Optical Implementation of Cellular Neural Networks Based on Bias and Joint Correlation
Applied Optics, Vol. 38, Issue 5, pp. 847-854 (1999)
http://dx.doi.org/10.1364/AO.38.000847
Acrobat PDF (167 KB)
Abstract
A new bias method for the optical implementation of cellular neural networks is proposed to reduce electronic precalculation and increase processing speed. A multiple-object joint transform correlator is then used to realize the summation of multiple correlations resulting from the bias method. Compared with other optical systems for cellular neural networks, the proposed method offers the advantages of higher processing speed, easy implementation, and robustness. Computer simulations of the optical cellular neural networks for edge detection and corner and horizontal line extraction are also presented.
© 1999 Optical Society of America
[Optical Society of America ]
OCIS Codes
(070.4550) Fourier optics and signal processing : Correlators
(070.4560) Fourier optics and signal processing : Data processing by optical means
(070.4690) Fourier optics and signal processing : Morphological transformations
(100.5010) Image processing : Pattern recognition
(170.1530) Medical optics and biotechnology : Cell analysis
(200.1130) Optics in computing : Algebraic optical processing
(200.4260) Optics in computing : Neural networks
(200.4690) Optics in computing : Morphological transformations
(200.4700) Optics in computing : Optical neural systems
(200.4860) Optics in computing : Optical vector-matrix systems
Citation
Shuqun Zhang and Mohammad A. Karim, "Optical Implementation of Cellular Neural Networks Based on Bias and Joint Correlation," Appl. Opt. 38, 847-854 (1999)
http://www.opticsinfobase.org/ao/abstract.cfm?URI=ao-38-5-847
You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Log in to access OSA Member Subscription
You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Log in to access OSA Member Subscription
You do not have subscription access to this journal. Article level metrics are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Log in to access OSA Member Subscription
Related Journal Articles 
- Influence of a perturbation in a double phase-encoding system (JOSAA)
- One-dimensional logarithmic harmonic synthetic discriminant function filters for shift-, scale-, and projection-invariant pattern recognition (OL)
- Morphologically Preprocessed Joint Transform Correlation (AO)
- Optically Computing the Hit-Miss Transform for an Automated Cervical Smear Screening System (AO)
- Statistical Performance of Cascaded Linear Shift-Invariant Processing (AO)
Related Conference Papers
- Novel optical packet header decoding via cross-correlation
- RM3A programmable optoelectronic neural network packet switch scheduler
- Automatic classification of images with a photorefractive crystal
- Template construction for object and biometric recognition
- <b>Optical Realization of Bio-Inspired Spiking Neurons </b><b>in SrS:Eu<sup>2+</sup>,Sm<sup>3+</sup> Thin Film</b>
« Previous Article | Next Article »
OSA is a member of 