GESTURE RECOGNITION USING NEURAL NETWORKS

• US 20110304573A1
• Filed: 06/14/2011
• Published: 12/15/2011
• Est. Priority Date: 06/14/2010
• Status: Active Grant

• Current Assignee: Harman Professional, Inc. (Samsung Electronics Co. Ltd.)
• Original Assignee: Amx LLC (Samsung Electronics Co. Ltd.)
• Inventors: Smith, George C.
• Granted Patent: US 9,285,983 B2
• Time in Patent Office: Days
• US Class Current: 345/173
• CPC Class Codes: G06F 2203/04808 Several contacts: gestures triggering a specific function, e.g. scrolling, zooming, right-click, when the user establishes several contacts with the surface simultaneously; e.g. using several fingers or a combination of fingers and pen
• CPC Class Codes: G06F 3/0418 for error correction or compensation, e.g. based on parallax, calibration or alignment
• CPC Class Codes: G06F 3/045 using resistive elements, e.g. a single continuous surface or two parallel surfaces put in contact
• CPC Class Codes: G06F 3/04883 for inputting data by handwriting, e.g. gesture or text
• CPC Class Codes: G06V 30/347 Sampling; Contour coding; Stroke extraction

Abstract

An apparatus, method, and a computer program is provided for gesture recognition using neural networks. An initial point is recorded when a user presses a finger on a screen. Subsequent points are recorded and an angle is calculated from point to point as the user periodically moves the finger. A set of the calculated angles are compared with an ideal angle in order to recognize the gesture.

Claims

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;

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.

2. The computer-implemented method of claim 1, further comprising:

determining an overall error for each possibility based on the comparing of each of the calculated angles.

3. The computer-implemented method of claim 1, further comprising:

based on the comparing of each of the calculated angles, selecting the calculated angles with the lowest error to be the correct gesture.

4. The computer-implemented method of claim 1, further comprising:

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

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

5. The computer implemented method of claim 1, further comprising:

iterating through a table to determine two points that are furthest away from each other when the plurality of points are below a minimum number of points; and

interpolating a new point between the two points.

6. The computer-implemented method of claim 1, further comprising:

when the plurality of points are below a minimum number of points, calculating a simple line when a maximum distance between two of the plurality of points exceeds a threshold number.

7. The computer-implemented method of claim 1, further comprising:

recording a time between when the first point is touched until a last point is touched; and

calculating a gesture velocity based on the recorded time.

8. An apparatus, comprising:

a processor; and

memory configured to store an application,

wherein the application, when executed, is configured to cause the processor to;

record an initial point when it is determined that a user presses a finger on a screen;

record subsequent points and calculate 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, compare each of the calculated angles with corresponding ideal angles in order to recognize the gesture.

9. The apparatus of claim 8, wherein the application is further configured to cause the processor to:

determine an overall error for each possibility based on the comparing of each of the calculated angles.

10. The apparatus of claim 8, wherein the application is further configured to cause the processor to:

based on the comparing of each of the calculated angles, select the calculated angles with the lowest error to be the correct gesture.

11. The apparatus of claim 8, wherein the application is further configured to cause the processor to:

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

calculate a geometric center value of the two points, replace the first point with the value and delete the second point.

12. The apparatus of claim 8, wherein the application is further configured to cause the processor to:

iterate through a table to determine two points that are furthest away from each other when a plurality of points is below a minimum number of points; and

interpolate a new point between the two points.

13. The apparatus of claim 8, wherein the application is further configured to cause the processor to:

when the plurality of points is below a minimum number of points, calculate a simple line when a maximum distance between two of the plurality of points exceeds a threshold number.

14. The apparatus of claim 8, wherein the application is further configured to cause the processor to:

record a time between when the first point is touched until a last point is touched; and

calculate a gesture velocity based on the recorded time.

15. A computer program, embodied on a non-transitory computer-readable medium, the computer program, when executed, configured to cause a processor to:

record an initial point when it is determined that a user presses a finger on a screen;

record subsequent points and calculate 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, compare each of the calculated angles with corresponding ideal angles in order to recognize the gesture.

16. The computer program of claim 15, wherein the computer program is further configured to cause the processor to:

determine an overall error for each possibility based on the comparing of each of the calculated angles.

17. The computer program of claim 15, wherein the computer program is further configured to cause the processor to:

based on the comparing of each of the calculated angles, select the calculated angles with the lowest error to be the correct gesture.

18. The computer program of claim 15, wherein the computer program is further configured to cause the processor to:

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

calculate a geometric center value of the two points and replacing the first point with the value and deleting the second point.

19. The computer program of claim 15, wherein the computer program is further configured to cause the processor to:

iterate through a table to determine two points that are furthest away from each other when a plurality of points is below a minimum number of points; and

interpolate a new point between the two points.

20. The computer program of claim 15, wherein the computer program is further configured to cause the processor to:

when the plurality of points are below a minimum number of points, calculate a simple line when maximum distance between two of the plurality of points exceeds a threshold number.