A Shape Retrieval Technique Using Isothetic Cover of Digital Objects

Abstract

This work presents a novel approach to classify digital objects based on outer isothetic cover (OIC). The descriptor vectors of the isothetic cover are used as the shape descriptors of a particular digital object. Two objects may be of similar kind of shape if their shape descriptors are analogous. To find a match between two descriptors, common substrings are found out and based on their length of the common substring a decision is made. Experimental results show encouraging results.