Graphics Reference
In-Depth Information
CHAPTER 4
Multi-Modal Classifier-
Fusion for the Recognition
of Emotions
Martin Schels, Michael Glodek, Sascha Meudt, Stefan
Scherer, Miriam Schmidt, Georg Layher, Stephan
Tschechne, Tobias Brosch, David Hrabal, Steffen Walter,
Harald C. Traue, Günther Palm, Heiko Neumann and
Friedhelm Schwenker
1. Introduction and Motivation
Research activities in the field of human-computer interaction
increasingly addressed the aspect of integrating features that
characterize different types of emotional intelligence . Human emotions
are expressed through different modalities such as speech, facial
expressions, hand or body gestures, and therefore the classification
of human emotions should be considered as a multi-modal pattern
recognition problem. In recent time, a multitude of approaches have
been proposed to enhance the training and recognition of multiple
classifier systems (MCSs) utilizing multiple modalities to classify
human emotional states. The work summarizes the progress of
investigating such systems and presents aspects of the problem namely
fusion architectures and training of statistical classifiers based on
only marginal informative features. Furthermore, it describes how the
effects of missing values, e.g. due to missing sensor data or classifiers
Search WWH ::




Custom Search