Large-Scale Real-Time Object Identification Based on Analytic Features

Inspired by biological findings, we present a system that is able to robustly identify a large number of pre-trained objects in realtime. In contrast to related work, we do not restrict the objects' pose to characteristic views but rotate them freely in hand in front of a cluttered background. We describe the essential system's ingredients, like prototype-based figure-ground segmentation, extraction of brain-like analytic features, and a simple classifier on top. Finally we analyze the performance of the system using databases of varying difficulty.

• Type: Conference
• Year: 2009
• Where: ICANN
• Authors: Stephan Hasler, Heiko Wersing, Stephan Kirstein, Edgar Körner
• Keywords: Brain-like Analytic Features, Essential System Ingredients, ICANN 2009, Neural Networks, Prototype-based Figure-ground Segmentation