Ensemble of Hankel matrices for face emotion recognition

Risultato della ricerca: Paper

6 Citazioni (Scopus)

Abstract

In this paper, a face emotion is considered as the result of the composition of multiple concurrent signals, each corresponding to the movements of a specific facial muscle. These concurrent signals are represented by means of a set of multi-scale appearance features that might be correlated with one or more concurrent signals. The extraction of these appearance features from a sequence of face images yields to a set of time series. This paper proposes to use the dynamics regulating each appearance feature time series to recognize among different face emotions. To this purpose, an ensemble of Hankel matrices corresponding to the extracted time series is used for emotion classification within a framework that combines nearest neighbor and a majority vote schema. Experimental results on a public available dataset show that the adopted representation is promising and yields state-of-the-art accuracy in emotion classification.
Lingua originaleEnglish
Stato di pubblicazionePublished - 2015

Fingerprint

Emotion Recognition
Hankel Matrix
Face recognition
Time series
Ensemble
Face
Concurrent
Muscle
Vote
Schema
Nearest Neighbor
Chemical analysis
Emotion
Experimental Results

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)

Cita questo

@conference{3a73003e63ca42fcb8d2b6b603856533,
title = "Ensemble of Hankel matrices for face emotion recognition",
abstract = "In this paper, a face emotion is considered as the result of the composition of multiple concurrent signals, each corresponding to the movements of a specific facial muscle. These concurrent signals are represented by means of a set of multi-scale appearance features that might be correlated with one or more concurrent signals. The extraction of these appearance features from a sequence of face images yields to a set of time series. This paper proposes to use the dynamics regulating each appearance feature time series to recognize among different face emotions. To this purpose, an ensemble of Hankel matrices corresponding to the extracted time series is used for emotion classification within a framework that combines nearest neighbor and a majority vote schema. Experimental results on a public available dataset show that the adopted representation is promising and yields state-of-the-art accuracy in emotion classification.",
keywords = "Classification; Emotion; Face processing; Hankel matrix; LTI systems; Computer Science (all); Theoretical Computer Science",
author = "{La Cascia}, Marco and {Lo Presti}, Liliana",
year = "2015",
language = "English",

}

TY - CONF

T1 - Ensemble of Hankel matrices for face emotion recognition

AU - La Cascia, Marco

AU - Lo Presti, Liliana

PY - 2015

Y1 - 2015

N2 - In this paper, a face emotion is considered as the result of the composition of multiple concurrent signals, each corresponding to the movements of a specific facial muscle. These concurrent signals are represented by means of a set of multi-scale appearance features that might be correlated with one or more concurrent signals. The extraction of these appearance features from a sequence of face images yields to a set of time series. This paper proposes to use the dynamics regulating each appearance feature time series to recognize among different face emotions. To this purpose, an ensemble of Hankel matrices corresponding to the extracted time series is used for emotion classification within a framework that combines nearest neighbor and a majority vote schema. Experimental results on a public available dataset show that the adopted representation is promising and yields state-of-the-art accuracy in emotion classification.

AB - In this paper, a face emotion is considered as the result of the composition of multiple concurrent signals, each corresponding to the movements of a specific facial muscle. These concurrent signals are represented by means of a set of multi-scale appearance features that might be correlated with one or more concurrent signals. The extraction of these appearance features from a sequence of face images yields to a set of time series. This paper proposes to use the dynamics regulating each appearance feature time series to recognize among different face emotions. To this purpose, an ensemble of Hankel matrices corresponding to the extracted time series is used for emotion classification within a framework that combines nearest neighbor and a majority vote schema. Experimental results on a public available dataset show that the adopted representation is promising and yields state-of-the-art accuracy in emotion classification.

KW - Classification; Emotion; Face processing; Hankel matrix; LTI systems; Computer Science (all); Theoretical Computer Science

UR - http://hdl.handle.net/10447/153960

UR - http://springerlink.com/content/0302-9743/copyright/2005/

M3 - Paper

ER -