Abstract
The “life” of most neural vision systems splits into a one-time training phase and an application phase during which knowledge is no longer acquired. This is both technically inflexible and cognitively unsatisfying. Here we propose an appearance based vision system for object recognition which can be adapted online, both to acquire visual knowledge about new objects and to correct erroneous classification. The system works in an office scenario, acquisition of object knowledge is triggered by hand gestures. The neural classifier offers two ways of training: Firstly, the new samples can be added immediately to the classifier to obtain a running system at once, though at the cost of reduced classification performance. Secondly, a parallel processing branch adapts the classification system thoroughly to the enlarged image domain and loads the new classifier to the running system when ready.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Heidemann, G., Rae, R., Bekel, H., Bax, I., Ritter, H.: Integrating context-free and context-dependent attentional mechanisms for gestural object reference. In: Proc. Int’l Conf. Cognitive Vision Systems, Graz, Austria, pp. 22–33 (2003)
Heidemann, G., Ritter, H.: Efficient Vector Quantization Using the WTA-rule with Activity Equalization. Neural Processing Letters 13(1), 17–30 (2001)
Kahn, R.E., Swain, M.J., Prokopowicz, P.N., Firby, R.J.: Gesture recognition using the perseus architecture. Technical Report TR-96-04, 19 (1996)
Kalinke, T., von Seelen, W.: Entropie als Maß des lokalen Informationsgehalts in Bildern zur Realisierung einer Aufmerksamkeitssteuerung. In: Jähne, B., Geißler, P., Haußecker, H., Hering, F. (eds.) Mustererkennung 1996, pp. 627–634. Springer, Heidelberg (1996)
Kohonen, T.: Self-Organizing Maps. Springer, Heidelberg (1995)
Leonardis, A., Bischof, H., Maver, J.: Multiple eigenspaces. Pattern Recognition 35(11), 2613–2627 (2002)
Andersen, H.J., Stoerring, M., Granum, E.: Physics-based modelling of human Skin colour under mixed illuminants. Robotics and Autonomous Systems 35(3-4), 131–142 (2001)
Mel, B.W.: SEEMORE: Combining color, shape, and texture histogramming in a neurally-inspired approach to visual object recognition. Neural Computation 9, 777–804 (1997)
Murase, H., Nayar, S.K.: Visual Learning and Recognition of 3-D Objects from Appearance. Int’l J. of Computer Vision 14, 5–24 (1995)
Ossola, J.C., Bremond, F., Thonnat, M.: A communication level in a distributed architecture for object recognition. In: 8th International Conference on Systems Research Informatics and Cybernetics (August 1996)
Ritter, H.J., Martinetz, T.M., Schulten, K.J.: Neuronale Netze. Addison-Wesley, München (1992)
Sanger, T.D.: Optimal Unsupervised Learning in a Single-Layer Linear Feedforward Neural Network. Neural Networks 2, 459–473 (1989)
Theis, C., Iossifidis, I., Steinhage, A.: Image Processing Methods for Interactive Robot Control. In: Proc. IEEE Roman International Workshop on Robot-Human Interactive Communication, Bordeaux and Paris, France (2001)
Tipping, M.E., Bishop, C.M.: Mixtures of probabilistic principal component analyzers. Neural Computation 11(2), 443–482 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bekel, H., Bax, I., Heidemann, G., Ritter, H. (2004). Adaptive Computer Vision: Online Learning for Object Recognition. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds) Pattern Recognition. DAGM 2004. Lecture Notes in Computer Science, vol 3175. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28649-3_55
Download citation
DOI: https://doi.org/10.1007/978-3-540-28649-3_55
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22945-2
Online ISBN: 978-3-540-28649-3
eBook Packages: Springer Book Archive