Firefly-based Facial Expression Recognition: Extended Abstract

Mistry, Kamlesh, Zhang, Li, Zeng, Yifeng and He, Mengda (2017) Firefly-based Facial Expression Recognition: Extended Abstract. In: AAMAS '17: Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems. Association for Computing Machinery, New York. ISBN 9781510855076

Full text not available from this repository. (Request a copy)
Official URL: https://doi.org/10.5555/3091125.3091390

Abstract

Automatic facial expression recognition plays an important role in various application domains such as medical imaging, surveillance and human-robot interaction. This research presents a novel facial expression recognition system with modified Local Binary Patterns (LBP) for feature extraction and a modified firefly algorithm (FA) for feature optimization. First, in order to deal with illumination, scaling and rotation variations, we propose a horizontal, vertical and diagonal neighborhood LBP to extract initial discriminative facial features. Then a modified FA is proposed to reduce the dimensionality of the extracted facial features. This FA variant employs Cauchy and Levy distributions to further mutate the best solution identified by the FA to increase exploration in the search space and avoid premature convergence. The overall system is evaluated using two facial expression databases (i.e. CK.+, and MMI). The proposed system outperforms other heuristic search algorithms such as Genetic Algorithm, Particle Swarm Optimization, and other existing state-of-the-art facial expression recognition research, significantly.

Item Type: Book Section
Uncontrolled Keywords: Facial expression recognition, Feature optimization
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Related URLs:
Depositing User: Paul Burns
Date Deposited: 14 Nov 2018 17:23
Last Modified: 13 Aug 2021 12:04
URI: http://nrl.northumbria.ac.uk/id/eprint/36695

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics