Parallel Distributed Networks for Image Smoothing and Segmentation in Analog VSLI
Abstract
Image smoothing and segmentation algorithms are frequently formulated as optimization problems. Linear and nonlinear (reciprocal) resistive networks have solutions characterized by an extremum principle. Thus, appropriately designed networks can automatically solve certain smoothing and segmentation problems in robot vision. This paper considers switched linear resistive networks and nonlinear resistive networks for such tasks. A new derivation of the latter network type from the former is given via an intermediate stochastic formulation, and a new result relating the solution sets of the two is given for the zero temperature limit. We then present simulation studies of several continuation methods that can be gracefully implemented in analog VLSI and that seem to give 'good' results for these non-convex optimization problems.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 1989
- Accession Number
- ADA216780
Entities
People
- A. Lumsdaine
- I. Elfadel
- J. Wyatt
Organizations
- Massachusetts Institute of Technology