D-CIS Publication Database

Publication

Type of publication:Inproceedings
Entered by:DD
Title Automatic bi-modal emotion recognition system based on fusion of facial expressions and emotion extraction from speech
Bibtex cite ID
Booktitle Proceedings of the IEEE Face and Gesture Conference FG2008
Year published 2008
Month September
Note ISBN 978-1-4244-2154-1
Keywords Bi-modal emotion recognition,facial expressions,speech analysis
Abstract
Our software demo package consists of an implementation for an automatic human emotion recognition system. The system is bi-modal and is based on fusing of data regarding facial expressions and emotion that has been extracted from speech signal. We have integrated Viola&Jones face detector (OpenCV), Active Appearance Model AAM (AAM-API) for extracting the face shape and Support Vector Machines (LibSVM) for the classification of emotion patterns. We have used Optical Flow algorithm for computing the features needed for the classification of facial expressions. Beside the integration of all processing components, the software system accommodates our implementation for the data fusion algorithm. Our C++ implementation has a working frame-rate of about 5fps.
Authors
Datcu, Dragos
Rothkrantz, Leon
Topics
=SEE CLASSIFICATION DIFFERENCE FROM OTHERS=
BibTeXBibTeX
RISRIS
Attachments
http://mmi.tudelft.nl/pub/dragos/_fg2008DatcuDemo.pdf (main file)
 
Total mark: 5