NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Robust pupil center detection using a curvature algorithmDetermining the pupil center is fundamental for calculating eye orientation in video-based systems. Existing techniques are error prone and not robust because eyelids, eyelashes, corneal reflections or shadows in many instances occlude the pupil. We have developed a new algorithm which utilizes curvature characteristics of the pupil boundary to eliminate these artifacts. Pupil center is computed based solely on points related to the pupil boundary. For each boundary point, a curvature value is computed. Occlusion of the boundary induces characteristic peaks in the curvature function. Curvature values for normal pupil sizes were determined and a threshold was found which together with heuristics discriminated normal from abnormal curvature. Remaining boundary points were fit with an ellipse using a least squares error criterion. The center of the ellipse is an estimate of the pupil center. This technique is robust and accurately estimates pupil center with less than 40% of the pupil boundary points visible.
Document ID
20040141915
Acquisition Source
Legacy CDMS
Document Type
Reprint (Version printed in journal)
Authors
Zhu, D.
(Brooklyn College of the City University of New York 11210, United States)
Moore, S. T.
Raphan, T.
Wall, C. C.
Date Acquired
August 22, 2013
Publication Date
June 1, 1999
Publication Information
Publication: Computer methods and programs in biomedicine
Volume: 59
Issue: 3
ISSN: 0169-2607
Subject Category
Life Sciences (General)
Funding Number(s)
CONTRACT_GRANT: DC 03284
CONTRACT_GRANT: EY 04148
Distribution Limits
Public
Copyright
Other
Keywords
Non-NASA Center
NASA Discipline Neuroscience

Available Downloads

There are no available downloads for this record.
No Preview Available