An Integrated Approach to Emotion Recognition for Advanced Emotional Intelligence

Research output: Chapter in Book/Report/Conference proceedingOther chapter contribution

View graph of relations Save citation

Authors

Research units

Abstract

Emotion identification is beginning to be considered as an essential feature in human-computer interaction. However, most of the studies are mainly focused on facial expression classifications and speech recognition and not much attention has been paid until recently to physiological pattern recognition. In this paper, an integrative approach is proposed to emotional interaction by fusing multi-modal signals. Subjects are exposed to pictures selected from the International Affective Picture System (IAPS). A feature extraction procedure is used to discriminate between four affective states by means of a Mahalanobis distance classifier. The average classifications rate (74.11%) was encouraging. Thus, the induced affective state is mirrored through an avatar by changing its facial characteristics and generating a voice message sympathising with the user’s mood. It is argued that multi-physiological patterning in combination with anthropomorphic avatars may contribute to the enhancement of affective multi-modal interfaces and the advancement of machine emotional intelligence.

Request a copy

Request a copy

Details

Publication date2009
Publication titleHCI 2009: Human-Computer Interaction. Ambient, Ubiquitous and Intelligent Interaction
PublisherSpringer
Pages565-574
ISBN (Electronic)978-3-642-02580-8
ISBN (Print)978-3-642-02579-2
Original languageEnglish

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume5612
ISSN (Print)0302-9743

Employable Graduates; Exploitable Research

Copy the text from this field...