Method and apparatus for classifying touch events on a touch sensitive surface

• US 10,642,407 B2
• Filed: 12/08/2017
• Issued: 05/05/2020
• Est. Priority Date: 10/18/2011
• Status: Active Grant

• Current Assignee: Carnegie Mellon University
• Original Assignee: Carnegie Mellon University
• Inventors: Harrison, Christopher, Schwarz, Julia, Hudson, Scott E.
• Primary Examiner(s): Wills-Burns, Chineyere D
• Application Number:
  US15/836,798
• Publication Number:
  US 20180107333A1
• Time in Patent Office: 879 Days
• Field of Search: 345174
• CPC Class Codes: G06F 2200/1636 Sensing arrangement for detection of a tap gesture on the housing
• 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
• 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

An apparatus classifies touch events. The apparatus includes a touch sensitive surface configured to generate a touch event when an object touches the touch sensitive surface. The touch event entails a mechanical vibration upon contact with the surface. The apparatus includes a touch event detector configured to detect the onset of a touch, and a touch event classifier configured to classify the touch event to identify the object used for the touch event. The mechanical vibration is created via any one of finger parts including a tip, a pad, a fingernail, and a knuckle, each of which has a unique feature different from each other.

Claims

1. A method for classifying touch events, the method comprising:

sampling at least one mechanical vibration signal associated with a touch event on a surface to create a digital representation of the at least one mechanical vibration signal;

converting the digital representation into an electrical signal having a frequency domain representation;

deriving a first set of features representative of the touch event based on at least a portion of the electrical signal;

down sampling the at least the portion of the electrical signal to create a down sampled signal;

deriving a second set of features representative of the touch event based on at least a portion of the down sampled signal; and

classifying, with a processor, the touch event using at least one of at least a portion of the first set of features or at least a portion of the second set of features to identify an object associated with the touch event.

2. The method of claim 1, wherein at least one of the deriving the first set of features representative of the touch event or the deriving the second set of features representative of the touch event comprises deriving at least one of an average absolute amplitude associated with the at least one mechanical vibration signal, a total absolute amplitude associated with the at least one mechanical vibration signal, a standard deviation of absolute amplitude associated with the at least one mechanical vibration signal, a center of mass of associated with the at least one mechanical vibration signal, a predetermined spectrogram associated with the at least one mechanical vibration signal, a power associated with at least one specific frequency component of the at least one mechanical vibration signal, a predetermined frequency spectrum content of the at least one mechanical vibration signal, or a frequency spectrum of a combination of the at least one mechanical vibration signal with at least another mechanical vibration signal.

3. The method of claim 1, wherein the sampling the at least one mechanical vibration signal associated with the touch event comprises sampling the at least one mechanical vibration signal associated with the touch event that is associated with at least one of a passive tool or a part of a user'"'"'s body impacting the surface.

4. The method of claim 1, wherein the classifying the touch event comprises classifying the touch event using the at least the portion of the first set of features and the at least the portion of the second set of features to identify the object associated with the touch event.

5. The method of claim 1, wherein the sampling the at least one mechanical vibration signal associated with the touch event comprises sampling the at least one mechanical vibration signal associated with the touch event that is created via at least one finger part including at least one of a tip, a pad, a fingernail, or a knuckle on the surface.

6. The method of claim 5, further comprising:

providing a touch based interface based at least in part on the at least one mechanical vibration signal created via the at least one finger part being identified as the object associated with the touch event.