Title :
Surface reconstruction using neural networks
Author :
Chen, David S. ; Jain, Ramesh C. ; Schunck, Brian G.
Author_Institution :
Artificial Intelligence Lab., Michigan Univ., Ann Arbor, MI, USA
Abstract :
A surface reconstruction method using multilayer feedforward neural networks is proposed. The parametric form represented by multilayer neural networks can model piecewise smooth surfaces in a way that is more general and flexible than many of the classical methods. The approximation method is based on a robust backpropagation (BP) algorithm, which extends the basic BP algorithm to handle errors, especially others, in the training data
Keywords :
feedforward neural nets; image processing; multilayer feedforward neural networks; neural networks; parametric form; piecewise smooth surfaces; surface reconstruction; Approximation algorithms; Approximation methods; Backpropagation algorithms; Feedforward neural networks; Multi-layer neural network; Neural networks; Reconstruction algorithms; Robustness; Surface reconstruction; Training data;
Conference_Titel :
Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92., 1992 IEEE Computer Society Conference on
Conference_Location :
Champaign, IL
Print_ISBN :
0-8186-2855-3
DOI :
10.1109/CVPR.1992.223251
