Current face recognition techniques tend to work well when recognizing faces under small variations in lighting, facial expression and pose, but deteriorate under more extreme conditions. In this paper, a face recognition system to recognize faces of known individuals, despite variations in facial expression due to different emotions, is developed. The eigenface approach is used for feature extraction. Classification methods include Euclidean distance, back propagation neural network and generalized regression neural network. These methods yield 100% recognition accuracy when the training database is representative, containing one image representing the peak expression for each emotion of each person apart from the neutral expression. The feature vectors used for comparison in the Euclidean distance method and for training the neural network must be all the feature vectors of the training set. These results are obtained for a face database consisting of only four persons.
Liyanage C. De Silva,
Kho Guan Poh Esther,
"Emotion-independent face recognition", Proc. SPIE 4310, Visual Communications and Image Processing 2001, (29 December 2000); doi: 10.1117/12.411839; https://doi.org/10.1117/12.411839