Skip to content Home Contact Mobile MyRMIT Library A-Z
RMIT UniversityResearch Repository
 

Feature selection for facial expression recognition based on optimization algorithm

Lajevardi, S and Hussain, Z 2009, 'Feature selection for facial expression recognition based on optimization algorithm', in K. Kyamakya (ed.) Proceedings of the 2nd International Workshop on Nonlinear Dynamics and Synchronization, 2009 (INDS '09), Klagenfurt, Austria, 20-21 July 2009, pp. 182-185.

Document type: Conference Paper
Collection: Conference Papers

Title Feature selection for facial expression recognition based on optimization algorithm
Author(s) Lajevardi, S
Hussain, Z
Year 2009
Conference name 2nd International Workshop on Nonlinear Dynamics and Synchronization (INDS'09)
Conference location Klagenfurt, Austria
Conference dates 20-21 July 2009
Proceedings title Proceedings of the 2nd International Workshop on Nonlinear Dynamics and Synchronization, 2009 (INDS '09)
Editor(s) K. Kyamakya
Publisher IEEE
Place of publication Austria
Start page 182
End page 185
Total pages 4
Abstract This paper presents a wrapper approach to feature selection from image sequences and applies it to the facial expression classification problem. The pre-processing phase automatically scans image sequences and detects frames with maximum intensity of facial expression. The features are generated using the log-Gabor filters. A global optimization algorithm genetic algorithm (GA) is adopted to select a sub-set of features based on minimization of the classification error. The wrapper approach is compared with two previously known filter-based feature selection methods: MID-mRMR and MIQ-mRMR. The features are classified using the naive Bayesian (NB) classifier. The average classification rates are: 79% (MIQ-mRMR), 78% (wrapper) and 64% (MID-mRMR). The results from the filter methods did not appear to be significantly effected by the size of the feature subset.
Subjects Signal Processing
Copyright notice © 2009 IEEE
ISBN 978-1-4244-3844-0
 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Access Statistics: 52 Abstract Views  -  Detailed Statistics
Created: Fri, 02 Jul 2010, 13:14:49 EST by Catalyst Administrator