Object Recognition with Multiple Feature Types

Abstract

One of the brain's recipes for robustly perceiving the world is to integrate multiple feature types such as shape, color, texture and motion. We have investigated how far also neural-network based object recognition can profit from the combination of several feature types. For this purpose we have extended Elastic Graph Matching such that several feature types may be combined in the object models. We applied the system in two difficult application domains, the interpretation of cluttered scenes and the recognition of hand postures against complex backgrounds. Our results demonstrate that the usage of additional feature types significantly improves performance.