COMPUTER VISION BASED HAND IDENTIFICATION

• US 20130279756A1
• Filed: 12/15/2011
• Published: 10/24/2013
• Est. Priority Date: 12/16/2010
• Status: Abandoned Application

• Current Assignee: PointGrab Ltd.
• Original Assignee: PointGrab Ltd.
• Inventors: Menadeva, Ovadya, Eilat, Eran, Kaplan, Amir, Perski, Haim
• Application Number:
  US13/993,326
• Publication Number:
  US 20130279756A1
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06V 40/113 Recognition of static hand signs
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113

Abstract

There is provided a method for computer vision based hand identification, the method comprising: obtaining an image of an object; detecting in the image at least two different types of shape features of the object; obtaining information of each type of shape feature; combining the information of each type of shape feature to obtain combined information; and determining that the object is a hand based on the combined information.

Claims

1. A method for computer vision based hand identification, the method comprising:

obtaining an image of an object;

detecting in the image at least two different types of shape features of the object;

obtaining information of each type of shape feature;

combining the information of each type of shape feature to obtain combined information; and

determining that the object is a hand based on the combined information.

2. The method according to claim 1 comprising:

applying on the image at least two types of detectors, said detectors configured to detect shape features of the object,

obtaining information from the two detectors;

combining the information from the two detectors to obtain combined information; and

determining that the object is a hand based on the combined information.

3. The method according to claim 1 wherein a shape feature comprises shape boundary features.

4. The method according to claim 3 wherein the shape boundary feature comprises contour information.

5. The method according to claim 1 wherein a shape feature comprises appearance features enclosed within boundaries of the object.

6. The method according to claim 1 wherein combining the information of each type of shape feature comprises assigning a weight to each information.

9. The method according to claim 6 wherein the weight assigned to each information is based on the reliability of each type of feature.

10. The method according to claim 9 wherein the reliability of each type of feature is specific to a frame environment.

11. The method according to claim 1 comprising combining the information of each type of feature and a value of a parameter which is unrelated to the features, to obtain combined information;

and

determining that the object is a hand based on the combined information.

12. The method according to claim 11 wherein the parameter that is unrelated to the features comprises pattern of object movement or a number of frames in which an object is detected.

13. The method according to claim 12 wherein the pattern of object movement comprises movement of the object in a predefined pattern.

18. The method according to claim 1 comprising

obtaining a plurality of images of an object;

subtracting two consecutive images of the object to obtain a motion image of the object; and

applying a contour detector to find contour features in the motion image.

25. The method of claim 18 comprising tracking the identified hand and controlling the device based on the tracking of the identified hand.

26. The method of claim 18 comprising identifying the hand by combining information from at least two different types of shape features of an imaged object and information regarding movement of the imaged object.

7. (canceled)

8. (canceled)

14. (canceled)

15. (canceled)

16. (canceled)

17. (canceled)

19. A system for computer vision based hand identification, the system comprising

a detector, said detector configured to detect at least two different types of shape features of an object from an image of the object, to obtain information of the two different types of shape features;

and

a processor to combine the information of the two different types of shape features to obtain combined information and to determine that the object is a hand based on the combined information.

20. The system according to claim 19 comprising two different types of detectors.

21. The system according to claim 20 comprising an image sensor to obtain an image of the object, said image sensor in communication with the at least two types of detectors.

22. The system according to claim 19 comprising a processor to generate a user command based on image analysis of the object determined to be a hand.

23. The system according to claim 22 wherein the user command is to be accepted by a device, selected from the group consisting of a TV, DVD player, PC, mobile phone, camera, STB (Set Top Box) and a streamer.

24. A method for computer vision based control of a device, the method comprising:

obtaining an image of an object;

identifying a hand in the image by combining information from at least two different types of shape features of an imaged object; and

controlling the device based on the identification of the hand.