Emotion Detector Developed Using a Genetic Algorithm

The International Journal of Artificial Intelligence and Soft Computing carries an interesting study on of how a computer is being taught to interpret human emotions based on lip pattern.

The findings will improve the way humans interact with computers and give the disabled people a chance to use computer based communications devices that include voice synthesizers more efficiently.

A unique system was devised by Karthigayan Muthukaruppan of Manipal International University in Selangor, Malaysia, and co-workers. The researchers used a genetic algorithm that gets better with each interation to match irregular ellipse fitting equations to the shape of the human mouth displaying different emotions.  

Photos of people from South-East Asia and Japan was used by the researchers to train the computer to recognize the basic six human emotion. They are happiness, sadness, fear, angry, disgust, surprise and a neutral emotion.

The upper and lower lip is each analyzed as two separate ellipses by the algorithm.

"In recent years, there has been a growing interest in improving all aspects of interaction between humans and computers especially in the area of human emotion recognition by observing facial expression," the team explains. 

The lips remain a crucial part of the outward expression of emotion. The team's algorithm can successfully classify the emotions and a neutral expression described.

The researchers suggest that initial applications of such an emotion detector might provide an opportunity to the disabled patients lacking speech to interact more effectively with computer-based communication devices.