A recurrent neural model for parameter estimation of mixed emotions from facial expressions of the subjects

  • Authors:
  • M. Ghosh;A. Chakraborty;A. Acharya;A. Konar;B. K. Panigrah

  • Affiliations:
  • Artificial Intelligence Lab., ETCE Dept., Jadavpur University, Kolkata;Dept. of Computer Sc. and Engg., St. Thomas' College of Engg. and Tech., Kolkata;Artificial Intelligence Lab., ETCE Dept., Jadavpur University, Kolkata;Artificial Intelligence Lab., ETCE Dept., Jadavpur University, Kolkata;Dept. of Electrical Engineering, lIT Delhi

  • Venue:
  • IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

The paper provides a novel approach to represent cooperative/competitive interactions among coexisting emotions by a recurrent neural dynamics, and proposes a scheme for parameter estimation of the dynamics from the facial expressions of the subjects, psychologically excited by audiovisual stimulus taken from select commercial movies. Conditions for chaotic and stable behavior of the neural dynamics have been derived, and the same parametric conditions are used to predict the fluctuating dynamic behavior of emotions by testing the satisfiability of the conditions over the measured range of parameters.