X
Business

Replace smileys with your face

According to Technology Review in "The New Face of Emoticons," computer scientists from U.S. and Taiwan have found a new way to personalize your messages. You just need a picture of you -- preferably with a neutral expression -- and their software will show your mood to your correspondent and tell them if you're happy, sad, or angry. The real innovation is that you will not have to transmit the whole image each time. Instead, your original picture will already have been stored on the recipient's device, and the desired expression will be automatically reconstructed when opening your message. Clever idea, which mixes emoticons and avatars, but will it work?
Written by Roland Piquepaille, Inactive

According to Technology Review in "The New Face of Emoticons," computer scientists from U.S. and Taiwan have found a new way to personalize your messages. You just need a picture of you -- preferably with a neutral expression -- and their software will show your mood to your correspondent and tell them if you're happy, sad, or angry. The real innovation is that you will not have to transmit the whole image each time. Instead, your original picture will already have been stored on the recipient's device, and the desired expression will be automatically reconstructed when opening your message. Clever idea, which mixes emoticons and avatars, but will it work?

The "Face Alive Icons" project has been initiated at the University of Pittsburgh by Xin Li, who now works for Google in New York. Interesting fact, isn't?

The computer scientists started with seven common expressions: neutral, happiness, sadness, surprise, anger, disgust, fear. But to reconstruct their images, they reduced this number from seven to four. You can see below how they've implemented their method for the left eye (top) and the mouth (bottom). (Credit: University of Pittsburgh, USA; and Industrial Technology Research Institute, Taiwan)

Face Alive icons construction

Here are some details from the Technology Review article.

This is not the first time that someone has tried to use photos in this way, says Li, who now works for Google in New York City. "But the traditional approach is to just send the image itself," he says. "The problem is, the size will be too big, particularly for low-bandwidth applications like PDAs and cell phones." Other approaches involve having to capture a different photo of the person for each unique emoticon, which only further increases the demand for bandwidth.
Li's solution is not to send the picture each time it is used, but to store a profile of the face on the recipient device. This profile consists of a decomposition of the original photo. Every time the user sends an emoticon, the face is reassembled on the recipient's device in such a way as to show the appropriate expression.

For more information, this research work has been published online on March 12, 2007, by the Journal of Visual Languages and Computing under the name "Face Alive Icons." Unfortunately, the Elsevier group doesn't even provide an abstract -- you need to pay $30 to read the article. But here is a link to a previous paper about these Face Alive Icons (PDF format, 8 pages, 386 KB), which was presented at the Seventeenth International Conference on Software Engineering and Knowledge Engineering (SEKE'05), Taipei, Taiwan, July 14-16, 2005. The above illustrations have been extracted from this paper.

Finally, Li said that this software could be used for distance learning applications. But now that he works for Google, it's possible that it will be used for more mainstream applications than education.

Sources: Duncan Graham-Rowe, for Technology Review, March 27, 2007; and various websites

You'll find related stories by following the links below.

Editorial standards