A GRAPH BASED OBJECT DESCRIPTION AND RECOGNITION METHODOLOGY

Abstract

This paper presents a methodology for recognizing 3D objects using synthesis of 2D views. In particular, the methodology uses wavelets for rearranging the shape of the perceived 2D view of an object for attaining a desirable size, local-global (LG) graphs for representing the shape, color and location of each image object's region obtained by an image segmentation method and the synthesis of these regions that compose that particular object. The synthesis of the regions is obtained by composing their local graph representations under certain neighborhood criteria. The LG graph representation of the extracted object is compared against a set of LG based object-models stored in a Database (DB). The methodology is accurate for recognizing objects existed in the DB and it has the capability of "learning" the LG patterns of new objects by associating them with attributes from existing LG patterns in the DB. Note that for each object-model stored in the database there are only six views, since all the intermediate views can be generated by appropriately synthesizing these six views. Illustrative examples are also provided.