A Combined Rule-Based & Machine Learning Audio-Visual Emotion Recognition Approach

This paper proposes an audio-visual emotion recognition system that uses a mixture of rule-based and machine learning techniques to improve the recognition efficacy in the audio and video paths. The visual path is designed using the Bi-directional Principal Component Analysis (BDPCA) and Least-Squar...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on affective computing 2018-01, Vol.9 (1), p.3-13
Hauptverfasser:	Seng, Kah Phooi, Ang, Li-Minn, Ooi, Chien Shing
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial intelligence audio-visual processing Audio-visual systems Basis functions Discriminant analysis Emotion recognition Feature extraction Machine learning Modules multimodal system Principal component analysis Principal components analysis Radial basis function rule-based Visual discrimination Visual signals
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!