Researchers Developed Facial Expression Recognition Software

Researchers have developed an advanced algorithm which is capable of processing 30 images per second to recognize a persons facial expressions and categorizes them in any of the six prototypes facial expressions like anger, fear, disgust, happiness, sadness and surprise. Though the software is still in the prototype phase but it can still be used on a desktop computer or laptop, the software is also capable of recognizing facial expressions in video sequences in realistic situations.

Well if we talk about the possible applications of this Facial expression detection technology then this Algo can be used in developing advanced human-computer interfaces, in virtual games like second life giving your avatar a more “you” type of looks and expressions, other possible uses could be in making more advanced lie detectors.

How it works:

The system analyses the person’s face (up to 30 images per second) through several boxes, each “attached” to or focusing on part of the user’s face. These boxes monitor the user’s facial movements until they manage to determine what the facial expression is by comparison with the expressions captured from different people (333 sequences) from the Cohn-Kanade database.

The success rate of this system is 89% and what’s good is that this system can work under adverse conditions like variant lightning, sideways facial expressions or camera displacements.

Via ScienceDaily