hough ellipse fit inaccurate?

Arno Dietz arnodietz86 at googlemail.com
Thu Mar 5 19:22:55 EST 2015


Hi Kevin and Johannes,

no the accuracy parameter has no effect on my measure accuracy.
Yes I tried opencv fitellipse and it is much more accurate. But I want to 
test several methods and I heard that the hough transform is quite robust.
The eyeball is a sphere and the Pupil a flat circle on the flat white 
plane. Since I view the circle from different angles it always appears 
<http://www.dict.cc/englisch-deutsch/appears.html> as a ellipse. So circle 
detection is not an option.
Ok Thank you..it seams the skimage hough ellipse fit just isn't that 
accurate. 

@Johannes: I tried the EllipseModel with ransac from your link today and I 
like it very much.
But I have some problems with greater angles. I always have a set of 25 
images where the eye is looking at different targets on a display. I plot 
the difference between the true center and the measured center in one error 
diagram (see images).
When the camera is located directly in front of the eye, so the angles are 
not to big, it works fine with low errors (see image 1).
But when I move the camera down so that the pupil appear more elliptical I 
always get some outlier <http://www.dict.cc/englisch-deutsch/outlier.html>s 
with bigger errors like Point 2, 7, 12, etc. (see image 2).
I tried to vary the parameters (min_samples, residual_threshold and 
max_trials) but there are always some outliers, but ever 
<http://www.dict.cc/englisch-deutsch/every.html>y time 
<http://www.dict.cc/englisch-deutsch/time.html> at different images.
Do you have an idea where this comes from? 

Thank you so far.

Kind regards
Arno

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.python.org/pipermail/scikit-image/attachments/20150305/facbe3ec/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: ellipse_errors1.jpg
Type: image/jpeg
Size: 35176 bytes
Desc: not available
URL: <http://mail.python.org/pipermail/scikit-image/attachments/20150305/facbe3ec/attachment.jpg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: ellipse_errors2.jpg
Type: image/jpeg
Size: 27691 bytes
Desc: not available
URL: <http://mail.python.org/pipermail/scikit-image/attachments/20150305/facbe3ec/attachment-0001.jpg>


More information about the scikit-image mailing list