Simultaneous Visual Object Recognition and Position Estimation Using SIFT

In the last decade, pattern recognition tasks have flourished and become one of the most popular tasks in computer vision. A wealth of research focused on building vision systems capable of recognizing objects in cluttered environments. Moreover industries address all their efforts to developing new frameworks for assisting people in everyday life. The need of robots working closely to human beings in domestic workplaces, makes a necessity the usage of intelligent sensorial systems that are able to find patterns and provide their location in the working space. In this paper a novel method able to recognize objects in a scene and provide their spatial information is presented. Furthermore, we investigate how SIFT could expand for the purposes of location assignment of an object in a scene.