Title :
Deformable models: canonical parameters for surface representation and multiple view integration
Author :
Vermuri, B.C. ; Malladi, R.
Author_Institution :
Dept. of Comput. & Inf. Sci., Florida Univ., Gainesville, FL, USA
Abstract :
Three-dimensional viewpoint invariance is an important requirement in the representation of surfaces for recognition tasks. Parameterized surfaces possess this desirable property. In general, the parameters in a parametric surface representation can be arbitrarily defined. A canonical, intrinsic parameterization provides a consistent, invariant form for describing surfaces. The goal of this work is to define and construct such a parameterization
Keywords :
computational geometry; computer graphics; computerised pattern recognition; 3D viewpoint invariance; deformable models; invariant form; multiple view integration; parametric surface representation; recognition tasks; stereo vision; surface representation; Capacitive sensors; Computer vision; Deformable models; Differential equations; Face detection; Nonlinear equations; Shape; Surface fitting; Surface reconstruction;
Conference_Titel :
Computer Vision and Pattern Recognition, 1991. Proceedings CVPR '91., IEEE Computer Society Conference on
Conference_Location :
Maui, HI
Print_ISBN :
0-8186-2148-6
DOI :
10.1109/CVPR.1991.139800
