Mind-reading still might be a ways off, but the MIT Media Lab has come up with spectacles that can read a person's emotions. These social X-ray specs have a built-in camera linked to software that analyzes facial expressions.
The special glasses were developed by Rosalind Picard, Rana el Kaliouby, and Simon Baron-Cohen. The research was originally intended to help autistic individuals in conversations where they would lack some social instincts to pick up a person's emotions.
The prototype glasses are built with a rice-grain-sized camera wired to a computer the size of a deck of cards. The camera is able to track 24 feature points of facial expression. The linked computer scans the micro expressions for how often and how long they appear, while comparing the data with a bank of expressions created actors and identified by volunteers.
The glasses relay a summarized version of emotional information to the user through an earpiece, telling the user the subject emotional state, such as confused or disagreement. There's also light that signifies agreement and conflict by turning green and red.
So far the device is effective in getting autistic individuals more involved in conversations. Picard and el Kaliouby also found that an average person could only correctly interpret expressions 54-percent of the time where as the glasses could gauge 64-percent. While the social X-ray specs are effective, Picard still says that the glasses are not a foolproof lie detector. The glasses can be tricked but it requires constant concentration and coercion.
The technology is currently being used by Picard and el Kaliouby's company, Affectiva, to provide deeper market testing for adverts and movies. Meanwhile another colleague of the researchers, Mohammed Hoque has jumped onboard to tune the algorithms detect subtle differences between expressions, such as smiles of delight and frustration and 10 different types of Japanese smiles.
New Scientist has the full details in their story; it's worth a read if you're at all interested int his technology.
[via New Scientist]