Novel Indexing Method of Relations Between Salient Objects

Abstract

During the last decade, a lot of work has been done in information technology in order to integrate image retrieval in the standard data processing environments (Rui, Huang & Chang, 1999; William & Grosky, 1997; Yoshitaka & Ichikawa, 1999).Relations between image objects are very frequently used to index the image-document (Peuquet, 1986). In medicine, for instance, the spatial data in surgical or radiation therapy of brain tumors are decisive because the location of a tumor has profound implications on a therapeutic decision (Chbeir, Amghar, & Flory, 2001). Hence, it is crucial to provide a precise and powerful system to express spatial relations. In the literature, three major types of spatial relations are proposed: metric (Peuquet, 1986), directional (El-kwae & Kabuka, 1999) and topological relations (Egenhofer, 1997; Egenhofer, Frank & Jackson, 1989).