Scientists teach a computer to recognize attractiveness in women

Apr 04, 2008

“Beauty,” goes the old saying, “is in the eye of the beholder.” But does the beholder have to be human? Not necessarily, say scientists at Tel Aviv University. Amit Kagian, an M.Sc. graduate from the TAU School of Computer Sciences, has successfully “taught” a computer how to interpret attractiveness in women.

Kagian published the findings in the scientific journal Vision Research. Co-authors on the work were Kagian’s supervisors Prof. Eytan Ruppin and Prof. Gideon Dror. The study combined the worlds of computer programming and psychology, an example of the multidisciplinary research for which TAU is world-renowned.

But there’s a more serious dimension to this issue that reaches beyond mere vanity. The discovery is a step towards developing artificial intelligence in computers. Other applications for the software could be in plastic and reconstructive surgery and computer visualization programs such as face recognition technologies.

From Mathematics to Aesthetics

"Until now, computers have been taught how to identify basic facial characteristics, such as the difference between a woman and a man, and even to detect facial expressions," says Kagian.
“But our software lets a computer make an aesthetic judgment. Linked to sentiments and abstract thought processes, humans can make a judgment, but they usually don't understand how they arrived at their conclusions.”

In the first step of the study, 30 men and women were presented with 100 different faces of Caucasian women, roughly of the same age, and were asked to judge the beauty of each face. The subjects rated the images on a scale of 1 through 7 and did not explain why they chose certain scores. Kagian and his colleagues then went to the computer and processed and mapped the geometric shape of facial features mathematically.

Additional features such as face symmetry, smoothness of the skin and hair color were fed into the analysis as well. Based on human preferences, the machine "learned" the relation between facial features and attractiveness scores and was then put to the test on a fresh set of faces.

Says Kagian, "The computer produced impressive results – its rankings were very similar to the rankings people gave." This is considered a remarkable achievement, believes Kagian, because it’s as though the computer “learned” implicitly how to interpret beauty through processing previous data it had received.

Beauty is Golden

The notion that beauty can be boiled down to binary data and interpreted by a mathematical model is nothing new. More than 2,000 years ago the Greek mystic, philosopher and mathematician Pythagoras observed the connection between math, geometry and beauty. He reasoned that features of physical objects corresponding to the “golden ratio” were considered most attractive.

“I know that Plato connected the good to the beautiful,” says Kagian. “Personally, I believe that some kind of universal correctness to beauty exists in nature, an aesthetic interpretation of the
universal truth. But because each of us is trapped with our own human biases and personalized viewpoints, this may detract us from finding the ultimate formula to a complete understanding of beauty.”

Kagian, who studied under the Adi Lautman multidisciplinary program for outstanding students at Tel Aviv University, says that a possible next step is to teach computers how to recognize “beauty” in men. This may be more difficult. Psychological research has shown that there is less agreement as to what defines “male beauty” among human subjects. And his own portrait, jokes Kagian, will not be part of the experiment.

“I would probably blow up the machine,” he says.

Source: American Friends of Tel Aviv University

Explore further: Computer scientists can predict the price of Bitcoin

add to favorites email to friend print save as pdf

Related Stories

Recommended for you

Tablets, cars drive AT&T wireless gains—not phones

8 hours ago

AT&T says it gained 2 million wireless subscribers in the latest quarter, but most were from non-phone services such as tablets and Internet-connected cars. The company is facing pricing pressure from smaller rivals T-Mobile ...

Twitter looks to weave into more mobile apps

8 hours ago

Twitter on Wednesday set out to weave itself into mobile applications with a free "Fabric" platform to help developers build better programs and make more money.

Blink, point, solve an equation: Introducing PhotoMath

10 hours ago

"Ma, can I go now? My phone did my homework." PhotoMath, from the software development company MicroBlink, will make the student's phone do math homework. Just point the camera towards the mathematical expression, ...

Google unveils app for managing Gmail inboxes

10 hours ago

Google is introducing an application designed to make it easier for its Gmail users to find and manage important information that can often become buried in their inboxes.

User comments : 2

Adjust slider to filter visible comments by rank

Display comments: newest first

Truthseeker013
3 / 5 (2) Apr 04, 2008
I'm not too certain about this. Myself, I see all of the women who prance across the world, pausing and posing in front of cameras, and easily 95% of them are, in my eyes, puppy chow. People tend to seek the ideal in their definition of beauty, totally ignorant of the fact that beauty if, far too often, artificially arrived at. I could put myself in front of it, based on the argument that many women I know consider me handsome, and I wager I'd have the same effect on the machine as Kagian says that his face would have.
murray
3 / 5 (2) Apr 05, 2008
Although an impressive achievement for artificial intelligence and robotics, this software simply replicates the behaviour of the humans that are polled as to beauty and does not carry much empirical, biological or philosophical significance. Artifice is part of beauty because true artifice signals capacity (in surplus time, health, wealth, social standing) to endure real cost for display and thus serves as a fairly reliable marker of fitness for sexual selection. What constitutes reliable artifice--to the extent artifice is part of beauty (markers of health being another aspect)--is culturally dependent, but sensitivity t artifice as part of attractiveness seems pan-cultural.