Summary: A Parallel Watershed Algorithm \Lambda
Andreas Bieniek, Hans Burkhardt
Albert­Ludwigs­Universit¨at Freiburg
Lehrstuhl f¨ur Mustererkennung und Bildverarbeitung
Am Flughafen 17, D­79085 Freiburg, Germany
Heiko Marschner, Gerald Schreiber
Technische Universit¨at Hamburg--Harburg
Technische Informatik I
Harburger Schloßstraße 20, D­21071 Hamburg, Germany
Michael N¨olle
University of Vienna
Institute for Software Technology and Parallel Systems
Lichtensteinstr. 22, A­1090 Wien, Austria
Abstract
The watershed transformation is a popular image segmentation algorithm for grey scale images. Sequen­
tial watershed algorithms perform a highly data dependent flooding process over the global image. Parallel
algorithms which distribute the image over the available processors and simulate the flooding process have a
limited, data dependent speedup. This is due to global data dependencies over the sub­domains. For images
without plateaus the presented formalism, based on a local condition, leads to a parallel algorithm with almost
data independent runtime. Temporary labels are inserted where the solution depends on neighboring results.

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

Collections: Computer Technologies and Information Sciences