Performance Review of a Multi-Layer Feed-Forward Neural Network and Normalized Cross Correlation for Facial Expression Identification
2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS 2016): Proceedings 2017
Latifa Greche, N Es-Sbai N, Egons Lavendelis

The paper presents two systems to recognize five facial expressions (anger, surprise, joy, sadness and neutral) and gives a performance review on them. Both systems are developed on the same facial features extraction process which is histograms of oriented gradients extraction. Vectors of facial features are classified by the systems using the following proposed methods: template matching method based on normalized cross correlation, to find the degree of similarity between inputted images and templates stored in a space of vectors, and supervised learning method of a multi-layer feed-forward neural network. Paper results demonstrate that the adopted methods are efficient, accurate and compete one with other. According to the performance review of these two methods on a three experimental databases (Karolinska Directed Emotional Faces, Cohn-Kanade and Chicago Face Database), normalized cross correlation recognize facial expressions rapidly in high resolutions while neural network is slower but more accurate during classification.


Keywords
Multi-layer feed-forward Neural Network, Normalized Cross Correlation, Facial Expression Identification
DOI
10.1109/SITIS.2016.43
Hyperlink
http://ieeexplore.ieee.org/document/7907470/

Greche, L., Es-Sbai N, N., Lavendelis, E. Performance Review of a Multi-Layer Feed-Forward Neural Network and Normalized Cross Correlation for Facial Expression Identification. In: 2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS 2016): Proceedings, Italy, Naples, 28 Nov-1 Dec., 2016. Los Alamitos: IEEE Computer Society, 2017, pp.223-229. ISBN 978-1-5090-5699-6. e-ISBN 978-1-5090-5698-9. Available from: doi:10.1109/SITIS.2016.43

Publication language
English (en)
The Scientific Library of the Riga Technical University.
E-mail: uzzinas@rtu.lv; Phone: +371 28399196