Relaxation methods for supervised image segmentation

Michael W. Hansen, William E. Higgins

Research output: Contribution to journalArticlepeer-review

32 Scopus citations

Abstract

We propose two methods for supervised image segmentation: supervised relaxation labeling and watershed-driven relaxation labeling. The methods are particularly well suited to problems in 3D medical image analysis, where the images are large, the regions are topologically complex, and the tolerance of errors is low. Each method uses predefined cues for supervision. The cues can be defined interactively or automatically, depending on the application. The cues provide statistical region information and region topological constraints. Supervised relaxation labeling exhibits strong noise resilience. Watershed-driven relaxation labeling combines the strengths of watershed analysis and supervised relaxation labeling to give a computationally efficient noise-resistant method. Extensive results for 2D and 3D images illustrate the effectiveness of the methods.

Original languageEnglish (US)
Pages (from-to)949-962
Number of pages14
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume19
Issue number9
DOIs
StatePublished - Dec 1 1997

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Relaxation methods for supervised image segmentation'. Together they form a unique fingerprint.

Cite this