Contour-Based Joint Clustering of Multiple Segmentations

Daniel Glasner, Shiv N. Vitaladevuni, Ronen Basri

פרסום מחקרי: פרסום בכתב עתמאמר מכנסביקורת עמיתים


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.
שפה מקוריתאנגלית
עמודים (מ-עד)92
מספר עמודים8
כתב עת2011 Ieee Conference On Computer Vision And Pattern Recognition (Cvpr)
סטטוס פרסוםפורסם - 2011
אירועIEEE Conference on Computer Vision and Pattern Recognition (CVPR) - Colorado Springs, CO
משך הזמן: 20 יוני 201125 יוני 2011

טביעת אצבע

להלן מוצגים תחומי המחקר של הפרסום 'Contour-Based Joint Clustering of Multiple Segmentations'. יחד הם יוצרים טביעת אצבע ייחודית.

פורמט ציטוט ביבליוגרפי