×

Gesture recognition using neural networks

  • US 9,285,983 B2
  • Filed: 06/14/2011
  • Issued: 03/15/2016
  • Est. Priority Date: 06/14/2010
  • Status: Active Grant
First Claim
Patent Images

1. A computer-implemented method for gesture recognition, comprising:

  • recording an initial point when it is determined that a user presses a finger on a screen comprising a resistive touch panel overlay that can only record a single point at a time;

    recording subsequent points and calculating an angle from point to point as the user periodically moves the finger; and

    when it is determined that the user'"'"'s finger is removed from the screen, comparing each of the calculated angles with corresponding ideal angles in order to recognize the gesture;

    wherein recognizing the gesture comprises;

    iterating through a table to determine two points that are closest to each other when a plurality of points exceeds a threshold number;

    calculating a geometric center value of the two points, replacing the first point with the value and deleting the second point; and

    repeating the iteration and replacing until the plurality of points is reduced to the threshold number.

View all claims
  • 2 Assignments
Timeline View
Assignment View
    ×
    ×