A Multilevel Fusion Approach for Audiovisual Emotion Recognition

Girija CHETTY, Michael WAGNER, Roland GOECKE

Research output: A Conference proceeding or a Chapter in BookChapter

4 Citations (Scopus)
1 Downloads (Pure)

Abstract

This chapter addresses the aspects of facial expression quantification to detect low, medium, and high levels of expressions. It develops an automatic emotion classification technique for recognizing six different facial emotions-anger, disgust, fear, happiness, sadness, and surprise. The authors evaluated two different facial features for this purpose: facial deformation features and marker-based features for extracting facial expression features. The results show that the sectored volumetric difference function (SVDF/VDF) shape transformation features allow better quantification of facial expressions as compared to marker-based features. The further plans for this research will be to find better methods to fuse audiovisual information that can model the dynamics of facial expressions and speech. Segmental level acoustic information can be used to trace the emotions at a frame level.

Original languageEnglish
Title of host publicationEmotion Recognition: A Pattern Analysis Approach
Subtitle of host publicationA Pattern Analysis Approach
EditorsAmit Konar, Aruna Chakraborty
Place of PublicationUSA
PublisherJohn Wiley & Sons
Pages437-460
Number of pages24
ISBN (Electronic)9781118910566
ISBN (Print)9781118130667
DOIs
Publication statusPublished - 2 Jan 2015

Publication series

NameEmotion Recognition: A Pattern Analysis Approach

Fingerprint

Electric fuses
Fusion reactions
Acoustics

Cite this

CHETTY, G., WAGNER, M., & GOECKE, R. (2015). A Multilevel Fusion Approach for Audiovisual Emotion Recognition. In A. Konar, & A. Chakraborty (Eds.), Emotion Recognition: A Pattern Analysis Approach: A Pattern Analysis Approach (pp. 437-460). (Emotion Recognition: A Pattern Analysis Approach). USA: John Wiley & Sons. https://doi.org/10.1002/9781118910566.ch17
CHETTY, Girija ; WAGNER, Michael ; GOECKE, Roland. / A Multilevel Fusion Approach for Audiovisual Emotion Recognition. Emotion Recognition: A Pattern Analysis Approach: A Pattern Analysis Approach. editor / Amit Konar ; Aruna Chakraborty. USA : John Wiley & Sons, 2015. pp. 437-460 (Emotion Recognition: A Pattern Analysis Approach).
@inbook{4a74bc238e154203b90a4efc96bba5d5,
title = "A Multilevel Fusion Approach for Audiovisual Emotion Recognition",
abstract = "This chapter addresses the aspects of facial expression quantification to detect low, medium, and high levels of expressions. It develops an automatic emotion classification technique for recognizing six different facial emotions-anger, disgust, fear, happiness, sadness, and surprise. The authors evaluated two different facial features for this purpose: facial deformation features and marker-based features for extracting facial expression features. The results show that the sectored volumetric difference function (SVDF/VDF) shape transformation features allow better quantification of facial expressions as compared to marker-based features. The further plans for this research will be to find better methods to fuse audiovisual information that can model the dynamics of facial expressions and speech. Segmental level acoustic information can be used to trace the emotions at a frame level.",
keywords = "Audiovisual emotion recognition, Facial expression, Sectored volumetric difference function (SVDF)",
author = "Girija CHETTY and Michael WAGNER and Roland GOECKE",
year = "2015",
month = "1",
day = "2",
doi = "10.1002/9781118910566.ch17",
language = "English",
isbn = "9781118130667",
series = "Emotion Recognition: A Pattern Analysis Approach",
publisher = "John Wiley & Sons",
pages = "437--460",
editor = "Amit Konar and Aruna Chakraborty",
booktitle = "Emotion Recognition: A Pattern Analysis Approach",
address = "United States",

}

CHETTY, G, WAGNER, M & GOECKE, R 2015, A Multilevel Fusion Approach for Audiovisual Emotion Recognition. in A Konar & A Chakraborty (eds), Emotion Recognition: A Pattern Analysis Approach: A Pattern Analysis Approach. Emotion Recognition: A Pattern Analysis Approach, John Wiley & Sons, USA, pp. 437-460. https://doi.org/10.1002/9781118910566.ch17

A Multilevel Fusion Approach for Audiovisual Emotion Recognition. / CHETTY, Girija; WAGNER, Michael; GOECKE, Roland.

Emotion Recognition: A Pattern Analysis Approach: A Pattern Analysis Approach. ed. / Amit Konar; Aruna Chakraborty. USA : John Wiley & Sons, 2015. p. 437-460 (Emotion Recognition: A Pattern Analysis Approach).

Research output: A Conference proceeding or a Chapter in BookChapter

TY - CHAP

T1 - A Multilevel Fusion Approach for Audiovisual Emotion Recognition

AU - CHETTY, Girija

AU - WAGNER, Michael

AU - GOECKE, Roland

PY - 2015/1/2

Y1 - 2015/1/2

N2 - This chapter addresses the aspects of facial expression quantification to detect low, medium, and high levels of expressions. It develops an automatic emotion classification technique for recognizing six different facial emotions-anger, disgust, fear, happiness, sadness, and surprise. The authors evaluated two different facial features for this purpose: facial deformation features and marker-based features for extracting facial expression features. The results show that the sectored volumetric difference function (SVDF/VDF) shape transformation features allow better quantification of facial expressions as compared to marker-based features. The further plans for this research will be to find better methods to fuse audiovisual information that can model the dynamics of facial expressions and speech. Segmental level acoustic information can be used to trace the emotions at a frame level.

AB - This chapter addresses the aspects of facial expression quantification to detect low, medium, and high levels of expressions. It develops an automatic emotion classification technique for recognizing six different facial emotions-anger, disgust, fear, happiness, sadness, and surprise. The authors evaluated two different facial features for this purpose: facial deformation features and marker-based features for extracting facial expression features. The results show that the sectored volumetric difference function (SVDF/VDF) shape transformation features allow better quantification of facial expressions as compared to marker-based features. The further plans for this research will be to find better methods to fuse audiovisual information that can model the dynamics of facial expressions and speech. Segmental level acoustic information can be used to trace the emotions at a frame level.

KW - Audiovisual emotion recognition

KW - Facial expression

KW - Sectored volumetric difference function (SVDF)

UR - http://www.scopus.com/inward/record.url?scp=85016382501&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/multilevel-fusion-approach-audiovisual-emotion-recognition

U2 - 10.1002/9781118910566.ch17

DO - 10.1002/9781118910566.ch17

M3 - Chapter

SN - 9781118130667

T3 - Emotion Recognition: A Pattern Analysis Approach

SP - 437

EP - 460

BT - Emotion Recognition: A Pattern Analysis Approach

A2 - Konar, Amit

A2 - Chakraborty, Aruna

PB - John Wiley & Sons

CY - USA

ER -

CHETTY G, WAGNER M, GOECKE R. A Multilevel Fusion Approach for Audiovisual Emotion Recognition. In Konar A, Chakraborty A, editors, Emotion Recognition: A Pattern Analysis Approach: A Pattern Analysis Approach. USA: John Wiley & Sons. 2015. p. 437-460. (Emotion Recognition: A Pattern Analysis Approach). https://doi.org/10.1002/9781118910566.ch17