ITK/Release 4/Enhancing Image Registration Framework: Difference between revisions
From KitwarePublic
Jump to navigationJump to search
| Line 11: | Line 11: | ||
* Wishlist items beyond standard use cases, e.g. projective transform (itkPerspective3DTransform). | * Wishlist items beyond standard use cases, e.g. projective transform (itkPerspective3DTransform). | ||
= | = Discussion Items = | ||
* Separate sampling and metric computation | * Separate sampling (interpolation strategy) and metric computation | ||
* Separate computation of derivative components | * Separate computation of derivative components via chain rule. | ||
e.g. Maximize MI( I(x) , J(T(x)) ) by gradient methods: | # e.g. Maximize MI( I(x) , J(T(x)) ) by gradient methods: | ||
# | |||
# \partial Metric / \partial Image \partial Image / \partial Transform \partial Transform / \partial x | |||
* Add feature based registration techniques (SIFT (patented?), SURF, etc) | * Add feature based registration techniques (SIFT (patented?), SURF, etc) | ||
| Line 26: | Line 26: | ||
[http://www.itk.org/Wiki/ITK_Release_4/Wish_List#Image_Registration Wish List for ITKv4 ] | [http://www.itk.org/Wiki/ITK_Release_4/Wish_List#Image_Registration Wish List for ITKv4 ] | ||
= Tcons = | = Tcons = | ||
Revision as of 17:28, 7 September 2010
Enhancing Image Registration Framework
Goals
- Review v4 registration plans and progress.
- Catalog target use cases.
- Discuss design changes in core itk to support these enhancements.
- Wishlist items beyond standard use cases, e.g. projective transform (itkPerspective3DTransform).
Discussion Items
- Separate sampling (interpolation strategy) and metric computation
- Separate computation of derivative components via chain rule.
- e.g. Maximize MI( I(x) , J(T(x)) ) by gradient methods:
- \partial Metric / \partial Image \partial Image / \partial Transform \partial Transform / \partial x
- Add feature based registration techniques (SIFT (patented?), SURF, etc)
Refactoring of optimization framework
Tcons
(Add one page for every tcon).
