Abstract
In this paper, we present a novel problem: “Given local de- scriptors, how can we incorporate both local and global spatial infor- mation into the descriptors, and obtain compact and discriminative fea- tures?” To address this problem, we proposed a general framework to improve any local descriptors by embedding both local and global spatial information. In addition, we proposed a simple and powerful combina- tion method for different types of features. We evaluated the proposed method for the most standard scene and ob ject recognition dataset, and confirm the effectiveness of the proposed method from the viewpoint of speed and accuracy.