Abstract

Depending on the application, local feature detectors should comply with properties that are often contradictory, e.g . distinctiveness vs. robustness. Providing a good balance is a standing problem in the field. In this direction, we propose a novel approach for local feature detection starting from sampled edges. The detector is based on shape stability measures across the weighted ?-filtration, a computational ge- ometry construction that captures the shape of a non-uniform set of points. The extracted features are blob-like and include non-extremal regions as well as regions determined by cavities of boundary shape. Overall, the approach provides distinctive regions, while achieving high robustness in terms of repeatability and matching score, as well as com- petitive performance in a large scale image retrieval application.