DocumentCode :
954413
Title :
Detecting instability in concavity trees
Author :
Marlow, B.K. ; Batchelor, B.G.
Author_Institution :
University of Southampton, Department of Electronics, Southampton, UK
Volume :
16
Issue :
4
fYear :
1980
Firstpage :
138
Lastpage :
139
Abstract :
A simple algorithm is described for detecting the possibility of encountering instability in the set of concavity trees generated from a class of very similar shapes (i.e. those which can be represented by a single archetype). The algorithm can detect instability in deep m-concavities but is unable to accommodate shallow depressions in the edge. However, an earlier paper showed that the latter can be tolerated by a simple modification to the concavity-tree generator. Once the potential for instability has been detected, it is usually obvious what course of action is necessary; the instability detector is intended to avoid applying tree-matching procedures in an inappropriate way.
Keywords :
pattern recognition; computerised pattern recognition; concavity trees; instability; instability detector;
fLanguage :
English
Journal_Title :
Electronics Letters
Publisher :
iet
ISSN :
0013-5194
Type :
jour
DOI :
10.1049/el:19800102
Filename :
4243897
Link To Document :
بازگشت