Where academic tradition
meets the exciting future

You are here: TUCS > PUBLICATIONS > Publication Search > A Binary-Based On-Chip CNN Sol...

A Binary-Based On-Chip CNN Solution for Pixel-Level Snakes

Victor M. Brea, Mika Laiho, David Vilarino, Ari Paasio, Diego Cabello, A Binary-Based On-Chip CNN Solution for Pixel-Level Snakes. International Journal of Circuit Theory and Applications 34(4), 383–407, 2006.

Abstract:

This paper introduces a binary-based on-chip cellular neural network (CNN) solution for pixel-level snakes.
Every cell in the array comprises circuitry for B/W and grey-scale processing. The B/W processing is
performed with a positive range high-gain discrete-time (DT)CNN model with 1-bit of programmability.
The grey-scale processing is executed on a dedicated sub-cell. The design efforts are mainly focused on
area consumption and processing speed. The result is a chip with a resolution of 9×9 cells in a 0.18 m
CMOS technology process and a density of more than 700 cells/mm2. Simulations at schematic level lead
to a time of less than 100 ns for every DTCNN step. The peak power dissipation is kept at a few watts
in a hypothetical chip of 128×128 cells.

BibTeX entry:

@ARTICLE{jBrLaViPaCa06a,
  title = {A Binary-Based On-Chip CNN Solution for Pixel-Level Snakes},
  author = {Brea, Victor M. and Laiho, Mika and Vilarino, David and Paasio, Ari and Cabello, Diego},
  journal = {International Journal of Circuit Theory and Applications},
  volume = {34},
  number = {4},
  editor = {Tamas Roska, Paulo Arena Csaba Rekeczky},
  publisher = {John Wiley & Sons, Ltd.},
  pages = {383–407},
  year = {2006},
}

Belongs to TUCS Research Unit(s): Microelectronics

Publication Forum rating of this publication: level 1

Edit publication