Sill Image Object Categorization Using 2D Objects Models

This paper proposes a novel recognition scheme for semantic labeling of 2D objects present in still images. The principle consists of matching unknown 2D objects with categorized 3D models in order to associate the semantics of the 3D object to the image. We tested our new recognition framework by using the MPEG-7 and Princeton 3D model databases in order to label unknown images randomly selected from the web. Experiments show that such a system can achieve recognition rate up to 70.4%.