Title: Automatic Quantification of Pupil Dilation under Stress
1Automatic Quantification of Pupil Dilation under
Stress
Julien Jomier, Erwann Rault, and Stephen R.
AylwardComputer Aided-Diagnosis and Display Lab
- University of North Carolina at Chapel Hill
Introduction
- Statistics of the iris are estimated on the left
and right part of the pupil. - Only the radius is optimized. The center of the
iris is assumed to be the center of the pupil.
We seek to automate the measurement of pupil and
iris areas from color digital photos so as to
calculate the ratio of those areas as a measure
of the amount that an individual has
dark-adapted.
regions used to evaluate statistics of the iris
Resulting segmentation of the iris
We are particularly interested in testing the
hypothesis that dark adaptation is slowed
proportional to the amount of stress that an
individual has experienced.
Precise Pupil Segmentation
- Calculate the optimal linear discriminant
between pupil and iris color classes to compute a
pupil-likelihood image (Top-Right). We seek the
boundary between the iris and the pupil that is
emphasized by that likelihood image.
Coarse Pupil and Iris Segmentation
1) Eye Localization
- Threshold the likelihood image to form a binary
image such that every pixel with a likelihood
greater or equal to zero is set to one. We then
use morphological operations to reduce noise
(Bottom-Left). - Active contours segmentation
3 (Bottom-Right)
- Sub sampling is performed to improve computation
speed. - Statistics filter is applied to extract pixels
that have the red component higher than the blue
component (Red Blue lt ?) defining two regions
of interest around each eye.
Resulting precise segmentation of the pupil via
active contours
Results
Eye localization using color statistics of the
pupil (middle) from the original image (left)
resulting to a definition of two regions of
interest (right)
- Training 5 left eyes from different subjects.
- Testing 20 eyes from 10 different patients.
- Comparison of the automated algorithm with
hand-segmentation of 5 raters shows equal
accuracy. - Automatic segmentation takes less than 1 minute
per image (2 times faster than manual
segmentation). - Fully automatic
2) Coarse Pupil Segmentation
- The pupil is segmented in three steps.
- The pixels that satisfy the equation
are set to 1 and 0 otherwise to
produce a binary image. - Hough Transform 1 is used to approximate the
center and radius of the best fitting circle in
the binary image. - We apply a model-to-image registration Aylward
2001 using the 11 evolutionary optimizer 2.
We define the metric f of the fit of the circle
with the binary image.
Segmentation Average ? ? Error Max Error
Raters 35010 1.94 6.76
Computer 34780 2.41 5.80
? Error
Max Error
Comparison with hand-segmentation of the pupil by
5 raters on 10 images.
References
1 D. H. Ballard, Generalized hough transform
to detect arbitrary patterns, IEEE Transactions
on Pattern Analysis and Machine Intelligence,
vol. 13, no. 2, pp. 111122, 1981 2 M Styner
and G. Gerig, Evaluation of 2d/3d bias
correction with 11es-optimization, Technical
Report BIWI-TR-179 3 Ross T. Whitaker,
Algorithms for implicit deformable models, in
Fifth International Conference on Computer
Vision. IEEE, 1995, IEEE Computer Society
Press 4 Insight Software Consortium, The
insight toolkit Segmentation and Registration
toolkit, http//www.itk.org
Resulting segmentation of the pupil
Plot of the metric for a radius r3
3) Coarse Iris Segmentation
The segmentation of the iris is done with the
same technique as the pupil.
April 2004