Summary: Technische Universit¨ at Hamburg--Harburg
Technische Informatik I
Efficient Parallel Algorithms for the
Extraction of Image Features with
Adjustable Invariance Properties
M. N¨olle, G. Schreiber, H. Schulz­Mirbach
Internal Report 5/94
June 1994

Efficient Parallel Algorithms for the Extraction of
Image Features with Adjustable Invariance
Properties \Lambda
Michael N¨olle, Gerald Schreiber, Hanns Schulz­Mirbach
TU Hamburg­Harburg
Institut f¨ur Technische Informatik I
Postfach 90 10 52, 21079 Hamburg, Germany
Abstract
The paper presents algorithms for the construction of features which are invariant
with respect to a given finite transformation group. We show that it is in principle
possible to construct complete feature sets. The developed methods are general and

Source: Albert-Ludwigs-Universität Freiburg, Institut für Informatik,, Lehrstuhls für Mustererkennung und Bildverarbeitung

Collections: Computer Technologies and Information Sciences