3-DIMENSIONAL PLANAR-FACED OBJECT CLASSIFICATION WITH KOHONEN MAPS

Three-dimensional (3-D) object recognition from digitized intensity im ages is a central problem in providing computers with human-like perce ption capabilities. We present a neural system that performs learning and classification of 3-D planar-faced objects. These objects are desc ribed through a set of line descriptors that provide a type of invaria nce to scaling and allow a reduction in the number of views needed to train the network. Kohonen networks have been used to allow a human-li ke classification of the object views. Each network is capable of disc riminating between several distinct objects and can be combined in a m odular way with similar networks to build large multiobject classifier s.