Alert icon
We're changing our privacy policy. This stuff matters.  Learn more  Dismiss

Opera Face Gestures Beta

Loading...

Sign in or sign up now!
12,834
Loading...
Alert icon
Sign in or sign up now!
Alert icon
There is no Interactive Transcript.

Uploaded by on Apr 22, 2009

Videos annotations weren't working. You will need to turn on subtitles.

I've decided to turn the joke into a reality by developing a prototype that can recognize some of the facial gestures in the Opera Face Gestures video.

Eyebrows down = Scroll down
Eyebrows up = Scroll up
Blink both eyes twice = New tab
Blink left eye twice = Back
Blink right eye twice = Forward
Lick = Save bookmark

Opera isn't really releasing this but I am. I'm not an Opera employee or affiliated with Opera in anyway. I really liked their video for April Fools and it inspired me to make a program that does some of the things found in their video. It will perform actions found on certain facial gestures but lighting plays an important role in how sensitive the detected movements are.

Here is the link to the blog article and where you can download the program...

http://www.smert.net/2009/04/23/opera-face-gestures-beta/

Music: Romeo X Juliet by Musicshake

Link to this comment:

Share to:

Video Responses

This video is a response to Opera Face Gestures
see all

All Comments (13)

Sign In or Sign Up now to post a comment!
  • opera supremacy !

  • Too bad I can't enable "Face Gestures" on Opera :(

  • Great idea!

  • PLEASE TELL ME IS THIS FAKED?!

  • I'm just using a webcam (Logitech QuickCam Pro for Notebooks). Eye tracking can be done with a webcam but I'm not sure how it compares to other solutions. The code for this is written in Python and you can find the instructions for setting everything up on my blog. The link is under more info.

  • Thank you so much I love the music

  • Basically, the way this could work is as follows:

    1) Every 200ms detect face, and within its boundaries detect features (e.g., mouth, etc). Reinitialize the meanshift trackers for each one (you may need to experiment to see which tracker works best).

    2) Track the features (and possibly the face). If the features tracked get outside the face boundary go to 1.

    3) For each feature region + extra slack around, compute the motion image as o you do now (to make it efficient).

  • I'm actually not 100% sure it isn't using mean-shift or cam-shift. OpenCV seems to have a specific API for mean-shift (cvMeanShift) so I assume that I'm not.

Loading...
0 / 00Unsaved Playlist Return to active list
    1. Your queue is empty. Add videos to your queue using this button:
      or sign in to load a different list.
    Loading...Loading...Saving...
    • Clear all videos from this list
    • Learn more