Neural network for three-dimensional object recognition based on digital holography
- 1 October 2001
- journal article
- Published by Optica Publishing Group in Optics Letters
- Vol. 26 (19), 1478-1480
- https://doi.org/10.1364/ol.26.001478
Abstract
We present a two-layer neural network for processing of three-dimensional (3D) images that are obtained by digital holography. The network is trained with a real 3D object to compute the weights of the layers. Experiments are presented to illustrate the system performance. The system is designed to detect a 3D object in the presence of various distortions. As an example, experiments are presented to illustrate how the system is able to recognize a 3D object with 360° out-of-plane rotation.Keywords
This publication has 14 references indexed in Scilit:
- Three-dimensional object recognition by use of digital holographyOptics Letters, 2000
- Application of multi-layer perceptron neural networks to vision problemsNeural Computing & Applications, 1998
- Recognizing 3-D objects by using a Hopfield-style optimization algorithm for matching patch-based descriptionsPattern Recognition, 1998
- Three-dimensional object recognition in intelligent assembly systemPublished by SPIE-Intl Soc Optical Eng ,1998
- Real-time vehicle navigation using a holographic memoryOptical Engineering, 1997
- Three-dimensional optical Fourier transform and correlationOptics Letters, 1997
- Distortion-invariant pattern recognition with Fourier-plane nonlinear filtersApplied Optics, 1996
- Optical implementation of neural networks for face recognition by the use of nonlinear joint transform correlatorsApplied Optics, 1995
- Nonlinear joint-transform correlation: an optimal solution for adaptive image discrimination and input noise robustnessOptics Letters, 1994
- A neural network architecture for understanding discrete three-dimensional scenes in medical imagingComputers and Biomedical Research, 1992