Software that recognises facial expressions

Washington, February 29:

Spanish software developers have written a program that can process 30 images per second to read a person’s face in real time, and categorize them into six facial expressions—namely anger, disgust, fear, happiness, sadness, and surprise.

The new algorithm results from the efforts of collaborators from the Technical University of Madrid’s School of Computing (FIUPM) and the Rey Juan Carlos University.

The software’s makers say that it can be applied to video sequences in realistic situations, and even to identify the facial expression of a person seated in front of a computer screen.

They also say that, though their software is just a prototype, it is still capable of working on a desktop computer or even on a laptop.

For determining a person’s facial expression, the system monitors the user’s facial movements, and compares them with expressions captured from different people (333 sequences) from the Cohn-Kanade database.

The system’s success rate on the Cohn-Kanade database is 89%, and it can work under adverse conditions where ambient lighting, frontal facial movements or camera displacements produce major changes in facial appearance.

The makers of the software say that it may help advance human-computer interfaces by enabling the construction of avatars that really do simulate a person’s facial expression, something that may be of interest to the video games industry.

The technology may also benefit electronic commerce (E-commerce) by enabling a seller to identify through a person’s facial expressions whether he is likely to make a purchase, or even to gauge customers’ satisfaction.

The results of this research were published in the journal Pattern Analysis and Applications.