Understanding eye movements in face recognition with hidden Markov model

Tim Chuk; Alvin C. W. Ng; Emanuele Coviello; Antoni B. Chan; Janet H. Hsiao

Understanding eye movements in face recognition with hidden Markov model

Tim Chuk
, Alvin C. W. Ng
, Emanuele Coviello
, Antoni B. Chan
, Janet H. Hsiao

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

3 Citations (Scopus)

Abstract

In this paper we propose a hidden Markov model (HMM)based method to analyze eye movement data. We conducted a simple face recognition task and recorded eye movements and performance of the participants. We used a variational Bayesian framework for Gaussian mixture models to estimate the distribution of fixation locations and modeled the fixation and transition data using HMMs. We showed that using HMMs, we can describe individuals' eye movement strategies with both fixation locations and transition probabilities. By clustering these HMMs, we found that the strategies can be categorized into two subgroups; one was more holistic and the other was more analytical. Furthermore, we found that correct and wrong recognitions were associated with distinctive eye movement strategies. The difference between these strategies lied in their transition probabilities. © CogSci 2013. All rights reserved.

Original language	English
Title of host publication	Cooperative Minds: Social Interaction and Group Dynamics - Proceedings of the 35^th Annual Meeting of the Cognitive Science Society, CogSci 2013
Editors	Markus Knauff, Michael Pauen, Natalie Sebanz, Ipke Wachsmuth
Place of Publication	Austin, TX
Publisher	The Cognitive Science Society
Pages	328-333
ISBN (Print)	9780976831891
Publication status	Published - Jul 2013
Event	35th Annual Meeting of the Cognitive Science Society (CogSci 2013): Cooperative Minds: Social Interaction and Group Dynamics - Berlin, Germany Duration: 31 Jul 2013 → 3 Aug 2013 https://cognitivesciencesociety.org/past-conferences/

Publication series

Name	Cooperative Minds: Social Interaction and Group Dynamics - Proceedings of the Annual Meeting of the Cognitive Science Society, CogSci

Conference

Conference	35th Annual Meeting of the Cognitive Science Society (CogSci 2013)
Abbreviated title	CogSci2013
Place	Germany
City	Berlin
Period	31/07/13 → 3/08/13
Internet address	https://cognitivesciencesociety.org/past-conferences/

Research Keywords

eye movement
face recognition
Hidden Markov Model (HMM)
holistic processing
scan path

Access Output

https://escholarship.org/uc/item/1197p8wz

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Chuk, T., Ng, A. C. W., Coviello, E., Chan, A. B., & Hsiao, J. H. (2013). Understanding eye movements in face recognition with hidden Markov model. In M. Knauff, M. Pauen, N. Sebanz, & I. Wachsmuth (Eds.), Cooperative Minds: Social Interaction and Group Dynamics - Proceedings of the 35^th Annual Meeting of the Cognitive Science Society, CogSci 2013 (pp. 328-333). (Cooperative Minds: Social Interaction and Group Dynamics - Proceedings of the Annual Meeting of the Cognitive Science Society, CogSci). The Cognitive Science Society. https://escholarship.org/uc/item/1197p8wz

Chuk, Tim ; Ng, Alvin C. W. ; Coviello, Emanuele et al. / Understanding eye movements in face recognition with hidden Markov model. Cooperative Minds: Social Interaction and Group Dynamics - Proceedings of the 35^th Annual Meeting of the Cognitive Science Society, CogSci 2013. editor / Markus Knauff ; Michael Pauen ; Natalie Sebanz ; Ipke Wachsmuth. Austin, TX : The Cognitive Science Society, 2013. pp. 328-333 (Cooperative Minds: Social Interaction and Group Dynamics - Proceedings of the Annual Meeting of the Cognitive Science Society, CogSci).

@inproceedings{6bb9d3a5509c4c8f9de05a6e873cb26a,

title = "Understanding eye movements in face recognition with hidden Markov model",

abstract = "In this paper we propose a hidden Markov model (HMM)based method to analyze eye movement data. We conducted a simple face recognition task and recorded eye movements and performance of the participants. We used a variational Bayesian framework for Gaussian mixture models to estimate the distribution of fixation locations and modeled the fixation and transition data using HMMs. We showed that using HMMs, we can describe individuals' eye movement strategies with both fixation locations and transition probabilities. By clustering these HMMs, we found that the strategies can be categorized into two subgroups; one was more holistic and the other was more analytical. Furthermore, we found that correct and wrong recognitions were associated with distinctive eye movement strategies. The difference between these strategies lied in their transition probabilities. {\textcopyright} CogSci 2013. All rights reserved.",

keywords = "eye movement, face recognition, Hidden Markov Model (HMM), holistic processing, scan path",

author = "Tim Chuk and Ng, \{Alvin C. W.\} and Emanuele Coviello and Chan, \{Antoni B.\} and Hsiao, \{Janet H.\}",

year = "2013",

month = jul,

language = "English",

isbn = "9780976831891",

series = "Cooperative Minds: Social Interaction and Group Dynamics - Proceedings of the Annual Meeting of the Cognitive Science Society, CogSci",

publisher = "The Cognitive Science Society",

pages = "328--333",

editor = "Markus Knauff and Michael Pauen and Natalie Sebanz and Ipke Wachsmuth",

booktitle = "Cooperative Minds: Social Interaction and Group Dynamics - Proceedings of the 35th Annual Meeting of the Cognitive Science Society, CogSci 2013",

note = "35th Annual Meeting of the Cognitive Science Society (CogSci 2013) : Cooperative Minds: Social Interaction and Group Dynamics, CogSci2013 ; Conference date: 31-07-2013 Through 03-08-2013",

url = "https://cognitivesciencesociety.org/past-conferences/",

}

Chuk, T, Ng, ACW, Coviello, E, Chan, AB & Hsiao, JH 2013, Understanding eye movements in face recognition with hidden Markov model. in M Knauff, M Pauen, N Sebanz & I Wachsmuth (eds), Cooperative Minds: Social Interaction and Group Dynamics - Proceedings of the 35^th Annual Meeting of the Cognitive Science Society, CogSci 2013. Cooperative Minds: Social Interaction and Group Dynamics - Proceedings of the Annual Meeting of the Cognitive Science Society, CogSci, The Cognitive Science Society, Austin, TX, pp. 328-333, 35th Annual Meeting of the Cognitive Science Society (CogSci 2013), Berlin, Germany, 31/07/13. <https://escholarship.org/uc/item/1197p8wz>

Understanding eye movements in face recognition with hidden Markov model. / Chuk, Tim; Ng, Alvin C. W.; Coviello, Emanuele et al.
Cooperative Minds: Social Interaction and Group Dynamics - Proceedings of the 35^th Annual Meeting of the Cognitive Science Society, CogSci 2013. ed. / Markus Knauff; Michael Pauen; Natalie Sebanz; Ipke Wachsmuth. Austin, TX: The Cognitive Science Society, 2013. p. 328-333 (Cooperative Minds: Social Interaction and Group Dynamics - Proceedings of the Annual Meeting of the Cognitive Science Society, CogSci).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Understanding eye movements in face recognition with hidden Markov model

AU - Chuk, Tim

AU - Ng, Alvin C. W.

AU - Coviello, Emanuele

AU - Chan, Antoni B.

AU - Hsiao, Janet H.

PY - 2013/7

Y1 - 2013/7

N2 - In this paper we propose a hidden Markov model (HMM)based method to analyze eye movement data. We conducted a simple face recognition task and recorded eye movements and performance of the participants. We used a variational Bayesian framework for Gaussian mixture models to estimate the distribution of fixation locations and modeled the fixation and transition data using HMMs. We showed that using HMMs, we can describe individuals' eye movement strategies with both fixation locations and transition probabilities. By clustering these HMMs, we found that the strategies can be categorized into two subgroups; one was more holistic and the other was more analytical. Furthermore, we found that correct and wrong recognitions were associated with distinctive eye movement strategies. The difference between these strategies lied in their transition probabilities. © CogSci 2013. All rights reserved.

AB - In this paper we propose a hidden Markov model (HMM)based method to analyze eye movement data. We conducted a simple face recognition task and recorded eye movements and performance of the participants. We used a variational Bayesian framework for Gaussian mixture models to estimate the distribution of fixation locations and modeled the fixation and transition data using HMMs. We showed that using HMMs, we can describe individuals' eye movement strategies with both fixation locations and transition probabilities. By clustering these HMMs, we found that the strategies can be categorized into two subgroups; one was more holistic and the other was more analytical. Furthermore, we found that correct and wrong recognitions were associated with distinctive eye movement strategies. The difference between these strategies lied in their transition probabilities. © CogSci 2013. All rights reserved.

KW - eye movement

KW - face recognition

KW - Hidden Markov Model (HMM)

KW - holistic processing

KW - scan path

UR - https://www.scopus.com/pages/publications/84970879539

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84970879539&origin=recordpage

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9780976831891

T3 - Cooperative Minds: Social Interaction and Group Dynamics - Proceedings of the Annual Meeting of the Cognitive Science Society, CogSci

SP - 328

EP - 333

BT - Cooperative Minds: Social Interaction and Group Dynamics - Proceedings of the 35th Annual Meeting of the Cognitive Science Society, CogSci 2013

A2 - Knauff, Markus

A2 - Pauen, Michael

A2 - Sebanz, Natalie

A2 - Wachsmuth, Ipke

PB - The Cognitive Science Society

CY - Austin, TX

T2 - 35th Annual Meeting of the Cognitive Science Society (CogSci 2013)

Y2 - 31 July 2013 through 3 August 2013

ER -

Chuk T, Ng ACW, Coviello E, Chan AB, Hsiao JH. Understanding eye movements in face recognition with hidden Markov model. In Knauff M, Pauen M, Sebanz N, Wachsmuth I, editors, Cooperative Minds: Social Interaction and Group Dynamics - Proceedings of the 35^th Annual Meeting of the Cognitive Science Society, CogSci 2013. Austin, TX: The Cognitive Science Society. 2013. p. 328-333. (Cooperative Minds: Social Interaction and Group Dynamics - Proceedings of the Annual Meeting of the Cognitive Science Society, CogSci).

Understanding eye movements in face recognition with hidden Markov model

Abstract

Publication series

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this