Automated classification of gaze direction using spectral regression and support vector machine

Steven Cadavid, Mohammad H. Mahoor, Daniel S Messinger, Jeffrey F. Cohn

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

8 Citations (Scopus)

Abstract

This paper presents a framework to automatically estimate the gaze direction of an infant in an infant-parent face-to-face interaction. Commercial devices are sometimes used to produce automated measurement of the subjects' gaze direction. This approach is intrusive, requiring cooperation from the participants, and cannot be employed in interactive face-to-face communication scenarios between a parent and their infant. Alternately, the infant gazes that are at and away from the parent's face may be manually coded from captured videos by a human expert. However, this approach is labor intensive. A preferred alternative would be to automatically estimate the gaze direction of participants from captured videos. The realization of a such a system will help psychological scientists to readily study and understand the early attention of infants. One of the problems in eye region image analysis is the large dimensionality of the visual data. We address this problem by employing the spectral regression technique to project high dimensionality eye region images into a low dimensional sub-space. Represented eye region images in the low dimensional sub-space are utilized to train a Support Vector Machine (SVM) classifier to predict the gaze direction (i.e., either looking at parent's face or looking away from parent's face). The analysis of more than 39,000 video frames of naturalistic gaze shifts of multiple infants demonstrates significant agreement between a human coder and our approach. These results indicate that the proposed system provides an efficient approach to automating the estimation of gaze direction of naturalistic gaze shifts.

Original languageEnglish
Title of host publicationProceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009
DOIs
StatePublished - Dec 1 2009
Event2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009 - Amsterdam, Netherlands
Duration: Sep 10 2009Sep 12 2009

Other

Other2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009
CountryNetherlands
CityAmsterdam
Period9/10/099/12/09

Fingerprint

Image analysis
Support vector machines
Classifiers
Personnel
Communication

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Software

Cite this

Cadavid, S., Mahoor, M. H., Messinger, D. S., & Cohn, J. F. (2009). Automated classification of gaze direction using spectral regression and support vector machine. In Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009 [5349517] https://doi.org/10.1109/ACII.2009.5349517

Automated classification of gaze direction using spectral regression and support vector machine. / Cadavid, Steven; Mahoor, Mohammad H.; Messinger, Daniel S; Cohn, Jeffrey F.

Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009. 2009. 5349517.

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

Cadavid, S, Mahoor, MH, Messinger, DS & Cohn, JF 2009, Automated classification of gaze direction using spectral regression and support vector machine. in Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009., 5349517, 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009, Amsterdam, Netherlands, 9/10/09. https://doi.org/10.1109/ACII.2009.5349517
Cadavid S, Mahoor MH, Messinger DS, Cohn JF. Automated classification of gaze direction using spectral regression and support vector machine. In Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009. 2009. 5349517 https://doi.org/10.1109/ACII.2009.5349517
Cadavid, Steven ; Mahoor, Mohammad H. ; Messinger, Daniel S ; Cohn, Jeffrey F. / Automated classification of gaze direction using spectral regression and support vector machine. Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009. 2009.
@inproceedings{f19a3fd6def1430985feb1d67ad44b71,
title = "Automated classification of gaze direction using spectral regression and support vector machine",
abstract = "This paper presents a framework to automatically estimate the gaze direction of an infant in an infant-parent face-to-face interaction. Commercial devices are sometimes used to produce automated measurement of the subjects' gaze direction. This approach is intrusive, requiring cooperation from the participants, and cannot be employed in interactive face-to-face communication scenarios between a parent and their infant. Alternately, the infant gazes that are at and away from the parent's face may be manually coded from captured videos by a human expert. However, this approach is labor intensive. A preferred alternative would be to automatically estimate the gaze direction of participants from captured videos. The realization of a such a system will help psychological scientists to readily study and understand the early attention of infants. One of the problems in eye region image analysis is the large dimensionality of the visual data. We address this problem by employing the spectral regression technique to project high dimensionality eye region images into a low dimensional sub-space. Represented eye region images in the low dimensional sub-space are utilized to train a Support Vector Machine (SVM) classifier to predict the gaze direction (i.e., either looking at parent's face or looking away from parent's face). The analysis of more than 39,000 video frames of naturalistic gaze shifts of multiple infants demonstrates significant agreement between a human coder and our approach. These results indicate that the proposed system provides an efficient approach to automating the estimation of gaze direction of naturalistic gaze shifts.",
author = "Steven Cadavid and Mahoor, {Mohammad H.} and Messinger, {Daniel S} and Cohn, {Jeffrey F.}",
year = "2009",
month = "12",
day = "1",
doi = "10.1109/ACII.2009.5349517",
language = "English",
isbn = "9781424447992",
booktitle = "Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009",

}

TY - GEN

T1 - Automated classification of gaze direction using spectral regression and support vector machine

AU - Cadavid, Steven

AU - Mahoor, Mohammad H.

AU - Messinger, Daniel S

AU - Cohn, Jeffrey F.

PY - 2009/12/1

Y1 - 2009/12/1

N2 - This paper presents a framework to automatically estimate the gaze direction of an infant in an infant-parent face-to-face interaction. Commercial devices are sometimes used to produce automated measurement of the subjects' gaze direction. This approach is intrusive, requiring cooperation from the participants, and cannot be employed in interactive face-to-face communication scenarios between a parent and their infant. Alternately, the infant gazes that are at and away from the parent's face may be manually coded from captured videos by a human expert. However, this approach is labor intensive. A preferred alternative would be to automatically estimate the gaze direction of participants from captured videos. The realization of a such a system will help psychological scientists to readily study and understand the early attention of infants. One of the problems in eye region image analysis is the large dimensionality of the visual data. We address this problem by employing the spectral regression technique to project high dimensionality eye region images into a low dimensional sub-space. Represented eye region images in the low dimensional sub-space are utilized to train a Support Vector Machine (SVM) classifier to predict the gaze direction (i.e., either looking at parent's face or looking away from parent's face). The analysis of more than 39,000 video frames of naturalistic gaze shifts of multiple infants demonstrates significant agreement between a human coder and our approach. These results indicate that the proposed system provides an efficient approach to automating the estimation of gaze direction of naturalistic gaze shifts.

AB - This paper presents a framework to automatically estimate the gaze direction of an infant in an infant-parent face-to-face interaction. Commercial devices are sometimes used to produce automated measurement of the subjects' gaze direction. This approach is intrusive, requiring cooperation from the participants, and cannot be employed in interactive face-to-face communication scenarios between a parent and their infant. Alternately, the infant gazes that are at and away from the parent's face may be manually coded from captured videos by a human expert. However, this approach is labor intensive. A preferred alternative would be to automatically estimate the gaze direction of participants from captured videos. The realization of a such a system will help psychological scientists to readily study and understand the early attention of infants. One of the problems in eye region image analysis is the large dimensionality of the visual data. We address this problem by employing the spectral regression technique to project high dimensionality eye region images into a low dimensional sub-space. Represented eye region images in the low dimensional sub-space are utilized to train a Support Vector Machine (SVM) classifier to predict the gaze direction (i.e., either looking at parent's face or looking away from parent's face). The analysis of more than 39,000 video frames of naturalistic gaze shifts of multiple infants demonstrates significant agreement between a human coder and our approach. These results indicate that the proposed system provides an efficient approach to automating the estimation of gaze direction of naturalistic gaze shifts.

UR - http://www.scopus.com/inward/record.url?scp=77949414347&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949414347&partnerID=8YFLogxK

U2 - 10.1109/ACII.2009.5349517

DO - 10.1109/ACII.2009.5349517

M3 - Conference contribution

SN - 9781424447992

BT - Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009

ER -