Method and apparatus for classifying touch events on a touch sensitive surface
First Claim
Patent Images
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 Assignments
0 Petitions
Accused Products
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.
291 Citations
6 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. - View Dependent Claims (2, 3, 4, 5, 6)
-
Specification