take a weighted average of quantities derived from the plurality of sensor elements to determine a barycenter of the thumb or other finger of the user performing the first detected gesture.

3. The mobile device of claim 2, wherein the barycenter determined by the second touch sensor algorithm may be used for one of an absolute position of the thumb or other finger of the user or differentiated to provide relative motion information.

4. The mobile device of claim 1, wherein the first touch sensor algorithm is to identify a position on one of the sensor ranks for the first detected gesture.

5. The mobile device of claim 4, wherein determining the sensor rank for the first detected gesture includes locating a distal-most sensor rank meeting a certain threshold.

6. The mobile device of claim 4, wherein the slider algorithm is preferred over the centroid algorithm when a tip of the thumb or other finger of the user is located on an upper portion of the touch sensor.

13. The mobile device of claim 1, wherein detecting rank skipping includes comparing a derivative for a detected position of the first detected gesture along the first axis for the first touch sensor algorithm with a derivative for a detected position of the first detected gesture along the first axis for the second touch sensor algorithm.

14. The mobile device of claim 13, wherein detecting rank skipping further includes comparing a detected position of the first detected gesture along a second axis, the second axis being perpendicular to the first axis, to an edge of the touch sensor.

17. The mobile device of claim 1, wherein a position on a second axis, the second axis being perpendicular to the first axis, is a linear transformation between the first touch sensor algorithm and the second touch sensor algorithm.

7. A method comprising:

receiving touch sensor data for a mobile device, the touch sensor data representing a gesture input for a first detected gesture performed by a thumb or other finger of a user on the touch sensor;

processing the touch sensor data to calculate a motion of the first detected gesture using a hybrid touch sensor algorithm, the hybrid touch sensor algorithm including a plurality of touch sensor algorithms to calculate motion of gestures detected by the touch sensor, the plurality of touch sensor algorithms including a first touch sensor algorithm and a second touch sensor algorithm; and

dynamically changing from utilizing results generated by the first touch sensor algorithm for the first detected gesture to utilizing results generated by the second touch sensor algorithm for the first detected gesture in response to detecting rank skipping between the plurality of sensor elements in data produced by the first touch sensor algorithm for the motion of the first detected gesture;

wherein the first touch sensor algorithm is a slider algorithm, the first touch sensor algorithm to treat the plurality of sensor elements as being physically arranged in a plurality of sensor ranks located in relation to a first axis, and the second touch sensor algorithm is a centroid algorithm, and wherein detecting rank skipping includes detecting a discontinuity in sensing of sensor rank positions for the calculated motion of the first detected gesture.

8. The method of claim 7, wherein:

the second touch sensor algorithm is to take a weighted average of quantities derived from the plurality of sensor elements to determine a barycenter of the thumb or other finger of the user performing the first detected gesture.

9. The method of claim 8, wherein the barycenter determined by the second touch sensor algorithm may be used for one of an absolute position of the thumb or other finger or differentiated to provide relative motion information for the first detected gesture.

10. The method of claim 7, wherein the first touch sensor algorithm is to identify a position on one of the sensor ranks for the first detected gesture.

11. The method of claim 10, wherein determining the sensor rank for the first gesture includes locating a distal-most sensor rank meeting a certain threshold.

12. The method of claim 8, wherein the slider algorithm is preferred over the centroid algorithm when a tip of the thumb or other finger of the user is located on an upper portion of the touch sensor.

15. The method of claim 7, wherein detecting rank skipping includes comparing a derivative for a detected position of the first detected gesture along the axis for the first touch sensor algorithm with a derivative for a detected position of the first detected gesture along the axis for the second touch sensor algorithm.

16. The method of claim 15, wherein detecting rank skipping further includes comparing a detected position of the first detected gesture along a second axis, the second axis being perpendicular to the first axis, to an edge of the touch sensor.

18. The method of claim 7, wherein a position on a second axis, the second axis being perpendicular to the first axis, is a linear transformation between the first touch sensor algorithm and the second touch sensor algorithm.