Contour-Based Joint Clustering of Multiple Segmentations

Daniel Glasner, Shiv N. Vitaladevuni, Ronen Basri

Research output: Contribution to journalConference articlepeer-review


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 contour-based 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 complex-valued 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.
Original languageEnglish
Pages (from-to)92
Number of pages8
Journal2011 Ieee Conference On Computer Vision And Pattern Recognition (Cvpr)
StatePublished - 2011
EventIEEE Conference on Computer Vision and Pattern Recognition (CVPR) - Colorado Springs, CO
Duration: 20 Jun 201125 Jun 2011


Dive into the research topics of 'Contour-Based Joint Clustering of Multiple Segmentations'. Together they form a unique fingerprint.

Cite this