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 real-time. 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.

[1]  Heiko Wersing,et al.  Online figure-ground segmentation with adaptive metrics in generalized LVQ , 2009, Neurocomputing.

[2]  Heiko Wersing,et al.  Biologically motivated visual behaviors for humanoids: Learning to interact and learning in interaction , 2006, 2006 6th IEEE-RAS International Conference on Humanoid Robots.

[3]  Keiji Tanaka,et al.  Inferotemporal cortex and object vision. , 1996, Annual review of neuroscience.

[4]  Jochen Triesch,et al.  Semi-autonomous Learning of Objects , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[5]  Horst-Michael Groß,et al.  Biological neural architecture for chromatic adaptation resulting in constant color sensations , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[6]  Mark Dunn,et al.  Visually Guided Whole Body Interaction , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[7]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[8]  Michael J. Swain,et al.  Color indexing , 1991, International Journal of Computer Vision.

[9]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[10]  Heiko Wersing,et al.  A Comparison of Features in Parts-Based Object Recognition Hierarchies , 2007, ICANN.

[11]  Thomas Serre,et al.  A feedforward architecture accounts for rapid categorization , 2007, Proceedings of the National Academy of Sciences.

[12]  Heiko Wersing,et al.  Learning Optimized Features for Hierarchical Models of Invariant Object Recognition , 2003, Neural Computation.

[13]  Y. Yamane,et al.  Complex objects are represented in macaque inferotemporal cortex by the combination of feature columns , 2001, Nature Neuroscience.

[14]  Hiroshi Murase,et al.  Real-time 100 object recognition system , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[15]  Paolo Pirjanian,et al.  SIFT-ing through features with ViPR , 2006, IEEE Robotics & Automation Magazine.