Today we're launching a new orkut application in Google Labs called People Hopper that lets you take your profile image and "morph" it into your friend's photo, using publicly available images from other orkut users along the way. No computer graphics tricks are used here, every image along the transition comes from real orkut users.
This new application hops across millions of user images in orkut so that one image is smoothly transformed into another. To do this, People Hopper uses "image matching technology." First, faces are automatically detected in public profile images and normalized in contrast and size. Then, for each image, we find other public profile images that are similar to one another. Finally, when you pick a friend you want to be your end match, we just hop along similar public images, step-by-step, until the connection is made.
It's a fun, new application that also allows you to make new connections. Since the images that show in your Hopper all come from people who've chosen to make their orkut profiles public, you can click through to their profiles to learn more about them and reach out to them.
Curious? Just click to try People Hopper on orkut right now!
We are eager to hear your feedback on how we can make this application more fun and useful. Also, if for any reason you would prefer your profile image not to appear in any Hopper path, you can choose to opt out by visiting our People Hopper homepage. Note that we don't use any face-specific features during this process and no facial recognition technology is involved. It's just simple, automatic image matching to find similar photographs.
Don't forget that a path between the same pair of images is likely to change every few days as new photos are uploaded to orkut, so try it frequently. Have fun matching photos!
Posted by Henry Rowley and Sanjiv Kumar, Google research scientists
This new application hops across millions of user images in orkut so that one image is smoothly transformed into another. To do this, People Hopper uses "image matching technology." First, faces are automatically detected in public profile images and normalized in contrast and size. Then, for each image, we find other public profile images that are similar to one another. Finally, when you pick a friend you want to be your end match, we just hop along similar public images, step-by-step, until the connection is made.
It's a fun, new application that also allows you to make new connections. Since the images that show in your Hopper all come from people who've chosen to make their orkut profiles public, you can click through to their profiles to learn more about them and reach out to them.
Curious? Just click to try People Hopper on orkut right now!
We are eager to hear your feedback on how we can make this application more fun and useful. Also, if for any reason you would prefer your profile image not to appear in any Hopper path, you can choose to opt out by visiting our People Hopper homepage. Note that we don't use any face-specific features during this process and no facial recognition technology is involved. It's just simple, automatic image matching to find similar photographs.
Don't forget that a path between the same pair of images is likely to change every few days as new photos are uploaded to orkut, so try it frequently. Have fun matching photos!
Posted by Henry Rowley and Sanjiv Kumar, Google research scientists
0 comments:
Post a Comment