Optical implementation of cellular neural networks based on bias and joint correlation.

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.

[1]  Jun Li,et al.  EXPERIMENTAL INVESTIGATION OF A REAL-TIME NONLINEAR JOINT TRANSFORM CORRELATOR , 1994 .

[2]  Jonathan S. Kane,et al.  POPART: partial optical implementation of adaptive resonance theory 2 , 1993, IEEE Trans. Neural Networks.

[3]  Norbert Fruehauf,et al.  Fourier optical realization of cellular neural networks , 1993 .

[4]  D Psaltis,et al.  Optical implementation of the Hopfield model. , 1985, Applied optics.

[5]  Francis T. S. Yu,et al.  Adaptive real-time pattern recognition using a liquid crystal TV based joint transform correlator. , 1987, Applied optics.

[6]  C C Guest,et al.  Designs and devices for optical bidirectional associative memories. , 1987, Applied optics.

[7]  Jean-Louis de Bougrenet de la Tocnaye,et al.  Real-time demonstration of an on-board nonlinear joint transform correlator system , 1997 .

[8]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[9]  T Yatagai,et al.  Reversal-input superposing technique for all-optical neural networks. , 1994, Applied optics.

[10]  M Deutsch,et al.  Multichannel single-output color pattern recognition by use of a joint-transform correlator. , 1996, Applied optics.

[11]  X M Wang,et al.  Optical neural network with bipolar neural states. , 1992, Applied optics.

[12]  Leon O. Chua,et al.  Cellular neural networks: applications , 1988 .

[13]  J F Walkup,et al.  Outer product processor using polarization encoding. , 1990, Applied optics.

[14]  Kehar Singh,et al.  Experimental and simulation studies on the performance of binary and gray-valued joint transform correlators under poor illumination conditions and nonoverlapping background noise , 1997 .

[15]  B Javidi,et al.  Optical implementation of neural networks for face recognition by the use of nonlinear joint transform correlators. , 1995, Applied optics.

[16]  G. J. Dunning,et al.  Holographic associative memory with nonlinearities in the correlation domain. , 1987, Applied optics.

[17]  J. M. Florence,et al.  Joint-transform correlator systems using deformable-mirror spatial light modulators. , 1989, Optics letters.

[18]  B E Saleh,et al.  Optical implementation of the Hopfield algorithm using correlations. , 1990, Applied optics.

[19]  M S Zubairy,et al.  Implementation of associative memory using grating structures. , 1994, Applied optics.

[20]  J. Goodman,et al.  A technique for optically convolving two functions. , 1966, Applied optics.

[21]  F T Yu,et al.  Implementation of a non-zero-order joint-transform correlator by use of phase-shifting techniques. , 1997, Applied optics.

[22]  Shizhuo Yin,et al.  NONZERO-ORDER JOINT TRANSFORM CORRELATOR , 1998 .

[23]  Feng Cheng,et al.  Removal of intra-class associations in joint transform power spectrum , 1993 .

[24]  Hidemitsu Ogawa,et al.  Optoelectronic architecture for cellular neural networks based on a new bias method and spatial coding scheme , 1997 .