Image segmentation through energy minimization based subspace fusion

Jason J. Corso, Maneesh Dewan, Gregory D. Hager

Research output: Contribution to journalConference articlepeer-review


In this paper we present an image segmentation technique that fuses contributions from multiple feature subspaces using an energy minimization approach. For each subspace, we compute a per-pixel quality measure and perform a partitioning through the standard normalized cut algorithm [12]. To fuse the subspaces into a final segmentation, we compute a subspace label for every pixel. The labeling is computed through the graph-cut energy minimization framework proposed by [3], Finally, we combine the initial subspace segmentation with the subspace labels obtained from the energy minimization to yield the final segmentation. We have implemented the algorithm and provide results for both synthetic and real images.

Original languageEnglish (US)
Pages (from-to)120-123
Number of pages4
JournalProceedings - International Conference on Pattern Recognition
StatePublished - 2004
EventProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004 - Cambridge, United Kingdom
Duration: Aug 23 2004Aug 26 2004

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Image segmentation through energy minimization based subspace fusion'. Together they form a unique fingerprint.

Cite this