Abstract | ||
---|---|---|
In this paper, we present a novel variational formulation of the registration assisted image segmentation problem which leads to solving a coupled set of nonlinear PDEs that are solved using efficient numerical schemes. Our work is a departure from earlier methods in that we have a unified variational principle wherein non-rigid registration and segmentation are simultaneously achieved; unlike previous methods of solution for this problem, our algorithm can accommodate for image pairs having very distinct intensity distributions. We present examples of performance of our algorithm on synthetic and real data sets along with quantitative accuracy estimates of the registration. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/11566465_3 | MICCAI |
Keywords | Field | DocType |
novel variational formulation,non-rigid registration,present example,earlier method,unified variational principle,anatomical structure,brain mri,efficient numerical scheme,image pair,image segmentation problem,simultaneous registration,nonlinear pdes,distinct intensity distribution,image segmentation,variational principle | Active contour model,Computer vision,Data set,Scale-space segmentation,Nonlinear system,Pattern recognition,Computer science,Segmentation,Segmentation-based object categorization,Variational principle,Image segmentation,Artificial intelligence | Conference |
Volume | Issue | ISSN |
8 | Pt 1 | 0302-9743 |
ISBN | Citations | PageRank |
3-540-29327-2 | 24 | 1.03 |
References | Authors | |
6 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Fei Wang | 1 | 272 | 19.41 |
B.C. Vemuri | 2 | 4208 | 536.42 |