Roads to innovation are sometimes surprising. As an example, a researcher at the University of Toronto (UT) used facial-recognition software developed by his professor several years ago and adapted it for plastic surgeons and their patients. In "Look, ma, no scalpel," the Globe and Mail describes how this new software allows you to see very quickly how you would look like with different facial features. This is not the first application that can simulate the results of plastic surgery, but this one is entirely automated. And Modiface -- the name of this AI-based software -- can recognize a face in a single second and updates its own algorithms automatically as it gains more experience. The researchers think this software also could be used by law enforcement personnel and consumers, so a commercial version might be available one day.
This software is based on previous work done at the UT's Artificial Perception Laboratory headed by Professor Parham Aarabi. Alireza Rabi adapted Aarabi's facial-recognition software for plastic surgeons.
The goal was a software program that would use an actual photo to show a person, realistically and in advance, what he or she would look like after having cosmetic surgery. Such a system could put an end to disappointed patients and also help surgeons refine their craft, Mr. Rabi says.
Below are several pictures showing how Modiface works. On the left is the face of a famous person -- but it could be anyone. In the middle are the features of a second person. The right images show you the result of the addition of the two previous ones. ( Credit: Modiface)
You can try Modiface yourself. You just have to upload an image of yourself and merge it with the facial features of Brad Pitt or Hillary Rodham Clinton for example. Here is how Modiface works.
"The first thing the system does is recognize the face and specific features," explains Dr. Parham Aarabi of the University of Toronto. "Once that is done, it is a matter of pointing and clicking on the prompts." The user chooses from a menu that includes hair, eyes, lips or whole face. Click here to try ModiFace for yourself.
But how the system learns?
Dr. Aarabi says the system actually learns from each attempt at reconstructing a face, slowly gaining the ability to correct its own errors (such as putting eyes in the wrong place) and refining its processes. Every three to four weeks the researchers fine tune the system to remove glitches caused by users who might, for example, submit a photo of a dog instead of a person. "Essentially the software amends and updates its own algorithms automatically as it gains more experience," Dr. Aarabi says
An interesting aspect of this project is how it was developed in four separate stages.
The first step was to create algorithms that achieved facial recognition at blazing speed; the second was to create software that would work well in high-traffic areas such as an Internet site. Both those goals have been met, Dr. Aarabi says. Step three is to have plastic surgeons work with the beta version and provide written feedback. The final stage will be to create a commercial product.
For more information, you can read Face Fusion: An Automatic Method For Virtual Plastic Surgery, which was published in the Proceedings of the 2006 International Conference on Information Fusion (Fusion'06), Florence, Italy, July 2006 (PDF format, 6 pages).
And after reading this paper, have fun mixing your face with the one of Paris Hilton or George Clooney.
Sources: Terrence Belford, The Globe and Mail, March 6, 2007; and various websites
You'll find related stories by following the links below.