Web Cam Based User Interaction

• US 20100211918A1
• Filed: 02/17/2009
• Published: 08/19/2010
• Est. Priority Date: 02/17/2009
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Wang, Shuo, Liang, Xiao, Zou, Xin, Zhang, Weiwei
• Granted Patent: US 8,732,623 B2
• Time in Patent Office: Days
• US Class Current: 715/863
• CPC Class Codes: G06F 3/012 Head tracking input arrangements
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06V 30/32 Digital ink
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16

Abstract

This document describes tools for inputting data into a computer via the movement of features of a user as detected by a webcam or other input device. This is accomplished by a user moving his or her features in view of a webcam. The webcam or other input device then detects the presence and motion of the feature(s) and converts these motions into input signals to execute predetermined input instructions.

Claims

1. One or more processor-accessible media comprising processor-executable instructions that, when executed, direct a device to perform actions comprising:

a. detecting a head of a user and a mouth of the user;

b. detecting the user opening the mouth and, in response to the detecting of the user opening the mouth, creating a start point of a character stroke on a display;

c. detecting the user moving the head horizontally and, in response to the detecting of the horizontal user head movement, extending the character stroke horizontally on the display;

d. detecting the user move the head vertically and, in response to the detecting of the vertical user head movement, extending the character stroke vertically on the display;

e. detecting the user moving the head diagonally and, in response to the detecting of the diagonal user head movement, extending the character stroke diagonally on the display; and

f. detecting the user closing the mouth and, in response to detecting that the user closed the mouth, creating an end point of the character stroke on the display.

2. The one or more processor-accessible media of claim 1, further comprising detecting via a webcam.

3. The one or more processor-accessible media of claim 1, further comprising displaying a real-time image of the user on the display via a webcam.

4. The one or more processor-accessible media of claim 1, further comprising detecting head movement toward and away from a webcam, and in response, executing a desired action.

5. The one or more processor-accessible media of claim 1, further comprising converting a stroke into a text character that is recognized by a word processing application via Optical Character Recognition (OCR).

6. One or more processor-accessible media comprising processor-executable instructions that, when executed, direct a device to perform actions comprising:

a. detecting a feature of a user via a webcam;

b. detecting the user positioning the feature in a first manner and, in response to detecting of the user positioning the feature in the first manner, creating a start point of a stroke on a display;

c. detecting the user move the feature in a second manner and, in response to the detecting of the feature moving in the second manner, extending the stroke horizontally, vertically or diagonally on the display; and

d. detecting the user move the feature in a third manner and, in response to the body part moving in the third manner, creating an end point of the stroke on the display.

7. The one or more processor-accessible media of claim 6, wherein the feature comprises a head of the user.

8. The one or more processor-accessible media of claim 6, wherein the feature comprises eyes of the user.

9. The one or more processor-accessible media of claim 6, wherein the feature comprises hands of the user.

10. The one or more processor-accessible media of claim 6, wherein the feature comprises a facial feature of the user.

11. The one or more processor-accessible media of claim 6, wherein the feature comprises legs of the user.

12. The one or more processor-accessible media of claim 6, further comprising displaying a real-time video of the user on the display via the webcam.

13. The one or more processor-accessible media of claim 6, further comprising detecting head movement toward and away from the webcam and, in response, executing a desired action.

14. The one or more processor-accessible media of claim 6, further comprising converting a stroke into a text character that is recognized by a word processing application via Optical Character Recognition (OCR).

15. One or more processor-accessible media comprising processor-executable instructions that, when executed, direct a device to perform actions comprising:

a. detecting a feature of a user;

b. detecting the user positioning the feature in a first predetermined manner and, in response to the detecting of the user positioning the feature in the first predetermined manner, creating a start point of a stroke on a display; and

c. detecting the user move the feature in a second predetermined manner and, in response to the detecting of the feature moving in the second predetermined manner, extending the stroke on the display.

16. The one or more processor-accessible media of claim 15, further comprising detecting via a webcam.

17. The one or more processor-accessible media of claim 15, wherein the feature comprises hands of the user.

18. The one or more processor-accessible media of claim 15, further comprising displaying a real-time video of the user on the display via a webcam.

19. The one or more processor-accessible media of claim 15, further comprising detecting head movement toward and away from a webcam that detects movement of the user and, in response, executing a desired action.

20. The one or more processor-accessible media of claim 15, further comprising converting a stroke into a text character that is recognized by a word processing application via Optical Character Recognition (OCR).