Neuromorphic Excitable Maps for Visual Processing

An excitable membrane is described which can perform different visual tasks such as contour detection, contour propagation, image segmentation, and motion detection. The membrane is designed to fit into a neuromorphic multichip system. It consists of a single two-dimensional (2-D) layer of locally connected integrate-and-fire neurons and propagates input in the subthreshold and the above-threshold range. It requires adjustment of only one parameter to switch between the visual tasks. The performance of two spiking membranes of different connectivity is compared, a hexagonally and an octagonally connected membrane. Their hardware and system suitability is discussed

[1]  Tetsuya Yagi,et al.  An analog silicon retina with multichip configuration , 2006, IEEE Transactions on Neural Networks.

[2]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Gustavo Deco,et al.  Computational neuroscience of vision , 2002 .

[4]  Shih-Chii Liu,et al.  Analog VLSI: Circuits and Principles , 2002 .

[5]  Christoph Rasche,et al.  Visual shape recognition with contour propagation , 2005, Biological Cybernetics.

[6]  Carver Mead,et al.  Analog VLSI and neural systems , 1989 .

[7]  Christoph Rasche,et al.  Speed estimation with propagation maps , 2006, Neurocomputing.

[8]  Rodney J. Douglas,et al.  Forward- and backpropagation in a silicon dendrite , 2001, IEEE Trans. Neural Networks.

[9]  H. Blum.  Biological shape and visual science. I. , 1973, Journal of theoretical biology.

[10]  Martin Wilson,et al.  The lateral spread of signal between bipolar cells of the tiger salamander retina , 2004, Biological Cybernetics.

[11]  Rodney J. Douglas,et al.  A pulse-coded communications infrastructure for neuromorphic systems , 1999 .

[12]  P Perona,et al.  Preattentive texture discrimination with early vision mechanisms. , 1990, Journal of the Optical Society of America. A, Optics and image science.

[13]  C. Mead,et al.  Neuromorphic Robot Vision with Mixed Analog- Digital Architecture , 2005 .

[14]  H. Blum.  Biological shape and visual science (part I) , 1973 .

[15]  Kwabena Boahen,et al.  A Retinomorphic Chip with Parallel Pathways: Encoding INCREASING, ON, DECREASING, and OFF Visual Signals , 2002 .

[16]  Christoph Rasche.  The Making of a Neuromorphic Visual System , 2004 .

[17]  Davis Barch,et al.  Motion detection and characterization by an excitable membrane: The "bow wave" model , 1999, Neurocomputing.

[18]  C. Mead,et al.  The silicon retina. , 1991 .

[19]  J. J. Hopfield,et al.  Pattern recognition computation using action potential timing for stimulus representation , 1995, Nature.

[20]  Denis Fize,et al.  Speed of processing in the human visual system , 1996, Nature.

[21]  F. Werblin,et al.  Spatiotemporal patterns at the retinal output. , 1998, Journal of neurophysiology.

[22]  Simon J. Thorpe,et al.  Spike arrival times: A highly efficient coding scheme for neural networks , 1990 .

[23]  Christoph Rasche,et al.  Signaling contours by neuromorphic wave propagation , 2004, Biological Cybernetics.

[24]  W. G. Owen,et al.  Receptive field of the retinal bipolar cell: a pharmacological study in the tiger salamander. , 1996, Journal of neurophysiology.

[25]  John G. Elias,et al.  Artificial Dendritic Trees , 1993, Neural Computation.

[26]  Florentin Wörgötter,et al.  A neuromorphic depth-from-motion vision model with STDP adaptation , 2006, IEEE Transactions on Neural Networks.

[27]  Eduardo Ros,et al.  Real-time computing platform for spiking neurons (RT-spike) , 2006, IEEE Trans. Neural Networks.

[28]  M. Potter.  Meaning in visual search. , 1975, Science.

[29]  Christoph Rasche,et al.  A neural architecture for the symmetric-axis transform , 2005, Neurocomputing.