Earlier we reported software that predicts how a wine will rate in reviews even before it is made. Now, for puber-geek delight, lets try that for women. Tel Aviv University student Amit Kagian, for his master's thesis in computer science, created software that can spot female beauty. Next a 3D cutter that automates the plastic surgery procedure accordingly?
The research, a combination of computer programming and psychological research, was conducted under professors Eytan Ruppin and Gideon Dror and was recently published by the scientific journal Vision Research.
"Our software allows the computer to complete a much more complex task of esthetic judgment, which humans cannot define exactly how they do it. Esthetic judgment is linked to sentiment and more abstract considerations, but now we have made the computer do it."
The researchers revealed that faces who are considered beautiful are average – with no extreme facial characteristics. "The computer learned a mathematical function, however it implicitly learned to prefer average faces," Kagian says. Being the proud owner of a computer science masters myself, I find this not the least surprising. Due to the statistical learning process, the software – by design – will rank average beauty rather than beauty per se. Try ranking uniquely yet gorgeously attractive women like Meril Streep or Uma Thurman to get my point.
Like fast food chains, who sell food without extreme characteristics, designed for people not to dislike and on average like, this software has been designed to recognize 'fast beauty'.
See also: Virtual Miss, Wine = Math, Photoshop Beauties, Ferrari Tomato, Natural Breasts.