Waterball - IterativeWatershed Algorithm with Reduced Oversegmentation

Michal Swiercz , Marcin Iwanowski

Abstract

In this paper we present a new approach to watershed algorithm for segmentation of digital grey-scale images. The approach is derived from rainfall-type watershed methods, but utilises a different method of path tracing and iterative gradient image preparation to reduce oversegmentation and yield better results in object extraction. Sample results are discussed, with emphasis on their global correctness and practical applications.
Author Michal Swiercz
Michal Swiercz,,
-
, Marcin Iwanowski (FoEE / ICIE)
Marcin Iwanowski,,
- The Institute of Control and Industrial Electronics
Pages385-394
Book Burduk Robert, Kurzyński Marek, Woźniak Michał, Żołnierek Andrzej (eds.): Computer Recognition Systems 4, Advances in Intelligent and Soft Computing, no. 95, 2011, Springer Berlin Heidelberg, ISBN 978-3-642-20319-0, 978-3-642-20320-6
Keywords in EnglishArtificial Intelligence (incl. Robotics), Computational Intelligence
URL http://link.springer.com/chapter/10.1007/978-3-642-20320-6_40
Score (nominal)4
Publication indicators WoS Citations = 1
Citation count*1 (2020-02-20)
Cite
Share Share

Get link to the record


* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Back
Confirmation
Are you sure?