METHOD, APPARTAUS AND COMPUTER PROGRAM PRODUCT FOR PROVIDING GESTURE ANALYSIS

• US 20090324008A1
• Filed: 06/27/2008
• Published: 12/31/2009
• Est. Priority Date: 06/27/2008
• Status: Active Grant

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: Nokia Corporation
• Inventors: Xiujuan, Chai, Kongqiao, Wang
• Granted Patent: US 8,194,921 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• 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: G06T 2207/10024 Color image
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 40/107 Static hand or arm

Abstract

A method for providing gesture analysis may include analyzing image data using a skin detection model generated with respect to detecting skin of a specific user, tracking a portion of the image data correlating to a skin region, and performing a gesture recognition for the tracked portion of the image based on comparing features recognized in the skin region to stored features corresponding to a predefined gesture. An apparatus and computer program product corresponding to the method are also provided.

Claims

1. A method comprising:

analyzing image data using a skin detection model generated with respect to detecting skin of a specific user;

tracking a portion of the image data correlating to a skin region; and

performing a gesture recognition for the tracked portion of the image based on comparing features recognized in the skin region to stored features corresponding to a predefined gesture.

2. The method of claim 1, further comprising generating the skin detection model for the specific user prior to analyzing image data.

3. The method of claim 2, wherein generating the skin detection model comprises utilizing a color histogram model to generate the skin model.

4. The method of claim 1, wherein tracking the portion of the image comprises initiating tracking motion of the skin region in response to generation of the skin detection model.

5. The method of claim 1, wherein performing the gesture recognition comprises initiating recognition of gestures in response to detection of a trigger gesture.

6. The method of claim 5, further comprising detecting the trigger gesture based on a frame by frame analysis of a connected region of pixels corresponding to skin pixels subsequent to detecting and neglecting a face region.

7. The method of claim 1, wherein tracking the portion of the image comprises determining a hand region in the image data based at least in part on hand location in a previous frame.

8. The method of claim 1, wherein tracking the portion of the image comprises expanding boundaries of the region and determining a skin cluster within the expanded boundaries to correspond to a hand portion for use in gesture recognition.

9. The method of claim 1, wherein performing gesture recognition comprises comparing a patch-based local texture descriptor for the portion of the image to a plurality of predefined samples.

10. The method of claim 1, further comprising determining whether a particular gesture recognized includes a threshold level of recognitions prior to enabling execution of a function corresponding to the particular gesture recognized.

11. An apparatus comprising a processor configured to:

analyze image data using a skin detection model generated with respect to detecting skin of a specific user;

track a portion of the image data correlating to a skin region; and

perform a gesture recognition for the tracked portion of the image based on comparing features recognized in the skin region to stored features corresponding to a predefined gesture.

12. The apparatus of claim 11, wherein the processor is further configured to perform generating the skin detection model for the specific user prior to analyzing image data.

13. The apparatus of claim 12, wherein the processor is configured to generate the skin detection model by utilizing a color histogram model to generate the skin model.

14. The apparatus of claim 11, wherein the processor is configured to track the portion of the image by initiating tracking motion of the skin region in response to generation of the skin detection model.

15. The apparatus of claim 11, wherein the processor is further configured to perform the gesture recognition by initiating recognition of gestures in response to detection of a trigger gesture.

16. The apparatus of claim 15, wherein the processor is further configured to detect the trigger gesture based on a frame by frame analysis of a connected region of pixels corresponding to skin pixels subsequent to detecting and neglecting a face region.

17. The apparatus of claim 11, wherein the processor is configured to track the portion of the image by determining a hand region in the image data based at least in part on hand location in a previous frame.

18. The apparatus of claim 11, wherein the processor is configured to track the portion of the image by expanding boundaries of the region and determining a skin cluster within the expanded boundaries to correspond to a hand portion for use in gesture recognition.

19. The apparatus of claim 11, wherein the processor is configured to perform gesture recognition by comparing a patch-based local texture descriptor for the portion of the image to a plurality of predefined samples.

20. The apparatus of claim 11, wherein the processor is further configured to determine whether a particular gesture recognized includes a threshold level of recognitions prior to enabling execution of a function corresponding to the particular gesture recognized.

21. A computer program product comprising at least one computer-readable storage medium having computer-executable program code instructions stored therein, the computer-executable program code instructions comprising:

first program code instructions for analyzing image data using a skin detection model generated with respect to detecting skin of a specific user;

second program code instructions for tracking a portion of the image data correlating to a skin region; and

third program code instructions for performing a gesture recognition for the tracked portion of the image based on comparing features recognized in the skin region to stored features corresponding to a predefined gesture.

22. The computer program product of claim 21, further comprising fourth program code instructions for generating the skin detection model for the specific user prior to analyzing image data.

23. The computer program product of claim 22, wherein the fourth program code instructions include instructions for utilizing a color histogram model to generate the skin model.

24. The computer program product of claim 21, wherein the second program code instructions include instructions for initiating tracking motion of the skin region in response to generation of the skin detection model.

25. The computer program product of claim 21, wherein the third program code instructions include instructions for initiating recognition of gestures in response to detection of a trigger gesture.

26. The computer program product of claim 25, further comprising fourth program code instructions for detecting the trigger gesture based on a frame by frame analysis of a connected region of pixels corresponding to skin pixels subsequent to detecting and neglecting a face region.

27. The computer program product of claim 21, wherein the second program code instructions include instructions for determining a hand region in the image data based at least in part on hand location in a previous frame.

28. The computer program product of claim 21, wherein the second program code instructions include instructions for expanding boundaries of the region and determining a skin cluster within the expanded boundaries to correspond to a hand portion for use in gesture recognition.

29. The computer program product of claim 21, wherein the third program code instructions include instructions for comparing a patch-based local texture descriptor for the portion of the image to a plurality of predefined samples.

30. The computer program product of claim 21, further comprising fourth program code instructions for determining whether a particular gesture recognized includes a threshold level of recognitions prior to enabling execution of a function corresponding to the particular gesture recognized.

31. An apparatus comprising:

means for analyzing image data using a skin detection model generated with respect to detecting skin of a specific user;

means for tracking a portion of the image data correlating to a skin region; and

means for performing a gesture recognition for the tracked portion of the image based on comparing features recognized in the skin region to stored features corresponding to a predefined gesture.

32. The apparatus of claim 31, further comprising means for generating the skin detection model for the specific user prior to analyzing image data.