A systematic performance evaluation of interactive image segmentation based on simulated user interaction

Emmanouil Moschidis, James Graham

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

23 Downloads (Pure)

Abstract

In this paper we report on results of a systematic performance evaluation of three efficient image segmentation algorithms, namely Graph-Cuts, Random Walker and Grow-cut. The evaluation focuses on their function as the computational part of an interactive segmentation system. The implications caused by the human involvement in the overall process are avoided by simulating two different patterns of user interaction. The methods are evaluated with respect to accuracy, precision, efficiency and parameter sensitivity on three-dimensional medical images. The results provide useful insight regarding the algorithmic performance of the selected techniques and the esffect of the identified patterns of interaction on the segmentation outcome.
Original languageEnglish
Title of host publicationIEEE International Symposium on Biomedical Imaging: From Nano to Macro
EditorsWiro Niessen, Erik Meijering Meijering
PublisherIEEE
Pages928-931
Number of pages4
ISBN (Print)978-1-4244-4126-6
Publication statusPublished - 14 Apr 2010
EventIEEE International Symposium on Biomedical Imaging: From Nano to Macro - Rotterdam, The Netherlands
Duration: 14 Apr 201014 Apr 2010

Conference

ConferenceIEEE International Symposium on Biomedical Imaging: From Nano to Macro
CityRotterdam, The Netherlands
Period14/04/1014/04/10

Keywords

  • Performance evaluation
  • Interactive image segmentation
  • Simulated user interaction
  • 3-D medical images
  • Graph-Cuts
  • Random-Walker
  • Grow-Cut

Fingerprint

Dive into the research topics of 'A systematic performance evaluation of interactive image segmentation based on simulated user interaction'. Together they form a unique fingerprint.

Cite this