DocumentCode
2620493
Title
Introducing new deformable surfaces to segment 3D images
Author
Cohen, Isaac ; Cohen, Laurent D. ; Ayache, Nicholas
Author_Institution
INRIA, Le Chesnay, France
fYear
1991
fDate
3-6 Jun 1991
Firstpage
738
Lastpage
739
Abstract
A 3D deformable model is introduced which evolves in true 3D images, under the action of internal forces (describing some elasticity properties of the surface), and external forces attracting the surface toward some detected edges. The formalism leads to the minimization of an energy which is expressed as a functional. The authors use a variational approach and a finite-element method to express the surface in a discrete basis of continuous functions. This leads to a reduced computational complexity and a better numerical stability. The power of the approach to segment 3D images is demonstrated by a set of experimental results on various complex medical 3D images
Keywords
computational complexity; computerised pattern recognition; computerised picture processing; convergence of numerical methods; finite element analysis; variational techniques; 3D images; computational complexity; continuous functions; deformable surfaces; elasticity properties; energy minimisation; finite-element method; internal forces; medical 3D images; numerical stability; variational approach; Biomedical imaging; Computational complexity; Deformable models; Elasticity; Equations; Finite element methods; Image edge detection; Image segmentation; Numerical stability; Surface fitting;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision and Pattern Recognition, 1991. Proceedings CVPR '91., IEEE Computer Society Conference on
Conference_Location
Maui, HI
ISSN
1063-6919
Print_ISBN
0-8186-2148-6
Type
conf
DOI
10.1109/CVPR.1991.139807
Filename
139807
Link To Document