OPTIMAL CONVOLUTION FILTERS AND AN ALGORITHM FOR THE DETECTION OF WIDE LINEAR FEATURES

Authors
PETROU M
Citation
M. Petrou, OPTIMAL CONVOLUTION FILTERS AND AN ALGORITHM FOR THE DETECTION OF WIDE LINEAR FEATURES, IEE proceedings. Part I. Communications, speech and vision, 140(5), 1993, pp. 331-339
Citations number
14
Categorie Soggetti
Engineering, Eletrical & Electronic
Journal title
IEE proceedings. Part I. Communications, speech and vision → ACNP
ISSN journal
09563776
Volume
140
Issue
5
Year of publication
1993
Pages
331 - 339
Database
ISI
SICI code
0956-3776(1993)140:5<331:OCFAAA>2.0.ZU;2-T
Abstract
The author presents the theory for developing optimal convolution filt ers for the identification of wide linear features and an algorithm fo r distinguishing them from other types of image feature. Some filters are given and the results of applying the algorithm to some real image s are shown. These filters, and the algorithm, are appropriate for use in knowledge based systems which aim at identifying roads, canals, he dges and rivers in images, or in digitised maps.