Robust facial expression recognition via compressive sensing

Recently, compressive sensing (CS) has attracted increasing attention in the areas of signal processing, computer vision and pattern recognition. In this paper, a new method based on the CS theory is presented for robust facial expression recognition. The CS theory is used to construct a sparse repr...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2012-03, Vol.12 (3), p.3747-3761
Main Authors: Zhang, Shiqing, Zhao, Xiaoming, Lei, Bicheng
Format: Article
Language:English
Subjects:
Affect (Psychology)
compressive sensing
Corruption
corruption and occlusion
Detection
Face recognition
Facial
facial expression recognition
Gabor wavelets representation
Human-computer interaction
local binary patterns
Neural networks
Pattern recognition
Performance evaluation
Recognition
Representations
Sensors
sparse representation
Support vector machines
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, compressive sensing (CS) has attracted increasing attention in the areas of signal processing, computer vision and pattern recognition. In this paper, a new method based on the CS theory is presented for robust facial expression recognition. The CS theory is used to construct a sparse representation classifier (SRC). The effectiveness and robustness of the SRC method is investigated on clean and occluded facial expression images. Three typical facial features, i.e., the raw pixels, Gabor wavelets representation and local binary patterns (LBP), are extracted to evaluate the performance of the SRC method. Compared with the nearest neighbor (NN), linear support vector machines (SVM) and the nearest subspace (NS), experimental results on the popular Cohn-Kanade facial expression database demonstrate that the SRC method obtains better performance and stronger robustness to corruption and occlusion on robust facial expression recognition tasks.
ISSN:1424-8220
1424-8220
DOI:10.3390/s120303747