1 April 1995 Invariant pattern recognition for range images using the phase Fourier transform and a neural network
Author Affiliations +
Abstract
A method for invariant pattern recognition of range images by means of the phase Fourier transform is introduced. The phase Fourier transform may be used for the segmentation of connected planar and quadric surfaces. The method is generalized to nonconnected planar surfaces through the use of the concept of the characteristic normal. An invariant representation under changes of position, scale, and orientation for the characteristic normals is defined. This representation is used as the input for a feedforward neural network. Examples of applications are given, and finally the method is applied to the problems of classification and occlusion.
Eric Paquet, Eric Paquet, Marc Rioux, Marc Rioux, Henri H. Arsenault, Henri H. Arsenault, } "Invariant pattern recognition for range images using the phase Fourier transform and a neural network," Optical Engineering 34(4), (1 April 1995). https://doi.org/10.1117/12.197093 . Submission:
JOURNAL ARTICLE
6 PAGES


SHARE
RELATED CONTENT

Pavement distress detection and severity analysis
Proceedings of SPIE (February 07 2011)
Imposing a temporal structure in neural networks
Proceedings of SPIE (February 28 1991)
Neural network post-processing of grayscale optical correlator
Proceedings of SPIE (September 10 2005)

Back to Top