Misalignment measure based on Hermann Weyl's

Autoren Bernhard Moser
Thomas Hoch
Editoren A. Kuijper
B. Heise
L. Muresan
Titel Misalignment measure based on Hermann Weyl's
Buchtitel Proceedings of 32nd Workshop of the Austrian Association for Pattern Recogntion (AAPT/OAGM), Challenges in the Biosciences: Image Analysis and Pattern Recognition Aspects
Typ in Konferenzband
Verlag OCG
Ort Linz, Austria
Abteilung KVS
ISBN 978-3-85403-232-8
Monat May
Jahr 2008
Seiten 187-198
SCCH ID# 805
Abstract

Similarity measures for translationally misaligned image patterns are studied. It turns out that for measures based on standard concepts like crosscorrelation, Lp-norm and mutual information monotonicity with respect to the extent of misalignment can not be guarantueed. In this paper we introduce a novel distance measure for images based on Hermann Weyl's discrepancy concept which relies on the evaluation of partial sums. In contrast to standard concepts in this case monotonicity, positive-definiteness and a homogenously linear upper bound with respect to the extent of misalignment can be proven. It is shown that this monotonicity property is not influenced by the image's frequencies or other characteristics which makes this new similarity measure predestinated for similarity-based registration, tracking and segmentation.