A Hybrid Fuzzy Approach for Human Eye Gaze Pattern Recognition

Dingyun Zhu; Sumudu Mendis; Tom Gedeon; Arkshay Asthana; Roland Goecke

doi:10.1007/978-3-642-03040-6_80

A Hybrid Fuzzy Approach for Human Eye Gaze Pattern Recognition

Dingyun Zhu, Sumudu Mendis, Tom Gedeon, Arkshay Asthana, Roland Goecke

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

11 Citations (Scopus)

Abstract

Face perception and text reading are two of the most developed visual perceptual skills in humans. Understanding which features in the respective visual patterns make them differ from each other is very important for us to investigate the correlation between human’s visual behavior and cognitive processes. We introduce our fuzzy signatures with a Levenberg-Marquardt optimization method based hybrid approach for recognizing the different eye gaze patterns when a human is viewing faces or text documents. Our experimental results show the effectiveness of using this method for the real world case. A further comparison with Support Vector Machines (SVM) also demonstrates that by defining the classification process in a similar way to SVM, our hybrid approach is able to provide a comparable performance but with a more interpretable form of the learned structure

Original language	English
Title of host publication	15th International Conference on Neural Information Processing of the Asia-Pacific Neural Network Assembly
Editors	Nikola Kasabov, George Coghill
Place of Publication	Germany
Publisher	Springer
Pages	655-662
Number of pages	8
Volume	5507
ISBN (Print)	9783642030390
DOIs	https://doi.org/10.1007/978-3-642-03040-6_80
Publication status	Published - 2009
Externally published	Yes
Event	ICONIP 2008 - Auckland, New Zealand Duration: 25 Nov 2008 → 28 Nov 2008

Conference

Conference	ICONIP 2008
Country/Territory	New Zealand
City	Auckland
Period	25/11/08 → 28/11/08

Access to Document

10.1007/978-3-642-03040-6_80

Cite this

@inproceedings{1f170f381a184c67a05fc2aad4307c32,

title = "A Hybrid Fuzzy Approach for Human Eye Gaze Pattern Recognition",

abstract = "Face perception and text reading are two of the most developed visual perceptual skills in humans. Understanding which features in the respective visual patterns make them differ from each other is very important for us to investigate the correlation between human{\textquoteright}s visual behavior and cognitive processes. We introduce our fuzzy signatures with a Levenberg-Marquardt optimization method based hybrid approach for recognizing the different eye gaze patterns when a human is viewing faces or text documents. Our experimental results show the effectiveness of using this method for the real world case. A further comparison with Support Vector Machines (SVM) also demonstrates that by defining the classification process in a similar way to SVM, our hybrid approach is able to provide a comparable performance but with a more interpretable form of the learned structure",

author = "Dingyun Zhu and Sumudu Mendis and Tom Gedeon and Arkshay Asthana and Roland Goecke",

year = "2009",

doi = "10.1007/978-3-642-03040-6_80",

language = "English",

isbn = "9783642030390",

volume = "5507",

pages = "655--662",

editor = "Nikola Kasabov and George Coghill",

booktitle = "15th International Conference on Neural Information Processing of the Asia-Pacific Neural Network Assembly",

publisher = "Springer",

address = "Netherlands",

note = "ICONIP 2008 ; Conference date: 25-11-2008 Through 28-11-2008",

}

Zhu, D, Mendis, S, Gedeon, T, Asthana, A & Goecke, R 2009, A Hybrid Fuzzy Approach for Human Eye Gaze Pattern Recognition. in N Kasabov & G Coghill (eds), 15th International Conference on Neural Information Processing of the Asia-Pacific Neural Network Assembly. vol. 5507, Springer, Germany, pp. 655-662, ICONIP 2008, Auckland, New Zealand, 25/11/08. https://doi.org/10.1007/978-3-642-03040-6_80

A Hybrid Fuzzy Approach for Human Eye Gaze Pattern Recognition. / Zhu, Dingyun; Mendis, Sumudu; Gedeon, Tom et al.
15th International Conference on Neural Information Processing of the Asia-Pacific Neural Network Assembly. ed. / Nikola Kasabov; George Coghill. Vol. 5507 Germany: Springer, 2009. p. 655-662.

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

TY - GEN

T1 - A Hybrid Fuzzy Approach for Human Eye Gaze Pattern Recognition

AU - Zhu, Dingyun

AU - Mendis, Sumudu

AU - Gedeon, Tom

AU - Asthana, Arkshay

AU - Goecke, Roland

PY - 2009

Y1 - 2009

N2 - Face perception and text reading are two of the most developed visual perceptual skills in humans. Understanding which features in the respective visual patterns make them differ from each other is very important for us to investigate the correlation between human’s visual behavior and cognitive processes. We introduce our fuzzy signatures with a Levenberg-Marquardt optimization method based hybrid approach for recognizing the different eye gaze patterns when a human is viewing faces or text documents. Our experimental results show the effectiveness of using this method for the real world case. A further comparison with Support Vector Machines (SVM) also demonstrates that by defining the classification process in a similar way to SVM, our hybrid approach is able to provide a comparable performance but with a more interpretable form of the learned structure

AB - Face perception and text reading are two of the most developed visual perceptual skills in humans. Understanding which features in the respective visual patterns make them differ from each other is very important for us to investigate the correlation between human’s visual behavior and cognitive processes. We introduce our fuzzy signatures with a Levenberg-Marquardt optimization method based hybrid approach for recognizing the different eye gaze patterns when a human is viewing faces or text documents. Our experimental results show the effectiveness of using this method for the real world case. A further comparison with Support Vector Machines (SVM) also demonstrates that by defining the classification process in a similar way to SVM, our hybrid approach is able to provide a comparable performance but with a more interpretable form of the learned structure

U2 - 10.1007/978-3-642-03040-6_80

DO - 10.1007/978-3-642-03040-6_80

M3 - Conference contribution

SN - 9783642030390

VL - 5507

SP - 655

EP - 662

BT - 15th International Conference on Neural Information Processing of the Asia-Pacific Neural Network Assembly

A2 - Kasabov, Nikola

A2 - Coghill, George

PB - Springer

CY - Germany

T2 - ICONIP 2008

Y2 - 25 November 2008 through 28 November 2008

ER -

A Hybrid Fuzzy Approach for Human Eye Gaze Pattern Recognition

Abstract

Conference

Access to Document

Fingerprint

Cite this