Relational matching
- 15 May 1987
- journal article
- Published by Optica Publishing Group in Applied Optics
- Vol. 26 (10) , 1845-1851
- https://doi.org/10.1364/ao.26.001845
Abstract
The problem of computer vision is to give a computer a representation of a picture of a scene and have it figure out what objects are in the scene and in what spatial relationships. This involves low-level vision (image processing), midlevel vision (feature extraction and measurement), and high-level vision (interpretation). One important part of high-level vision is relational matching, the process of matching two relational descriptions of objects, often for the purpose of object identification. In this paper, we describe several kinds of relational matching, give sequential algorithms for solving relational matching problems, and briefly discuss parallel algorithm possibilities.Keywords
This publication has 7 references indexed in Scilit:
- Computer Architecture for Solving Consistent Labelling ProblemsThe Computer Journal, 1985
- A Metric for Comparing Relational DescriptionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1985
- Organization of Relational Models for Scene AnalysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1982
- Structural Descriptions and Inexact MatchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1981
- The Consistent Labeling Problem: Part IIPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1980
- The Consistent Labeling Problem: Part IIEEE Transactions on Pattern Analysis and Machine Intelligence, 1979
- Scene Labeling by Relaxation OperationsIEEE Transactions on Systems, Man, and Cybernetics, 1976