Sciweavers

Share
CVPR
2011
IEEE

Contour Based Joint Clustering of Multiple Segmentations

8 years 5 months ago
Contour Based Joint Clustering of Multiple Segmentations
We present an unsupervised, shape-based method for joint clustering of multiple image segmentations. Given two or more closely-related images, such as nearby frames in a video sequence or images of the same scene taken under different lighting conditions, our method generates a joint segmentation of the images. We introduce a novel contourbased representation that allows us to cast the shape-based joint clustering problem as a quadratic semi-assignment problem. Our score function is additive. We use complexvalued affinities to assess the quality of matching the edge elements at the exterior bounding contour of clusters, while ignoring the contributions of elements that fall in the interior of the clusters. We further combine this contour-based score with region information and use a linear programming relaxation to solve for the joint clusters. We evaluate our approach on the occlusion boundary data-set of Stein et al.
Daniel Glasner, Shiv Vitaladevuni, Ronen Basri
Added 09 May 2011
Updated 09 May 2011
Type Journal
Year 2011
Where CVPR
Authors Daniel Glasner, Shiv Vitaladevuni, Ronen Basri
Comments (0)
books