Integration of Points of Interest and Regions of Interest

摘要

Images consist of different low-level features, such as Points of Interest (POIs) and Regions of Interest (ROIs). A distinction between POIs and ROIs is that the latter ones have intrinsic scale information while the former ones may not have. In this paper, we propose a scheme to integrate these two kinds of image features. The proposed scheme optimizes feature distribution so that the optimized features become more compact. The scheme also assigns scale information to a POI via a stable association between the POI and a certain “nearest” ROI. We test the proposed integration scheme in terms of the repeatability across various imaging transformations. The experimental results demonstrate the effectiveness of the integration scheme.