Classifying Mechanical Interactions
A method of classifying a mechanical interaction on a sensing array is described. The sensing array comprises a plurality of sensing elements and the method comprises the steps of identifying positional (x,y) and extent (z) data in response to a mechanical interaction such as a finger press in the sensing array; converting the positional and extent data to image data to produce an image; and classifying the positional and extent data by providing the image to an artificial neural network.
1 . A method of classifying a mechanical interaction on a sensing array, said sensing array comprising a plurality of sensing elements, said method comprising the steps of:
identifying positional and extent data in response to said mechanical interaction on said sensing array;
converting said positional and extent data to image data to produce an image recorded over a series of frames, said image comprising a three-layer image, and each layer corresponding to a different color output measured over a period of time; and
classifying said positional and extent data by providing said image to an artificial neural network.
2 . The method of claim 1 , wherein said step of identifying positional and extent data identifies two-dimensional location data and a magnitude of force applied.
3 . The method of claim 1 , wherein said extent data is defined as a range of levels corresponding to a numerically similar range of levels of each said color output.
4 . The method of claim 1 , wherein a value of said extent data is presented in said image by a brightness of said color output.
5 . The method of claim 1 , wherein said artificial neural network is a convolutional neural network.
6 . The method of claim 5 , further comprising the step of:
pre-training said convolutional neural network to interpret said image as a predetermined gesture.
7 . The method of claim 1 , further comprising the step of:
providing a repeated mechanical interaction to said artificial neural network to establish a classification image.
8 . The method of claim 1 , further comprising the step of:
removing background noise by means of said artificial neural network.
9 . The method of claim 1 , further comprising the step of:
confirming said classification step by providing an output in response to said mechanical interaction.
10 . A touch screen comprising said sensing array and a processor configured to perform the method of claim 1 .
11 . Apparatus for classifying a mechanical interaction, comprising:
a sensing array comprising a plurality of sensing elements, said plurality of sensing elements being configured to become active in response to said mechanical interaction;
a processor configured to perform the steps of:
identifying positional and extent data in response to said mechanical interaction;
converting said positional and extent data to image data to produce an image recorded over a series of frames, said image comprising a three-layer image, and each layer corresponding to a different color output measured over a period of time; and
classifying said positional and extent data by providing said image to an artificial neural network.
12 . The apparatus of claim 11 , wherein said sensing array comprises a first plurality of sensing elements arranged in rows and a second plurality of sensing elements arranged in columns; and
said image comprises a corresponding first plurality of pixels arranged in rows and a corresponding second plurality of pixels arranged in columns.
13 . The apparatus of claim 12 , wherein a value of said extent data is presented in said image by a brightness of said color output.
14 . The apparatus of claim 11 , wherein said artificial neural network is a convolutional neural network.