Three-dimensional object recognition from two-dimensional images using wavelet transforms and neural networks
Sylvain Deschênes · Optical Engineering · 1998
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 in- variant Fourier descriptor is used to describe the contour curves. Invari- ance under out-of-plane rotation is achieved by the feature space trajec- tory neural network working as a classifier. © 1998 Society of Photo-Optical Instrumentation Engineers. (S0091-3286(98)01203-3)