Art facing science: Artistic heuristics for face detection: tracking gaze when looking at faces

Andrew T. Duchowski , Nina Gehrer , Michael Schönenberg , Krzysztof Krejtz

Abstract

Automatic Area Of Interest (AOI) demarcation of facial regions is not yet commonplace in applied eye-tracking research, partially because automatic AOI labeling is prone to error. Most previous eye-tracking studies relied on manual frame-by-frame labeling of facial AOIs. We present a fully automatic approach for facial AOI labeling (i.e., eyes, nose, mouth) and gaze registration within those AOIs, based on modern computer vision techniques combined with heuristics drawn from art. We discuss details in computing gaze analytics, provide proof-of-concept, and a short validation against what we consider ground truth. Relative dwell time over expected AOIs exceeded 98% showing efficacy of the approach
Author Andrew T. Duchowski
Andrew T. Duchowski,,
-
, Nina Gehrer
Nina Gehrer,,
-
, Michael Schönenberg
Michael Schönenberg,,
-
, Krzysztof Krejtz (Wydział Psychologii)
Krzysztof Krejtz,,
- Wydział Psychologii
Pages1-5
Publication size in sheets0.5
Article number80
Book Krejtz Krzysztof, Sharif Bonita (eds.): Proceedings of the 11th ACM Symposium on Eye Tracking Research & Applications, 2019, Association for Computing Machinery, ISBN 978-1-4503-6709-7, 623 p.
Proceedings ETRA2019.pdf / No licence information (file archived - login or check accessibility on faculty)
Keywords in Englisheye tracking, face tracking, gaze analytics
Keywords in original languageeye tracking, face tracking, gaze analytics
Abstract in original languageAutomatic Area Of Interest (AOI) demarcation of facial regions is not yet commonplace in applied eye-tracking research, partially because automatic AOI labeling is prone to error. Most previous eye-tracking studies relied on manual frame-by-frame labeling of facial AOIs. We present a fully automatic approach for facial AOI labeling (i.e., eyes, nose, mouth) and gaze registration within those AOIs, based on modern computer vision techniques combined with heuristics drawn from art. We discuss details in computing gaze analytics, provide proof-of-concept, and a short validation against what we consider ground truth. Relative dwell time over expected AOIs exceeded 98% showing efficacy of the approach
DOIDOI:10.1145/3317958.3319809
URL https://dl.acm.org/citation.cfm?doid=3317958.3319809
Languageen angielski
File
Art Facing Science_Artistic Heuristics for Face Detection.pdf 706.92 KB
Additional file
Oswiadczenie_K.Krejtz_Art facing.pdf 19.86 KB
Score (nominal)20
Score sourcepublisherList
Citation count*
Cite
Share Share

Get link to the record


* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Back
Confirmation
Are you sure?