Synthesis of Nonseparable 3-D Spatiotemporal Bandpass Filters on Analog Networks

Linear cellular neural networks (CNNs) are capable of performing efficient spatiotemporal filtering operations as recursive infinite impulse response (IIR) filters. Particularly, linear CNNs can be characterized as a spatial frequency-dependent recursive temporal filter with complex coefficients. Based on a modified version of the CNN paradigm recently proposed by the authors, nonseparable spatiotemporal bandpass filters with tunable spatiotemporal passband volumes are synthesized. The filters reported here qualitatively resemble spatiotemporal receptive field models for the primary visual cortex. Numerical simulation results confirm the bandpass characteristics of our filtering network.

[1]  Bertram E. Shi,et al.  An eight layer cellular neural network for spatio‐temporal image filtering , 2006, Int. J. Circuit Theory Appl..

[2]  Moustafa M. Fahmy,et al.  Analysis of N-D general-support filters , 1985, IEEE Trans. Acoust. Speech Signal Process..

[3]  Eero P. Simoncelli,et al.  A model of neuronal responses in visual area MT , 1998, Vision Research.

[4]  I. Ohzawa,et al.  Spatiotemporal organization of simple-cell receptive fields in the cat's striate cortex. II. Linearity of temporal and spatial summation. , 1993, Journal of neurophysiology.

[5]  Valeri Mladenov,et al.  Cellular Neural Networks: Theory And Applications , 2004 .

[6]  Leon O. Chua,et al.  Design of linear cellular neural networks for motion sensitive filtering , 1993 .

[7]  Emmanuel M. Drakakis,et al.  Analog networks for mixed domain spatiotemporal filtering , 2005, 2005 IEEE International Symposium on Circuits and Systems.

[8]  E.M. Drakakis,et al.  Towards Analog VLSI Arrays for Nonseparable 3D Spatiotemporal Filtering , 2006, 2006 10th International Workshop on Cellular Neural Networks and Their Applications.

[9]  Bertram E. Shi,et al.  Gabor-type filtering in space and time with cellular neural networks , 1998 .

[10]  D. Ruderman,et al.  INDEPENDENT COMPONENT ANALYSIS OF NATURAL IMAGE SEQUENCES YIELDS SPATIOTEMPORAL FILTERS SIMILAR TO SIMPLE CELLS IN PRIMARY VISUAL CORTEX , 1998 .

[11]  István Petrás,et al.  A bio-inspired two-layer mixed-signal flexible programmable chip for early vision , 2003, IEEE Trans. Neural Networks.

[12]  Emmanuel M. Drakakis,et al.  On Analog Networks and Mixed-Domain Spatio-Temporal Frequency Response , 2008, IEEE Transactions on Circuits and Systems I: Regular Papers.

[13]  D. Ruderman,et al.  Independent component analysis of natural image sequences yields spatio-temporal filters similar to simple cells in primary visual cortex , 1998, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[14]  Hans Knutsson,et al.  Signal processing for computer vision , 1994 .

[15]  Antonio Torralba,et al.  An efficient neuromorphic analog network for motion estimation , 1999 .

[16]  Kenneth W. Martin,et al.  Complex signal processing is not - complex , 2004, ESSCIRC 2004 - 29th European Solid-State Circuits Conference (IEEE Cat. No.03EX705).

[17]  I. Ohzawa,et al.  Spatiotemporal organization of simple-cell receptive fields in the cat's striate cortex. I. General characteristics and postnatal development. , 1993, Journal of neurophysiology.

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

[19]  J. Shanks,et al.  Stability criterion for N -dimensional digital filters , 1973 .