25 October 1993 Three-dimensional pattern recognition using an optoelectronic inner product complex neural network
Author Affiliations +
A complex associative memory model based on a neural network architecture is proposed for recognizing three-dimensional objects acquired from a dynamic environment. The storage representation of the complex associative memory model is based on an efficient amplitude modulated phase-only matched filter. The input to the memory is derived from the discrete Fourier transform of the edge coordinates of the to-be-recognized moving object, where the edges are obtained through motion-based segmentation of the image scene. An adaptive threshold is used during the decision making process to indicate a match or identify a mismatch. Computer simulation on real world data proves the effectiveness of the proposed model. The proposed scheme is readily amenable to opto-electronic implementation.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Abdul Ahad Sami Awwal, Abdul Ahad Sami Awwal, Gregory J. Power, Gregory J. Power, } "Three-dimensional pattern recognition using an optoelectronic inner product complex neural network", Proc. SPIE 1959, Optical Pattern Recognition IV, (25 October 1993); doi: 10.1117/12.160315; https://doi.org/10.1117/12.160315


A new approach to ultrasonic elasticity imaging
Proceedings of SPIE (March 31 2016)
Optical Implementation Of High-Speed Pattern Recognition
Proceedings of SPIE (October 24 1989)
Improving The Performance Of Neural Networks
Proceedings of SPIE (May 02 1988)
Bilinear Pattern Recognition Processors
Proceedings of SPIE (June 28 1989)
Optoelectronic techniques for real-time pattern recognition
Proceedings of SPIE (December 05 2001)

Back to Top