Gesture recognition apparatus, gesture recognition method and program

• US 8,756,508 B2
• Filed: 04/11/2011
• Issued: 06/17/2014
• Est. Priority Date: 06/24/2010
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Ohki, Yoshihito, Shigeta, Osamu
• Primary Examiner(s): PHANTANA ANGKOOL, DAVID
• Application Number:
  US13/084,092
• Publication Number:
  US 20110320949A1
• Time in Patent Office: 1,163 Days
• Field of Search: 715/727, 715/863
• US Class Current: 715/727
• 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 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/177 of tables; using ruled lines

Abstract

There is provided a gesture recognition apparatus including a recognition unit for recognizing a gesture based on a set of gesture information input in a given input period, a prediction unit for predicting the gesture from halfway input gesture information among the set of gesture information, and a notification unit for notifying a user of prediction information about the result of predicting the gesture. A user can confirm what kind of gesture is recognized by continuing to input gesture information through a notification of the prediction information.

Claims

1. A gesture recognition apparatus comprising:

a processor;

a recognition unit configured to recognize a gesture based on a set of gesture information input in a given input period;

a prediction unit configured to predict a type of the gesture from a partially input gesture information among the set of gesture information; and

a notification unit configured to notify a user of prediction information about the result of predicting the gesture,

wherein the prediction information includes a prediction confidence value of the gesture prediction result.

2. The gesture recognition apparatus according to claim 1, wherein the prediction confidence value is represented as a ratio of the partially input gesture information to the set of gesture information.

3. The gesture recognition apparatus according to claim 2, wherein the prediction confidence value sharply increases when the ratio increases.

4. The gesture recognition apparatus according to claim 1, wherein the notification unit initiates a notification of the prediction information when the prediction confidence value is equal to or greater than a given threshold.

5. The gesture recognition apparatus according to claim 4, wherein the notification unit terminates the notification of the prediction information when the set of gesture information is not input in the input period.

6. The gesture recognition apparatus according to claim 1, wherein the notification unit notifies of a list of recognizable gestures when a frequency at which the set of gesture information is not input in the input period is equal to or more than a given threshold.

7. The gesture recognition apparatus according to claim 1, further comprising a second notification unit configured to notify the user of the gesture information.

8. The gesture recognition apparatus according to claim 1, further comprising an input unit configured to input image information as the gesture information.

9. The gesture recognition apparatus according to claim 1, further comprising an input unit configured to input voice information as the gesture information.

10. The gesture recognition apparatus according to claim 1, wherein the type of the gesture is a left swipe or a right swipe.

11. The gesture recognition apparatus according to claim 1, wherein the type of the gesture is a motion performed by a hand.

12. The gesture recognition apparatus according to claim 1, wherein the prediction confidence value indicates a level of confidence of an accuracy of the gesture prediction result.

13. The gesture recognition apparatus according to claim 1, wherein the notification unit notifies the user of the prediction information by providing an indicator depicting a representation of a level of the prediction confidence value.

14. The gesture recognition apparatus according to claim 13, wherein the level of the prediction confidence value increases as the gesture information is fully input.

15. The gesture recognition apparatus according to claim 1, wherein the notification unit notifies the user of the prediction information by providing an first indicator depicting a representation of the type of the recognized gesture and a second indicator depicting a representation of a level of the prediction confidence value.

16. A gesture recognition method comprising the step of recognizing a gesture based on a set of gesture information input in a given input period,

wherein the recognition step includes predicting a type of the gesture from partially input gesture information among the set of gesture information, and notifying a user of prediction information about the result of predicting the gesture, and

wherein the prediction information includes a prediction confidence value of the gesture prediction result.

17. A non-statutory computer-readable medium having embodied thereon a program, which when executed by a computer causes the computer to execute a step of recognizing a gesture based on a set of gesture information input in a given input period,

wherein the recognition step includes predicting a type of the gesture from partially input gesture information among the set of gesture information, and notifying a user of prediction information about the result of predicting the gesture, and

wherein the prediction information includes a prediction confidence value of the gesture prediction result.