A Multilevel Parallel Processing Approach to Scene Labeling Problems

Authors:
Hsi-Ho Liu;Amitava Das
Affiliations:
Vanderbilt Univ., Nashville;Univ. of Miami, Coral Gables, FL
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
1988

Citing 4
Cited 1

The complexity of some polynomial network consistency algorithms for constraint satisfaction problems

Artificial Intelligence
Parallel Computer Architectures and Problem Solving Strategies for the Consistent Labeling Problem

IEEE Transactions on Computers
Computer Vision

Computer Vision
Introduction to VLSI Systems

Introduction to VLSI Systems

A Neural Network Approach to the Labeling of Line Drawings

IEEE Transactions on Computers - Special issue on artificial neural networks

Quantified Score

Hi-index	0.14

Visualization

Abstract

A parallel tree search procedure and multilevel array architectures are presented for scene labeling problems. In the scene labeling problem, when the number of variables is not large, e.g. less than 100, its solutions and search space are not expected to greatly increase with problem size. The multilevel arrays only use a polynomial number of processors at each level and a bus or mesh connection for interlevel communication. This approach is very efficient compared to the binary-tree machine if the number of nodes in the search tree of labeling problem increases polynomially with the number of variables. Because of its regular structure, the multilevel array is particularly suitable for VLSI implementation.