Optical EngineeringThree-dimensional object recognitions from two-dimensional images using wavelet transforms and neural networks
|Format||Member Price||Non-Member Price|
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.