Interactive online learning
- 76 Downloads
This paper describes a system for visual object recognition based on mobile augmented reality gear. The user can train the system to the recognition of objects online using advanced methods of interaction with mobile systems: Hand gestures and speech input control “virtual menus,” which are displayed as overlays within the camera image. Here we focus on the underlying neural recognition system, which implements the key requirement of an online trainable system—fast adaptation to novel object data. The neural three-stage architecture can be adapted in two modes: In a fast training mode (FT), only the last stage is adapted, whereas complete training (CT) rebuilds the system from scratch. Using FT, online acquired views can be added at once to the classifier, the system being operational after a delay of less than a second, though still with reduced classification performance. In parallel, a new classifier is trained (CT) and loaded to the system when ready.
Unable to display preview. Download preview PDF.
- 1.H. Bekel, I. Bax, G. Heidemann, and H. Ritter, “Adaptive Computer Vision: Online Learning for Object Recognition,” in Proc. DAGM 2004, Ed. by C. E. Rasmussen (Springer, Tubingen, Germany, 2004), pp. 447–454.Google Scholar
- 2.C. Bregler and S. M. Omohundro, “Surface Learning with Applications to Lipreading,” in Advances in Neural Information Processing Systems 1993, Eds. by J. Cowan, G. Tesauro, and J. Alspector (Morgan-Kaufmann Publishers, 1994), Vol. 6, pp. 43–50.Google Scholar
- 3.C. Harris and M. Stephens, “A Combined Corner and Edge Detector,” in Proceedings of 4th Alvey Vision Conf., 1988, pp. 147–151.Google Scholar
- 4.T. Hastie, P. Simard, and E. Sackinger, “Learning Prototype Models For Tangent Distance,” in Advances in Neural Information Processing Systems 1994, Eds. by G. Tesauro, D. Touretzky, and T. Leen (MIT Press, 1995), Vol. 7, pp. 999–1006.Google Scholar
- 5.G. Heidernann, D. Lücke, and H. Ritter, “A System for Various Visual Classification Tasks Based on Neural Networks,” in Proc. 15th Int’l Conf. on Pattern Recognition ICPR, 2000, Barselona, Ed. by A. Sanfeliu (IEEE-CS, 2000), Vol. 1, pp. 9–12.Google Scholar
- 7.G. Heidernann and H. Ritter, “Making Robots Learn to See,” in Perspectives on Adaptivity and Learning, Ed. by R. Kühn (Springer, 2003), pp. 285–309.Google Scholar
- 9.I. Jolliffe, Principal Component Analysis (Springer Verlag, New York, 1986).Google Scholar
- 10.T. Kalinke and W. von Seelen, “Entropie als Mafi des lokalen Informationsgehalts in Bildern zur Realisierung einer Aufmerksamkeitssteuerung,” in Mustererkennung, 1996, Eds. by B. Jahne, P. Geifiler, H. Haufiecker, and F. Hering (Springer Verlag, Heidelberg, 1996), pp. 627–634.Google Scholar
- 11.N. Kambhatla and T. K. Leen, “Fast Non-Linear Dimension Reduction,” in Advances in Neural Information Processing Systems, 1993, Eds. by J. Cowan, G. Tesauro, and J. Alspector (Morgan Kaufmann Publishers, 1994), Vol. 6, pp. 152–159.Google Scholar
- 13.T. Kohonen, Self-Organizing Maps (Springer Verlag, 1995).Google Scholar
- 16.R. Rae, M. Fislage, and H. Ritter, “Visuelle Aufmerksamkeitssteuerung zur Unterstiitzung gestikbasierter Mensch-Maschine Interaktion,” KI—Künstliche Intelligenz, Themenheft Aktive Sehsysteme (1), 18–24 (1999).Google Scholar