A Neuron-MOS-Based VLSI Implementation of Pulse-Coupled Neural Networks for Image Feature Generation

An analog circuit for implementing pulse-coupled neural networks (PCNNs) in very-large-scale integration (VLSI) hardware has been developed using the Neuron-MOS (νMOS) technology. PCNNs are biologically inspired models having powerful ability for image feature generation. With the νMOS technology, weighted sum of multiple input signals, which is an essential of PCNNs, is implemented simply by the capacitive coupling effect in a νMOS block. By employing the switched floating gates in the νMOS blocks as temporary analog memories, the storage of image data is simply realized. Moreover, the function of decay generation, which is crucial for emulating PCNNs neuronal dynamics, is also merged into a νMOS block by utilizing the input-terminal capacitors in it. With such techniques, the circuit achieves a purely voltage-mode implementation of PCNNs in a compact structure. Inheriting the merits of PCNNs, the circuit has good discriminability against different patterns as well as robustness against rotation and translation of identical patterns, which is analogous to human image perception. The performance of the circuit has been verified by the measurements of a proof-of-concept chip fabricated in a 0.35- μm double-polysilicon CMOS technology.

[1]  Timothy K. Horiuchi,et al.  A Neuromorphic VLSI Model of Bat Interaural Level Difference Processing for Azimuthal Echolocation , 2007, IEEE Transactions on Circuits and Systems I: Regular Papers.

[2]  Guojun Lu,et al.  Review of shape representation and description techniques , 2004, Pattern Recognit..

[3]  M. Khakani,et al.  Room-Temperature Deposited Titanium Silicate Thin Films for MIM Capacitor Applications , 2007, IEEE Electron Device Letters.

[4]  Xiaodong Gu,et al.  Image shadow removal using pulse coupled neural network , 2005, IEEE Transactions on Neural Networks.

[5]  Tadashi Shibata,et al.  Neuron MOS binary-logic integrated circuits. I. Design fundamentals and soft-hardware-logic circuit implementation , 1993 .

[6]  Martin Schäfer,et al.  An accelerator for neural networks with pulse-coded model neurons , 1999, IEEE Trans. Neural Networks.

[7]  Jun Chen,et al.  A Hardware-Implementation-Friendly Pulse-Coupled Neural Network Algorithm for Analog Image-Feature-Generation Circuits , 2007 .

[8]  Jason M. Kinser,et al.  Image Processing using Pulse-Coupled Neural Networks , 1998, Perspectives in Neural Computing.

[9]  Y. Ota.  VLSI structure for static image processing with pulse-coupled neural network , 2002, IEEE 2002 28th Annual Conference of the Industrial Electronics Society. IECON 02.

[10]  Alan Wee-Chung Liew,et al.  Information-Based Color Feature Representation for Image Classification , 2007, 2007 IEEE International Conference on Image Processing.

[11]  Scott E. Umbaugh,et al.  Computer Imaging: Digital Image Analysis and Processing , 2005 .

[12]  Jason M. Kinser,et al.  Image object signatures from centripetal autowaves , 2000, Pattern Recognit. Lett..

[13]  Tadahiro Ohmi,et al.  Neuron MOS binary-logic integrated circuits. II. Simplifying techniques of circuit configuration and their practical applications , 1993 .

[14]  R. Schuffny,et al.  Simulation and implementation of an analog VLSI pulse-coupled neural network for image segmentation , 2004, The 2004 47th Midwest Symposium on Circuits and Systems, 2004. MWSCAS '04..

[15]  Tadashi Shibata,et al.  Clocked-neuron-MOS logic circuits employing auto-threshold-adjustment , 1995, Proceedings ISSCC '95 - International Solid-State Circuits Conference.

[16]  Elisa Ricci,et al.  Cellular Neural Networks With Virtual Template Expansion for Retinal Vessel Segmentation , 2007, IEEE Transactions on Circuits and Systems II: Express Briefs.

[17]  John L. Johnson,et al.  PCNN models and applications , 1999, IEEE Trans. Neural Networks.

[18]  Mikael Millberg,et al.  Image analysis for airborne reconnaissance and missile applications , 2000, Pattern Recognit. Lett..

[19]  Ali A. Minai,et al.  Temporally sequenced intelligent block-matching and motion-segmentation using locally coupled networks , 2004, IEEE Transactions on Neural Networks.

[20]  Igor M. Filanovsky,et al.  CMOS Schmitt trigger design , 1994 .

[21]  Zhang Yi,et al.  Binary Fingerprint Image Thinning Using Template-Based PCNNs , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[22]  I. Mokris,et al.  Feature generation improving by optimized PCNN , 2008, 2008 6th International Symposium on Applied Machine Intelligence and Informatics.

[23]  Bo Yu,et al.  Pulse-coupled neural networks for contour and motion matchings , 2004, IEEE Transactions on Neural Networks.

[24]  Raul Cristian Muresan,et al.  Pattern recognition using pulse-coupled neural networks and discrete Fourier transforms , 2003, Neurocomputing.

[25]  Yuichi Motai,et al.  Salient feature extraction of industrial objects for an automated assembly system , 2005, Comput. Ind..

[26]  Alejandro Rodríguez,et al.  A soft image edge detection approach based on the time matrix of a PCNN , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[27]  Carsten Wolff,et al.  PCNN neurocomputers - Event driven and parallel architectures , 2002, ESANN.

[28]  Bogdan M. Wilamowski,et al.  CMOS architecture of synchronous pulse-coupled neural network and its application to image processing , 2000, 2000 26th Annual Conference of the IEEE Industrial Electronics Society. IECON 2000. 2000 IEEE International Conference on Industrial Electronics, Control and Instrumentation. 21st Century Technologies.

[29]  Chung-Yu Wu,et al.  The Design and Analysis of a CMOS Low-Power Large-Neighborhood CNN With Propagating Connections , 2009, IEEE Transactions on Circuits and Systems I: Regular Papers.

[30]  Bogdan M. Wilamowski,et al.  Analog implementation of pulse-coupled neural networks , 1999, IEEE Trans. Neural Networks.

[31]  Vlatko Becanovic.  Image object classification using saccadic search, spatio-temporal pattern encoding and self-organisation , 2000, Pattern Recognit. Lett..

[32]  S. Getzlaff,et al.  An Analog VLSI Pulsed Neural Network Implementation for Image Segmentation , 2004 .