13 July 2000 How to train a phase-only filter
Author Affiliations +
Abstract
This paper establishes the equivalence of the phase only filter and a complex-valued neural network, and then shows how neural network learning can be utilized to design completely novel phase-only-filter based system. By incorporating the neural network based learning, the pattern recognition capability of the phase only type of filter under various transformation and distortions can be enhanced.
© (2000) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Howard E. Michel, Howard E. Michel, Abdul Ahad Sami Awwal, Abdul Ahad Sami Awwal, } "How to train a phase-only filter", Proc. SPIE 4046, Advances in Optical Information Processing IX, (13 July 2000); doi: 10.1117/12.391949; https://doi.org/10.1117/12.391949
PROCEEDINGS
10 PAGES


SHARE
RELATED CONTENT

Neural nets in information retrieval a case study of...
Proceedings of SPIE (July 01 1992)
Optical Implementation Of High-Speed Pattern Recognition
Proceedings of SPIE (October 25 1989)
Review of wavelet transforms for pattern recognitions
Proceedings of SPIE (March 22 1996)
Analyzing decision boundaries of neural networks
Proceedings of SPIE (November 02 2000)
Geometry of decision boundaries of neural networks
Proceedings of SPIE (November 13 2001)

Back to Top