Abstract:
Facial expression recognition is a major task
concerning human-computer interaction issue. Plenty of
techniques were proposed to recognize an expression
either in still images or image sequences. However, most
of them were applied for images recorded under
controlled recording conditions. This paper aims at
describing Gabor filters’ application to extract facial
features required to classify facial expression when the
images are disturbed by various noise levels. The
experiments indicate a satisfactory performance for
Gabor filters when compared to another state-of-the-art
method named principal component analysis (PCA).
