An approach to three-dimensional object recognition using a hybrid Hopfield network

Abstract

A hybrid Hopfield network previously used to solve two-dimensional occluded object recognition problems is adapted to the three-dimensional problem. It is assumed that feature extraction has yielded a set of vertices for the model and a set of vertices for the input object. From these vertices local and relational features are obtained for use in a hybrid Hopfield network graph-matching algorithm used to realize three-dimensional single-input object recognition.