Prior-based segmentation by projective registration and level sets

Tammy Riklin-Raviv, Nahum Kiryati, Nir Sochen

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

29 Scopus citations


Object detection and segmentation can be facilitated by the availability of a reference object. However, accounting for possible transformations between the different object views, as part of the segmentation process, remains a challenge. Recent works address this problem by using comprehensive training data. Other approaches are applicable only to limited object classes or can only accommodate similarity transformations. We suggest a novel variational approach to prior-based segmentation, which accounts for planar projective transformation, using a single reference object. The prior shape is registered concurrently with the segmentation process, without point correspondence. The algorithm detects the object of interest and correctly extracts its boundaries. The homography between the two object views is accurately recovered as well. Extending the Chan-Vese level set frame-work, we propose a region-based segmentation functional that includes explicit representation of the projective homography between the prior shape and the shape to segment. The formulation is derived from two-view geometry. Segmentation of a variety of objects is demonstrated and the recovered transformation is verified.

Original languageEnglish
Title of host publicationProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
Number of pages8
StatePublished - 1 Dec 2005
Externally publishedYes
EventProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005 - Beijing, China
Duration: 17 Oct 200520 Oct 2005

Publication series

NameProceedings of the IEEE International Conference on Computer Vision


ConferenceProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Prior-based segmentation by projective registration and level sets'. Together they form a unique fingerprint.

Cite this