Summary: Invariant features for gray scale images
Hanns Schulz­Mirbach
Technische Universit¨at Hamburg­Harburg
Institut f¨ur Technische Informatik I
21071 Hamburg, Germany
Abstract. Invariant features are image characteristics which remain un­
changed under the action of a transformation group. We consider in this
paper image rotations and translations and present algorithms for con­
structing invariant features. After briefly sketching the theoretical back­
ground we develop algorithms for recognizing several objects in a single
scene without the necessity to segment the image beforehand. The ob­
jects can be rotated and translated independently. Moderate occlusions
are tolerable. Furthermore we show how to use these techniques for the
recognition of articulated objects. The methods work directly with the
gray values and do not rely on the extraction of geometric primitives like
edges or corners in a preprocessing step. All algorithms have been imple­
mented and tested both on synthetic and real image data. We present
some illustrative experimental results.
1 Introduction
For most recognition tasks in digital image processing the object position in the

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

Collections: Computer Technologies and Information Sciences