Touch classification

Patent metadata

Field	Value
Publication number	US-9558455-B2
Application number	US-201414329052-A
Country	US
Kind code	B2
Filing date	Jul 11, 2014
Priority date	Jul 11, 2014
Publication date	Jan 31, 2017
Grant date	Jan 31, 2017

Abstract

A method for touch classification includes obtaining frame data representative of a plurality of frames captured by a touch-sensitive device, analyzing the frame data to define a respective blob in each frame of the plurality of frames, the blobs being indicative of a touch event, computing a plurality of feature sets for the touch event, each feature set specifying properties of the respective blob in each frame of the plurality of frames, and determining a type of the touch event via machine learning classification configured to provide multiple non-bimodal classification scores based on the plurality of feature sets for the plurality of frames, each non-bimodal classification score being indicative of an ambiguity level in the machine learning classification.

First claim

What is claimed is:

1. A computer-implemented method comprising:
obtaining frame data representative of a plurality of frames captured by a touch-sensitive device;
analyzing the frame data to define a respective blob in each frame of the plurality of frames, the blobs being indicative of a touch event;
computing a plurality of feature sets for the touch event, each feature set specifying properties of the respective blob in each frame of the plurality of frames; and
determining a type of the touch event via machine learning classification configured to provide multiple non-bimodal classification scores based on the plurality of feature sets for the plurality of frames, each non-bimodal classification score being indicative of an ambiguity level in the machine learning classification.

2. The computer-implemented method of claim 1 , wherein the machine learning classification is configured to generate the non-bimodal classification scores such that each non-bimodal classification score is representative of a probability that the touch event is of a respective type.

3. The computer-implemented method of claim 2 , wherein each one of the non-bimodal classification scores is generated by a machine learning classifier configured to accept the plurality of feature sets as inputs.

4. The computer-implemented method of claim 3 , wherein the machine learning classifier comprises a random decision forest classifier.

5. The computer-implemented method of claim 1 , further comprising:
defining a track of the blobs across the plurality of frames for the touch event; and
computing a track feature set for the track,
wherein determining the type comprises applying the track feature set to a machine learning classifier.

6. The computer-implemented method of claim 1 , wherein computing the plurality of feature sets comprises aggregating data indicative of the plurality of feature sets before application of the plurality of feature sets to a machine learning classifier in determining the type of the touch event.

7. The computer-implemented method of claim 1 , wherein each feature set comprises data indicative of an appearance of an image patch disposed at the respective blob in each frame.

8. The computer-implemented method of claim 1 , wherein each feature set comprises data indicative of an intensity gradient in the frame data for the respective blob in each frame.

9. The computer-implemented method of claim 1 , wherein each feature set comprises data indicative of an isoperimetric quotient or other metric of a roundness of the respective blob in each frame.

10. The computer-implemented method of claim 1 , wherein the machine learning classification comprises a lookup table-based classification.

11. The computer-implemented method of claim 1 , wherein determining the type comprises applying the feature set for a respective frame of the plurality of frames to multiple look-up tables, each look-up table providing a respective individual non-bimodal classification score of the multiple non-bimodal classification scores.

12. The computer-implemented method of claim 11 , wherein determining the type comprises combining each of the individual non-bimodal classification scores for the respective frame to generate a blob classification rating score for the respective frame.

13. The computer-implemented method of claim 12 , wherein:
the multiple look-up tables comprise a first look-up table configured to provide a first rating that the touch event is an intended touch and further comprise a second look-up table to determine a second rating that the touch event is an unintended touch; and
determining the type comprises subtracting the second rating from the first rating to determine the blob classification rating score for the respective frame.

14. The computer-implemented method of claim 12 , wherein determining the type comprises aggregating the blob classification rating scores across the plurality of frames to determine a cumulative, multi-frame classification score for the touch event.

15. The computer-implemented method of claim 14 , wherein determining the type comprises:
determining whether the cumulative, multi-frame classification score passes one of multiple classification thresholds; and
if not, then iterating the feature set applying, the classification score combining, and the rating score aggregating acts in connection with a further feature set of the plurality of feature sets.

16. The computer-implemented method of claim 14 , wherein determining the type further comprises, once the cumulative, multi-frame classification score exceeds passes a palm classification threshold for the touch event, classifying a further blob in a subsequent frame of the plurality of frames that overlaps the touch event as a palm touch event.

17. The computer-implemented method of claim 12 , wherein combining each of the individual non-bimodal classification scores comprises adjusting the blob classification rating score by subtracting a value from the blob classification rating score if the respective blob overlaps an anti-blob.

18. The computer-implemented method of claim 12 , wherein combining each of the individual non-bimodal classification scores comprises, when the blob has an area greater than a threshold area, and when the blob is within a threshold distance of a further blob having bimodal classification scores indicative of a palm, adjusting the blob classification rating score by subtracting a quotient calculated by dividing a blob area of the blob by the threshold area.

19. The computer-implemented method of claim 12 , wherein combining each of the individual non-bimodal classification scores comprises:
determining if a number of edge pixels in the respective blob exceeds a threshold; and
if the threshold is exceeded, adjusting the blob classification rating score by subtracting a difference between the number of edge pixels and the threshold from the blob classification rating score.

20. A touch-sensitive device comprising:
a touch-sensitive surface;
a memory in which blob definition instructions, feature computation instructions, and machine learning classification instructions are stored; and
a processor coupled to the memory, configured to obtain frame data representative of a plurality of frames captured via the touch-sensitive surface and configured to execute the blob definition instructions to analyze the frame data to define a respective blob in each frame of the plurality of frames, the blobs being indicative of a touch event;
wherein the processor is further configured to execute the feature computation instructions to compute a plurality of feature sets for the touch event, each feature set specifying properties of the respective blob in each frame of the plurality of frames; and
wherein the processor is further configured to execute the machine learning classification instructions to determine a type of the touch event via machine learning classification configured to provide multiple non-bimodal classification scores based on the plurality of feature sets for the plurality of frames, each non-bimodal classification score being indicative of an ambiguity level in the machine learning classification.

21. The touch-sensitive device of claim 20 , wherein each non-bimodal classification score is representative of a probability that the touch event is of a respective type.

22. The touch-sensitive device of claim 20 , wherein:
each non-bimodal classification score is a blob c

Assignees

• Microsoft Corp
• Microsoft Technology Licensing Llc

Inventors

• Johnson Dan
• Sala Pablo

Classifications

• G06F3/04186

  Touch location disambiguation · CPC title

• G06F3/04883

  for inputting data by handwriting, e.g. gesture or text · CPC title

• G06F3/044

  by capacitive means · CPC title

• G06F3/0416 Primary

  Control or interface arrangements specially adapted for digitisers · CPC title

• G06N5/027

  Frames · CPC title