Abstract
We present a new algorithm for large deformation image matching via volume data. The image matching problem is stated as a control problem with the optimal diffeomorphic match constructed to minimize a running smoothness cost on a velocity field generating the diffeomorphism while simultaneously minimizing a matching end point condition of the imagery. The diffeomorphic deformation field on the image space is generated by numerically integrating the velocity field.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 317-323 |
| Number of pages | 7 |
| Journal | Proceedings of SPIE - The International Society for Optical Engineering |
| Volume | 3454 |
| DOIs | |
| State | Published - Dec 1 1998 |
| Event | Vision Geometry VII - San Diego, CA, United States Duration: Jul 20 1998 → Jul 22 1998 |
ASJC Scopus subject areas
- Electronic, Optical and Magnetic Materials
- Condensed Matter Physics
- Computer Science Applications
- Applied Mathematics
- Electrical and Electronic Engineering
Fingerprint Dive into the research topics of 'Large deformation image matching via volume imagery'. Together they form a unique fingerprint.
Cite this
Wang, L., & Miller, M. I. (1998). Large deformation image matching via volume imagery. Proceedings of SPIE - The International Society for Optical Engineering, 3454, 317-323. https://doi.org/10.1117/12.323268