Share Email Print

Optical Engineering

Three-dimensional object recognitions from two-dimensional images using wavelet transforms and neural networks
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Three-dimensional object classification from 2-D IR images is shown. The wavelet transform is used for edge detection. Edge tracking is used for removing noise effectively in the wavelet transform. The invariant Fourier descriptor is used to describe the contour curves. Invariance under out-of-plane rotation is achieved by the feature space trajectory neural network working as a classifier.

Paper Details

Date Published: 1 March 1998
PDF: 8 pages
Opt. Eng. 37(3) doi: 10.1117/1.601908
Published in: Optical Engineering Volume 37, Issue 3
Show Author Affiliations
Sylvain Deschenes, Univ. Laval (Canada)
Yunlong Sheng, Univ. Laval (Canada)
Paul C. Chevrette, Defence Research Establishment Valcartier (Canada)

© SPIE. Terms of Use
Back to Top