Title: GPSO versus GA in facial emotion detection

Authors: Bashir Mohammed Ghandi; Ramachandran Nagarajan; Sazali Yaacob; Desa Hazry

Addresses: School of Mechatronics Engineering, Universiti Malaysia Perlis (UniMAP), Ulu Pauh, 02600 Arau, Perlis, Malaysia ' School of Mechatronics Engineering, Universiti Malaysia Perlis (UniMAP), Ulu Pauh, 02600 Arau, Perlis, Malaysia ' School of Mechatronics Engineering, Universiti Malaysia Perlis (UniMAP), Ulu Pauh, 02600 Arau, Perlis, Malaysia ' School of Mechatronics Engineering, Universiti Malaysia Perlis (UniMAP), Ulu Pauh, 02600 Arau, Perlis, Malaysia

Abstract: We recently proposed the guided particle swarm optimisation (GPSO) algorithm as a modification to the popular particle swarm optimisation (PSO) algorithm with the objective of solving the facial emotion recognition problem. A real-time facial emotion recognition software was implemented using GPSO and tested with 25 subjects. The result was found to be good both in terms of recognition success rate and recognition speed. As a follow-up, we decided to investigate how our novel (GPSO) approach compares with existing popular classification methods, such as genetic algorithm (GA). We re-implement our emotion recognition software using GA and tested it using the video recordings of the same 25 subjects that were used to test the GPSO-based system. Our results show that while the recognition success rate achieved using GA is still reasonable, the recognition speed is very slow, suggesting that the GA method may not be suitable for real-time emotion recognition applications.

Keywords: emotion detection; genetic algorithms; GAs; facial emotions; facial expressions; guided PSO; particle swarm optimisation; GPSO; emotion recognition; facial recognition; facial emotion; real-time recognition.

DOI: 10.1504/IJAISC.2013.056828

International Journal of Artificial Intelligence and Soft Computing, 2013 Vol.3 No.4, pp.310 - 329

Received: 27 Jul 2012
Accepted: 03 Mar 2013
Published online: 12 Jul 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article