Washington: Indian researchers from Mathura, Uttar Pradesh have reached a step further in face recognition software by developing an emotion detector.
Dev Drume Agrawal, Shiv Ram Dubey and Anand Singh Jalal of the GLA University suggested that the recognition of emotions by future artificial intelligences, in the form of computers or robots, would provide a missing link between the human and machine environments without which appropriate interactions between the two domains might never be entirely successful.
The team had taken a three-phase approach to a software emotion detector. The first involved developing an algorithm that could precisely identify and define the features of the human face. Then, the second analysed the particular positions and shapes of the face. The third phase then associated those features with a person's emotional state to decide whether they are happy, sad, angry, surprised, fearful or disgusted. Preliminary tests gave a 94 percent success rate, the team reported.
The team said that their experimental results suggested that the introduced method was able to support more accurate classification of emotion classification from images of faces. They added that additional refinements to the classification algorithms would improve their emotion detector still further.
The study is published in the International Journal of Computational Vision and Robotics.