Indian-American develops imaging system to track moods

Toronto, Dec 4 : We might never know what evil lurks in the hearts of humans, but Prabir Bhattacharya's computers might.

The Indian-American scientist at Concordia University is developing a computer image processing system that detects and classifies facial expressions.

The system aims at taking and analysing photos of individuals, potentially in areas of high traffic where security is a primary concern, such as an airport.

If one could take random photos of the crowd and process them fast enough, there is the potential to identify those individuals who might be problematic, including Jihadi terrorists.

Facial expressions do not actually involve the entire face, but rather specific sets of muscles under the face near the eyes, nose and mouth, according to a Concordia release.

Bhattacharya's system measures 15 key points on the face and then compares these measures against images of identifiable facial expressions.

Although there is great variety in expression across both individuals and cultures, the pair has identified seven basic expressions that seem to be relatively universal.

These results were recently published by Verlag Dr. Müller in Classification of Human Facial Expression: A Prospective Application of Image Processing and Machine Learning.