Voice recognition and gaze-tracking for a camera
View Patent ↗A method is disclosed for enabling user friendly interaction with a camera system. Specifically, the inventive method has several aspects to improve the interaction with a camera system, including voice recognition, gaze tracking, touch sensitive inputs and others. The voice recognition unit is operable for, among other things, receiving multiple different voice commands, recognizing the vocal commands, associating the different voice commands to one camera command and controlling at least some aspect of the digital camera operation in response to these voice commands. The gaze tracking unit is operable for, among other things, determining the location on the viewfinder image that the user is gazing upon. Another aspect of the invention provides for gesture recognition to be used to interface with and control the camera system.
1. A method of human-interfacing to a camera system having automatic focusing capability and a voice recognition system including at least two microphones, at least one microphone placed on the front of the camera system and at least one microphone placed on the back of the camera system, comprising:
(a) displaying an image for the user to view, the image being representative of the picture the camera system will take;
(b) determining an approximate location on the image that the user is viewing;
(c) indicating to the viewer the approximate location being viewed;
(d) receiving a sound at a microphone placed on the front of the camera system and at a microphone placed on the back of the camera system;
(e) directing the sound from each microphone to a processor in the camera system;
(f) processing the sound to determine spatial information and determine if the primary source of the sound is behind the camera system, and filter background noise; and
(g) recognizing the sound is associated with a command only if the primary source of the sound is behind the camera system, the command indicating that the user desires to modify a setting giving greater importance to the location on the image that the user is viewing.
2. The method of claim 1 wherein the camera setting is a focus setting.
3. The method of claim 1 wherein the camera setting is an aperture setting.
4. The method of claim 1 wherein the camera setting is an amount of flash.
5. The method of claim 1 further comprising determining an amount of flash to be used to properly expose the approximate location within the image that the user is viewing.
6. The method of claim 1 wherein the camera system is integrated with a cellular phone.
7. The method of claim 1 further comprising taking a picture in response to detecting a wink from the user.
8. A method of performing a camera operation in a camera with at least two microphones, at least one microphone placed on the front of the camera and at least one microphone placed on the back of the camera, comprising:
(a) displaying an image to be captured by the camera to a user;
(b) detecting an approximate location within the displayed image that a user is gazing;
(c) receiving a sound from the microphones;
(d) determining if the primary source of the sound is behind the camera;
(e) recognizing the sound as a command to perform a camera operation only if the primary source of the sound is behind the camera;
(f) performing the camera operation in response to having recognized the sound; and
(g) giving greater importance to the approximate location within the image that the user is gazing at in determining a setting for the camera operation by more heavily weighting the approximate location within the image that the user is gazing than other areas of the displayed image.
9. The method of claim 8 wherein greater importance is given to the approximate location within the image that the user is gazing at in determining a flash setting.
10. The method of claim 8 wherein greater importance is given to the approximate location within the image that the user is gazing at in determining a focus setting.
11. The method of claim 8 wherein greater importance is given to the approximate location within the image that the user is gazing at in determining an aperture setting.
12. The method of claim 8 wherein the camera is integrated with a cellular phone.
13. The method of claim 8 further comprising taking a picture in response to detecting a wink from the user.
14. A method of performing a camera operation in a camera with at least two microphones, at least one microphone placed on the front of the camera and at least one microphone placed on the back of the camera, comprising:
(a) displaying an image to be captured by the camera to a user;
(b) detecting an approximate location within the displayed image that a user is gazing;
(c) receiving a sound from the microphones;
(d) determining if the primary source of the sound is behind the camera;
(e) recognizing the sound as a command to perform a camera operation only if the primary source of the sound is behind the camera;
(f) performing the camera operation in response to having recognized the sound; and
(g) giving greater importance to the approximate location within the image that the user is gazing at in determining an amount of flash to be used for the capture of the displayed image by more heavily weighting the approximate location within the image that the user is gazing at than other areas of the displayed image.
15. The method of claim 14 wherein greater importance is given to the approximate location within the image that the user is gazing at in determining a focus setting.
16. The method of claim 14 wherein greater importance is given to the approximate location within the image that the user is gazing at in determining an aperture setting.
17. The method of claim 14 wherein the camera is integrated with a cellular phone.
18. The method of claim 14 further comprising taking a picture in response to detecting a wink from the user.