Boundary Preserving Dense Local Regions

9 years 3 months ago
Boundary Preserving Dense Local Regions
We propose a dense local region detector to extract features suitable for image matching and object recognition tasks. Whereas traditional local interest operators rely on repeatable structures that often cross object boundaries (e.g., corners, scale-space blobs), our sampling strategy is driven by segmentation, and thus preserves object boundaries and shape. At the same time, whereas existing regionbased representations are sensitive to segmentation parameters and object deformations, our novel approach to robustly sample dense sites and determine their connectivity offers better repeatability. In extensive experiments, we find that the proposed region detector provides significantly better repeatability and localization accuracy for object matching compared to an array of existing detectors. In addition, we show our regions lead to excellent results on two benchmark tasks that require good feature matching: weakly supervised foreground discovery, and nearest neighbor-based object ...
Jaechul Kim, Kristen Grauman
Added 08 Apr 2011
Updated 29 Apr 2011
Type Journal
Year 2011
Where CVPR
Authors Jaechul Kim, Kristen Grauman
Comments (0)