Abstract
The pixel-wise classification of CCD colour images into previously learned colour classes at video-rate is a demanding vision task, both with regard to the complicated cluster shapes encountered in natural scenes and to the required computing power for real-time operation. We discuss the use of a perceptron Neural Network and propose an alternative simple and low-cost classifier based on approbriately trained look-up-tables. Two different learning rules for the supervised training of this LUT classifier are presented. This LUT classifier shows all the positive features of a 3-layer perceptron Neural Network, but performs 60.000 times faster then the Neural Network PC-simulation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Janke, P., Breuckmann, K.: Internal report and commercial documentation of the Opto-Tech “Fast Frame Processor ” VME-Bus vision processor (1989) OptoTech GmbH, Meersburg, FRG
Lippmann, R.: Introduction to Computing with Neural Nets. IEEE Trans. ASSP, April 1987
Rumelhart, D.E.: Parallel Distributed Processing: Exploration in the Microstructure of Cognition. Vol. I, Foundations, MIT Press 1986
Rumelhart, D.E.: Learning internal representations by error propagation. Neural Networks, Vol. 1. ed. by Rumelhart, 1986
Product information of the NeuralWorks simulation package. Neural Ware Inc. Pittsburgh USA
Strobach, P.: A Simplex Design of Linear Hyperplane Decision Networks. in: Pattern Recognition 1989. 11th DAGM Symposium, Hamburg October 1989. ed. Burkhardt. Springer-Verlag
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Massen, R., Gässler, J., Böttcher, P., Reichelt, W. (1990). Trainable Look-Up-Tables versus Neural Networks for Real-time Colour Classification. In: Großkopf, R.E. (eds) Mustererkennung 1990. Informatik-Fachberichte, vol 254. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-84305-1_46
Download citation
DOI: https://doi.org/10.1007/978-3-642-84305-1_46
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-53172-2
Online ISBN: 978-3-642-84305-1
eBook Packages: Springer Book Archive