Contact FutureLearn for Support Skip main navigation
We use cookies to give you a better experience, if that’s ok you can close this message and carry on browsing. For more info read our cookies policy.
We use cookies to give you a better experience. Carry on browsing if you're happy with this, or read our cookies policy for more information.

Scalismo Lab: finding correspondence in an image

In this hands-on step, we build upon the previous tutorial video and address the problem of finding correspondences between a shape model and an image.

Similar to the video, we will start by building a first simplistic intensity model for the tip of the nose and use it to try and locate the tip in a target MRI image.

We will then expand on the video and build a better intensity model, taking into account the intensity at a neighbourhood of the tip in the training data. The neighbourhood definition, borrowed from the Active Shape Model (ASM) algorithm, will in this case be a set of points along the surface normal at the tip of the nose.

To access the tutorial document:

  1. Switch to Scalismo Lab.
  2. Select the Finding Correspondence in an Image document under:
    Documents -> Fast track, for the fast track version
    Documents -> Full track, for the full track version

If you have questions, ask them in the comments section here on FutureLearn.

If you are doing the full track version, please remember that the exercises are optional. If you find them too hard, you can continue going through the tutorial without solving the exercises.

Did anything go wrong and you have a weird shape output? Post it in our Shapes Gone Wrong Padlet!

This article is from the free online course:

Statistical Shape Modelling: Computing the Human Anatomy

University of Basel