Emotion Recognition

Emotion Recognition

Abstract :

For a computer to be able to interact with humans, it needs to have the communication skills of humans. One of these skills is the ability to understand the emotional state of the person. The most expressive way humans display emotions is through facial expressions. This work focuses on the strengths and the limitations of systems based on facial expressions and speech. When we smile, frown or grimace, thousands of tiny facial muscles are at work. ERS creates a map in a 3D format, selecting points on a face that can be used as matching points. Then a mathematical algorithm is matched to the movements and facial expressions are calculated based on facial points such as lip curvature, eyebrow position, and cheek contraction. The software detects happiness, disgust, fear, anger, surprise and sadness with great accuracy. Marketers increasingly use this technology to determine what gives consumers bliss. This technology may be used to detect if a driver is getting sleepy at the wheel. This new technology would be used in market research, customer service, patient evaluation, terrorist identification, prisoner’s behaviour and hence the national security.

Key Words : Emotion, Facial, Recognition, Speech, Emotion Recognition Software(ERS).

1. Introduction :

Expressions form a significant part of human interactions and providing computers with the ability to recognise and make use of such non-verbal information could open the way to new and exciting paradigms in human-computer interaction. The human face is a key element of non-verbal communication, with our facial expressions acting as a type of social semaphore.

Without the ability to express and recognise emotions, social interaction is less fulfilling, with either or both parties often unable to fully understand the meaning of the other. The importance of signalling emotional state in communication is demonstrated by the use of emoticons in internet chat rooms where...