[Insight-users] algorithm inside HoughTransform2DCirclesImageFilter

[Lei Wang]

Hello,

Currently i am using HoughTransform2DCirclesImageFilter to detect circular
objects within the images.
By reading the documentation of this filter, it is not so hard to understand
the whole procedure of detection and the meaning of parameters.

However, one thing which really puzzled me is that, how the accumulator and
radius images are filled.
As i understood, the accumulator image is filled by drawing a line interval
specified by MIN_RADIUS and MAX_RADIUS along the gradient direction.
But how the radius image is filled simultaneously and how the radius is
determined after having the center point?

Anybody can give me some hints about this or send me a link of the papers
which might be related to the algorithm inside this filter in detail?

Thanks a lot.

William
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20080905/e5883a63/attachment.htm>