Exploiting visual quasi-periodicity for automated chewing event detection using active appearance models and support vector machines

Steven Cadavid, Mohamed Abdel-Mottaleb

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

We present a method that automatically detects chewing events in surveillance video of a subject. Firstly, an Active Appearance Model (AAM) is used to track a subject's face across the video sequence. It is observed that the variations in the AAM parameters across chewing events demonstrate a distinct periodicity. We utilize this property to discriminate between chewing and non-chewing facial actions such as talking. A feature representation is constructed by applying spectral analysis to a temporal window of model parameter values. The estimated power spectra subsequently undergo non-linear dimensionality reduction via spectral regression. The low-dimensional representations of the power spectra are employed to train a Support Vector Machine (SVM) binary classifier to detect chewing events. Experimental results yielded a cross-validated percentage agreement of 93.4%, indicating that the proposed system provides an efficient approach to automated chewing detection.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages1714-1717
Number of pages4
DOIs
StatePublished - Nov 18 2010
Event2010 20th International Conference on Pattern Recognition, ICPR 2010 - Istanbul, Turkey
Duration: Aug 23 2010Aug 26 2010

Other

Other2010 20th International Conference on Pattern Recognition, ICPR 2010
CountryTurkey
CityIstanbul
Period8/23/108/26/10

Fingerprint

Mastication
Support vector machines
Power spectrum
Spectrum analysis
Classifiers

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Exploiting visual quasi-periodicity for automated chewing event detection using active appearance models and support vector machines. / Cadavid, Steven; Abdel-Mottaleb, Mohamed.

Proceedings - International Conference on Pattern Recognition. 2010. p. 1714-1717 5597478.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cadavid, S & Abdel-Mottaleb, M 2010, Exploiting visual quasi-periodicity for automated chewing event detection using active appearance models and support vector machines. in Proceedings - International Conference on Pattern Recognition., 5597478, pp. 1714-1717, 2010 20th International Conference on Pattern Recognition, ICPR 2010, Istanbul, Turkey, 8/23/10. https://doi.org/10.1109/ICPR.2010.424
@inproceedings{6f377139cd254e6a9f5218b60faa70c2,
title = "Exploiting visual quasi-periodicity for automated chewing event detection using active appearance models and support vector machines",
abstract = "We present a method that automatically detects chewing events in surveillance video of a subject. Firstly, an Active Appearance Model (AAM) is used to track a subject's face across the video sequence. It is observed that the variations in the AAM parameters across chewing events demonstrate a distinct periodicity. We utilize this property to discriminate between chewing and non-chewing facial actions such as talking. A feature representation is constructed by applying spectral analysis to a temporal window of model parameter values. The estimated power spectra subsequently undergo non-linear dimensionality reduction via spectral regression. The low-dimensional representations of the power spectra are employed to train a Support Vector Machine (SVM) binary classifier to detect chewing events. Experimental results yielded a cross-validated percentage agreement of 93.4{\%}, indicating that the proposed system provides an efficient approach to automated chewing detection.",
author = "Steven Cadavid and Mohamed Abdel-Mottaleb",
year = "2010",
month = "11",
day = "18",
doi = "10.1109/ICPR.2010.424",
language = "English",
isbn = "9780769541099",
pages = "1714--1717",
booktitle = "Proceedings - International Conference on Pattern Recognition",

}

TY - GEN

T1 - Exploiting visual quasi-periodicity for automated chewing event detection using active appearance models and support vector machines

AU - Cadavid, Steven

AU - Abdel-Mottaleb, Mohamed

PY - 2010/11/18

Y1 - 2010/11/18

N2 - We present a method that automatically detects chewing events in surveillance video of a subject. Firstly, an Active Appearance Model (AAM) is used to track a subject's face across the video sequence. It is observed that the variations in the AAM parameters across chewing events demonstrate a distinct periodicity. We utilize this property to discriminate between chewing and non-chewing facial actions such as talking. A feature representation is constructed by applying spectral analysis to a temporal window of model parameter values. The estimated power spectra subsequently undergo non-linear dimensionality reduction via spectral regression. The low-dimensional representations of the power spectra are employed to train a Support Vector Machine (SVM) binary classifier to detect chewing events. Experimental results yielded a cross-validated percentage agreement of 93.4%, indicating that the proposed system provides an efficient approach to automated chewing detection.

AB - We present a method that automatically detects chewing events in surveillance video of a subject. Firstly, an Active Appearance Model (AAM) is used to track a subject's face across the video sequence. It is observed that the variations in the AAM parameters across chewing events demonstrate a distinct periodicity. We utilize this property to discriminate between chewing and non-chewing facial actions such as talking. A feature representation is constructed by applying spectral analysis to a temporal window of model parameter values. The estimated power spectra subsequently undergo non-linear dimensionality reduction via spectral regression. The low-dimensional representations of the power spectra are employed to train a Support Vector Machine (SVM) binary classifier to detect chewing events. Experimental results yielded a cross-validated percentage agreement of 93.4%, indicating that the proposed system provides an efficient approach to automated chewing detection.

UR - http://www.scopus.com/inward/record.url?scp=78149492153&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78149492153&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2010.424

DO - 10.1109/ICPR.2010.424

M3 - Conference contribution

SN - 9780769541099

SP - 1714

EP - 1717

BT - Proceedings - International Conference on Pattern Recognition

ER -