Firefly-based Facial Expression Recognition: Extended Abstract

Kamlesh Mistry, Li Zhang, Yifeng Zeng, Mengda He

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Downloads (Pure)

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. Author.

Original languageEnglish
Title of host publication16th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2017
Place of PublicationNew York
PublisherACM
Pages1643-1645
Number of pages3
Volume3
ISBN (Electronic)9781510855076
DOIs
Publication statusPublished - 8 May 2017
Event16th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2017 - Sao Paulo, Brazil
Duration: 8 May 201712 May 2017

Conference

Conference16th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2017
CountryBrazil
CitySao Paulo
Period8/05/1712/05/17

Fingerprint

Dive into the research topics of 'Firefly-based Facial Expression Recognition: Extended Abstract'. Together they form a unique fingerprint.

Cite this