9 July 1991 Continuous-time segmentation networks
Author Affiliations +
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.
© (1991) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
John G. Harris, John G. Harris, } "Continuous-time segmentation networks", Proc. SPIE 1473, Visual Information Processing: From Neurons to Chips, (9 July 1991); doi: 10.1117/12.45549; https://doi.org/10.1117/12.45549
PROCEEDINGS
12 PAGES


SHARE
RELATED CONTENT

Neural network for image segmentation
Proceedings of SPIE (October 13 2000)
Integrate-and-fire models for image segmentation
Proceedings of SPIE (May 30 2000)
Negative fuse network
Proceedings of SPIE (July 09 1991)
Modeling of neural net chips using image algebra
Proceedings of SPIE (November 01 1990)

Back to Top