Automatic facial expression recognition: Feature extraction and selection

Lajevardi, S and Hussian, Z 2012, 'Automatic facial expression recognition: Feature extraction and selection', Signal, Image and video processing, vol. 6, no. 1, pp. 159-169.


Document type: Journal Article
Collection: Journal Articles

Title Automatic facial expression recognition: Feature extraction and selection
Author(s) Lajevardi, S
Hussian, Z
Year 2012
Journal name Signal, Image and video processing
Volume number 6
Issue number 1
Start page 159
End page 169
Total pages 11
Publisher Springer
Abstract In this paper,we investigate feature extraction and feature selection methods as well as classification methods for automatic facial expression recognition (FER) system. The FER system is fully automatic and consists of the following modules: face detection, facial detection, feature extraction, selection of optimal features, and classification. Face detection is based on AdaBoost algorithm and is followed by the extraction of frame with the maximum intensity of emotion using the inter-frame mutual information criterion. The selected frames are then processed to generate characteristic features using different methods including: Gabor filters, log Gabor filter, local binary pattern (LBP) operator, higher-order local autocorrelation (HLAC) and a recent proposed method calledHLAC-like features (HLACLF). Themost informative features are selected based on both wrapper and filter feature selection methods. Experiments on several facial expression databases show comparisons of different methods.
Subject Signal Processing
Keyword(s) Facial expression recognition
Emotion recognition
Mutual information
Higher order auto correlation
Gabor filters
DOI - identifier 10.1007/s11760-010-0177-5
Copyright notice © Springer-Verlag London Limited 2010
ISSN 1863-1703
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 53 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 36 times in Scopus Article | Citations
Altmetric details:
Access Statistics: 264 Abstract Views  -  Detailed Statistics
Created: Thu, 12 May 2011, 08:08:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us