Share Email Print
cover

Proceedings Paper

Continuous-time segmentation networks
Author(s): John G. Harris
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Segmentation is a basic problem in computer vision. The tiny-tanh network, a continuous-time network that segments scenes based upon intensity, motion, or depth is introduced. The tiny- tanh algorithm maps naturally to analog circuitry since it was inspired by previous experiments with analog VLSI segmentation hardware. A convex Lyapunov energy is utilized so that the system does not get stuck in local minima. No annealing algorithms of any kind are necessary- -a sharp contrast to previous software/hardware solutions of this problem.

Paper Details

Date Published: 9 July 1991
PDF: 12 pages
Proc. SPIE 1473, Visual Information Processing: From Neurons to Chips, (9 July 1991); doi: 10.1117/12.45549
Show Author Affiliations
John G. Harris, California Institute of Technology and Hughes Aircraft Artificial Intelligence Ctr. (United States)


Published in SPIE Proceedings Vol. 1473:
Visual Information Processing: From Neurons to Chips
Bimal P. Mathur; Christof Koch, Editor(s)

© SPIE. Terms of Use
Back to Top