An LG graph based monitoring scheme for representing incomplete objects

Abstract

One of the challenging problems in the field of Objects Recognition is the incomplete appearance of objects and the need to make a guess or a decision about the existence of such objects. There are several research efforts to this direction, mainly based on models from the estimation theory. This paper we present an alternative approach based on the use of a geometrically focused image processing method, the LG Algorithm, when simple objects are partially objects and the results from the application of such an algorithm.