ERRORS-2: a 3D object recognition system using aspect graphs

A prototype 3D object recognition system is described that is composed of three major sections; an object representation module, a feature extraction and matching module, and a recognition control strategy module. The object representation module uses an algorithm which constructs perspective projection aspect graphs of convex polyhedra. The feature extraction and matching module uses Fourier descriptors to characterize the complete 2D projection of an object. The recognition control strategy module uses the aspect graph object representation to control the application of a constrained optimization algorithm. The system is implemented in C on a Sun workstation, and some simple recognition experiments are reported that demonstrate the validity of the overall concept.<>