Computers Can Determine Whether You Are Hot or Not

Computers may soon be assessing your social traits simply by taking a picture of your face.

Researchers at the Computer Vision Center in the Autonomous University of Barcelona in Spain and at the Psychology of Princeton University claim to have developed a technology that can determine whether your traits fall in categories such as attractive or threatening with an accuracy level of at least 90 percent.

The idea here is, for example, to use such a system for new human interaction technologies online - or simply services such as partnership sites. "The perception of dominance has been shown to be an important part of social roles at different stages of life, and to play a role in mate selection," said Mario Rojas from the University of Barcelona. "If the information on which the evaluation of faces is based could be automatically learned, it could be modeled and used as a tool for designing better interactive systems."

The scientists said that were able to use machine learning techniques to train a computer system to evaluate nine different facial traits, including attractive, competent, trustworthy, dominant, mean, frightening, extroverted, threatening, and likable.

The algorithm was tested on a set of synthetic facial images that were generated based on the opinions of people which facial features express certain traits, such as trustworthiness or dominance. A subset of these images was used to teach the computer how to read a face and the remaining pictures were used to test what the computer had learned. The result? Three traits, dominant, threatening and mean, were found to be predictable with accuracies between 91 percent and 96 percent.

Another result included the conclusion that the area around the eyes contains more information about attractiveness, while the area around the mouth is more informative about extroversion.