S. Deschenes et al., 3-DIMENSIONAL OBJECT RECOGNITION FROM 2-DIMENSIONAL IMAGES USING WAVELET TRANSFORMS AND NEURAL NETWORKS, Optical engineering, 37(3), 1998, pp. 763-770
Three-dimensional object classification from 2-D IR images is shown. T
he wavelet transform is used for edge detection. Edge tracking is used
for removing noise effectively in the wavelet transform. The invarian
t Fourier descriptor is used to describe the contour curves. Invarianc
e under out-of-plane rotation is achieved by the feature space traject
ory neural network working as a classifier. (C) 1998 Society of Photo-
Optical Instrumentation Engineers. [S0091-3286(98)01203-3].