Hierarchical Image Segmentation using a Watershed Scale-Space Tree

Fisher, Mark H. and Aldridge, Richard V. (1999) Hierarchical Image Segmentation using a Watershed Scale-Space Tree. In: 7th International Conference on Image Processing and Its Applications, 1999-07-13 - 1999-07-15, University of Manchester.

Full text not available from this repository. (Request a copy)


The watershed transformation is a useful morphological segmentation tool which has been used in a variety of grey-scale image processing applications. However, a major problem with the watershed transformation is that it produces a severe over-segmentation due to the great number of minima embedded in the image or its gradient, and therefore it is rarely applied directly to images. In this paper we discuss modifications to the basic watershed transformation that enable watershed scale trees to be produced and we illustrate the approach with some example segmentations taken from a medical image processing application. The mapping between image and scale tree allows the user to overcome the over-segmentation by either setting a global threshold or interactively editing the tree description of the image.

Item Type: Conference or Workshop Item (Other)
Faculty \ School: Faculty of Science > School of Computing Sciences
UEA Research Groups: Faculty of Science > Research Groups > Interactive Graphics and Audio
Depositing User: EPrints Services
Date Deposited: 01 Oct 2010 13:41
Last Modified: 16 Jul 2024 23:42
URI: https://ueaeprints.uea.ac.uk/id/eprint/3021
DOI: 10.1049/cp:19990377

Actions (login required)

View Item View Item