Attribute State Classification

• US 20120280897A1
• Filed: 05/02/2011
• Published: 11/08/2012
• Est. Priority Date: 05/02/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Moore, Richard E., Finocchio, Mark J., Balan, Alexandru O.
• Granted Patent: US 10,671,841 B2
• Time in Patent Office: Days
• US Class Current: 345/156
• 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: G06F 3/0304 Detection arrangements using opto-electronic means constructional details of pointing devices not related to the detection arrangement using opto-electronic means G06F3/033; optical digitisers G06F3/042
• 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

Attribute state classification techniques are described. In one or more implementations, one or more pixels of an image are classified by a computing device as having one or several states for one or more attributes that do not identify corresponding body parts of a user. A gesture is recognized by the computing device that is operable to initiate one or more operations of the computing device based at least in part of the state classifications of the one or more pixels of one or more attributes.

Claims

1. A method comprising:

classifying one or more pixels of an image by a computing device as having one of several states for one or more attributes that do not identify corresponding body parts of a user; and

recognizing a gesture by the computing device that is operable to initiate one or more operations of the computing device based at least in part of the state classifications of the one or more pixels of one or more attributes.

2. A method as described in claim 1, wherein the image also includes data that describes depth of portions of a body part of the user.

3. A method as described in claim 1, wherein the recognizing involves excluding one or more parts of an object while training the classifier that do not influence a corresponding said attribute.

4. A method as described in claim 1, wherein the recognizing involves combining classifications from multiple pixels to derive a dominate said state of the one or more attributes.

5. A method as described in claim 4, wherein the classifying is performed:

for at least one other attribute that identifies an associated body part of a user; and

uses pixels for the associated body part and excludes from aggregation pixels that are associated with at least one other body part that does not influence the one or more attributes.

6. A method as described in claim 1, wherein the recognizing involves combining classifications across time.

7. A method as described in claim 6, wherein the recognizing across time includes examination of several frames of state from sequential periods of time to identify a sequence that is indicative of the gesture.

8. A method as described in claim 1, wherein at least one of the attributes relates to orientation.

9. A method as described in claim 1, wherein at least one of the attributes relates to a shape.

10. A method as described in claim 1, wherein at least one of the attributes relates to appearance.

11. A method as described in claim 10, wherein the appearance describes a texture or color.

12. A method comprising:

classifying pixels of an image by a computing device as associated with parts of an object and as having one of several states for one or more attributes that relate to the particular parts of an object; and

aggregating the classifications of the one or more attribute states of the pixels by the computing device to derive an aggregate classification for the parts of the object.

13. A method as described in claim 12, wherein the attributes relate to orientation, shape, or appearance of the part of the object.

14. A method as described in claim 12, wherein the parts are body parts of a user of the computing device.

15. A method as described in claim 12, wherein the aggregating is performed by taking an average or a weighted average of the classifications of the attribute states of the pixels.

16. A method as described in claim 12, further comprising initiating one or more operations of the computing device based at least in part of the aggregated classifications.

17. A method comprising:

classifying pixels of an image by a computing device as belonging to particular parts of a body and as having a state for one or more attributes that relate to the parts;

recognizing a gesture by the computing device, which is operable to initiate one or more operations of the computing device, by examining pixels that relate to one or more said parts of the body that define the gesture and excluding pixels that do not relate to the one or more said parts of the body.

18. A method as described in claim 17, wherein the attributes relate to orientation, shape, or appearance of the part of the object.

19. A method as described in claim 17, wherein the recognizing is based at least in part of the classifications of the one or more pixels to the body part and the state of one or more attributes.

20. A method as described in claim 17, wherein the recognizing is based at least in part on aggregating the classifications of the attributes and states of the pixels of the one or more said part of the body by the computing device to derive an aggregate classification.