Facial detection zeroes in on micro-expressions

ComputerVision Software is moving beyond the simple boundaries of facial detection, and now is taking that technology one step further to identifying and decoding micro-expressions on faces.

Scientists working with the Machine Vision Group at the University of Oulu in Finland have developed a new system which is able to interpret facial expressions and tell when they betray an individual.

The field of studying micro-expression, which was featured on the television show “Lie to Me,” is difficult to precisely detect even by the most trained of humans. This is because the expressions tend to last between 1/3 and 1/25 of a second, and even standard cameras are incapable of properly detecting them.

However, the Oulu scientists developed a Local Binary Pattern (LBP), which is a special system of increasing the details of an algorithm, which breaks down and further categorizes and classifies expressions.

The use of micro-expressions can range from interviewing suspects who could be untruthful to identifying potential terrorists at an airport, but that’s only the beginning. What other ways can you foresee this technology being used?

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s