METHOD FOR IMPROVING ACCURACY OF TOUCH SCREEN EVENT ANALYSIS BY USE OF SPATIOTEMPORAL TOUCH PATTERNS

• US 20160085324A1
• Filed: 09/24/2014
• Published: 03/24/2016
• Est. Priority Date: 09/24/2014
• Status: Active Grant

• Current Assignee: Qeexo Co. (TDK Corporation)
• Original Assignee: Qeexo Co. (TDK Corporation)
• Inventors: SCHWARZ, JULIA, HARRISON, CHRIS
• Granted Patent: US 10,606,417 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• 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 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 3/043 using propagating acoustic waves

Abstract

A method of classifying touch screen events uses known non-random patterns of touch events over short periods of time to increase the accuracy of analyzing such events. The method takes advantage of the fact that after one touch event, certain actions are more likely to follow than others. Thus if a touch event is classified as a knock, and then within 500 ms a new event in a similar location occurs, but the classification confidence is low (e.g., 60% nail, 40% knuckle), the classifier may add weight to the knuckle classification since this touch sequence is far more likely. Knowledge about the probabilities of follow-on touch events can be used to bias subsequent classification, adding weight to particular events.

Claims

1. A method of analyzing touch screen events based on characterization of features derived from each touch event, the method comprising:

detecting touch events on a touch sensitive surface;

generating vibro-acoustic waveform signals using at least one sensor associated with the touch events;

converting the waveform signals into at least one domain signal;

extracting distinguishing features from said domain signal; and

classifying said features to analyze the domain signal by employing spatiotemporal event data to weight the analysis of the touch events.

2. The method recited in claim 1, wherein said spatiotemporal event data comprises data from prior multiple touch event sequences over a selected time period.

3. The method recited in claim 1, wherein said spatiotemporal event data comprises data suggesting a likelihood of each touch event after a first of a plurality of touch events over a selected time period.

4. The method recited in claim 1, wherein said spatiotemporal event data is accumulated and stored in advance of said classifying.

5. The method recited in claim 1, wherein said classifying the weights the analysis by multiplying spatiotemporal event likelihood by classification confidences.

6. A method of classifying multiple touch event sequences in touch screen devices to improve the accuracy of determining the characteristics of the touch events imparted to a touch screen;

the method comprising;

analyzing each touch event in said sequence to determine within a level of confidence what hand part caused the touch event;

determining likelihoods of possible hand part touch event sequences; and

combining said level of confidence for each touch event in said sequence and said likelihoods of possible hand part sequences to produce a most likely result of what hand part actually generated each touch event in said sequence.

7. The method recited in claim 6, wherein said hand part may be at least one of a fingertip, a finger knuckle, a fingernail and a hand palm.

8. The method recited in claim 6, wherein said determining uses elapsed time over said multiple touch event sequences to determine said likelihoods.

9. The method recited in claim 6, wherein said combining comprises weighting of said confidence levels by said likelihoods.

10. The method recited in claim 6, wherein said combining comprises multiplication of said confidence levels by said likelihoods.

11. A computer readable medium containing instructions for classifying multiple touch event sequences in touch screen devices to improve the accuracy of determining the characteristics of the touch events imparted to a touch screen, wherein execution of the program instructions by a processor causes the processor to:

analyze each touch event in said sequence to determine within a level of confidence what hand part caused the touch event;

determine likelihoods of possible hand part touch event sequences; and

combine said level of confidence for each touch event in said sequence and said likelihoods of possible hand part sequences to produce a most likely result of what hand part actually generated each touch event in said sequence.

12. The computer readable medium recited in claim 11, wherein said hand part may be at least one of a fingertip, a finger knuckle, a fingernail and a hand palm.

13. The computer readable medium recited in claim 11, wherein said instructions to determine likelihoods of possible hand part touch event sequences uses elapsed time over said multiple touch event sequences to determine said likelihoods.

14. The computer readable medium recited in claim 11, wherein said instructions to combine said level of confidence for each touch event in said sequence and said likelihoods of possible hand part sequences comprises weighting of said confidence levels by said likelihoods.

15. The computer readable medium recited in claim 11, wherein said instructions to combine comprises instructions to multiply said confidence levels by said likelihoods.