A Hardware-Implementation-Friendly Pulse-Coupled Neural Network Algorithm for Analog Image-Feature-Generation Circuits

Pulse-coupled neural networks (PCNNs) are biologically inspired algorithms that have been shown to be highly effective for image feature generation. However, conventional PCNNs are software-oriented algorithms that are too complicated to implement as very-large-scale integration (VLSI) hardware. To employ PCNNs in image-feature-generation VLSIs, a hardware-implementation-friendly PCNN is proposed here. By introducing the concepts of exponentially decaying output and a one-branch dendritic tree, the new PCNN eliminates the large number of convolution operators and floating-point multipliers in conventional PCNNs without compromising its performance at image feature generation. As an analog VLSI implementation of the new PCNN, an image-feature-generation circuit is proposed. By employing floating-gate metal–oxide–semiconductor (MOS) technology, the circuit achieves a full voltage-mode implementation of the PCNN in a compact structure. Inheriting the merits of the PCNN, the circuit is capable of generating rotation-independent and translation-independent features for input patterns, which has been verified by SPICE simulation.

[1]  Tadashi Shibata,et al.  An image representation algorithm compatible with neural-associative-processor-based hardware recognition systems , 2003, IEEE Trans. Neural Networks.

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

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

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

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

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

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

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

[9]  Jason M. Kinser,et al.  Inherent features of wavelets and pulse coupled networks , 1999, IEEE Trans. Neural Networks.

[10]  Jason M. Kinser,et al.  Theoretical foundation of the intersecting cortical model and its use for change detection of aircraft, cars, and nuclear explosion tests , 2004, Signal Process..

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

[12]  J. L. Johnson.  Pulse-coupled neural nets: translation, rotation, scale, distortion, and intensity signal invariance for images. , 1994, Applied optics.

[13]  Tadashi Shibata,et al.  A functional MOS transistor featuring gate-level weighted sum and threshold operations , 1992 .

[14]  Jason M. Kinser,et al.  The intersecting cortical model in image processing , 2004 .