Abstract
For a long time pixel based segmentation methods were restricted to grayscale images due to the enormous computational costs when dealing with color. With the availability of more powerful computers it is nowadays possible to perform pixel based operations on real camera images even in the full color space. New adaptive classification tools like neural networks make it possible to develop special-purpose object detectors that can segment arbitrary objects in real images with a complex distribution in the feature space after training with one or several previously labelled image(s). The proposed adaptive segmentation method uses local color information to estimate the membership probability in the object resp. background class. The method is applied to the recognition and localization of human hands in color camera images of complex laboratory scenes. The paper focuses on the influence of the chosen color representation and a detailed comparison of the neural approach to standard statistical methods, a threshold filter, and a classifier based on normal distributions.
This is a preview of subscription content, log in via an institution to check access.
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
Colorimetry. Publication CIE (Commission Internationale de l’Eclairage) No. 15.2, Vienna, 1986.
A. Drees, F. Kümmert, E. Littmann, S. Posch, H. Ritter, and G. Sagerer. A hybrid system to detect hand orientation in stereo images. In E.S. Gelsema and L.N. Kanal, editors, Pattern Recognition in Practice IV: Multiple Paradigms, Comparative Studies and Hybrid Systems, pages 551–562. Elsevier Science Publishers B.V., North Holland, 1994.
F. Kümmert, E. Littmann, A. Meyering, S. Posch, H. Ritter, and G. Sagerer. A hybrid approach to signal interpretation using neural and semantic networks. In S. J. Pöppl and H. Handels, editors, Mustererkennung 1993, pages 245–252. Springer-Verlag, Berlin Heidelberg New York, 1993.
F. Kümmert, E. Littmann, A. Meyering, S. Posch, H. Ritter, and G. Sagerer. Recognition of 3d-hand orientation from monocular color images by neural semantic networks. Pattern Recognition and Image Analysis, 3(3):311–316,1993.
F. Kümmert, H. Niemann, R. Prechtel, and G. Sagerer. Control and Explanation in a Signal Understanding Environment. Signal Processing, special issue on ’Intelligent Systems for Signal and Image Understanding’, 32:111–145,1993.
E. Littmann. Strukturierung Neuronaler Netze zwischen Biologie und Anwendung. DISKI. Infix Veriag, St. Augustin, FR Germany, 1995.
E. Littmann and H. Ritter. Neuronale und statistische Verfahren zur adaptiven Farbsegmentierung — ein Leistungsvergleich. Technical Report TR 95/3, SFB 360, Bielefeld University, Bielefeld, FR Germany, 1995.
H. Niemann. Pattern Analysis and Understanding. Springer-Verlag Series in Information Sciences 4. Springer-Verlag, Berlin Heidelberg New York, 2nd edition, 1990.
J. Platt. A resource-allocating network for function interpolation. Neural Computation, 3:213–221,1991.
T. Poggio and F. Girosi. Regularization algorithms for learning that are equivalent to multilayer networks. Science, 247, 1990.
H. Ritter. Learning with the self-organizing map. In T. Kohonen, K. Mäkisara, O. Simula, and J. Kangas, editors. Artificial Neural Networks 1, pages 357–364. Elsevier Science Publishers B.V., North Holland, 1991.
H. Ritter, T. Martinetz, and K. Schulten. Neural Computation and Self-Organizing Maps: An Introduction. Addison-Wesley, New York, 1992. (English and German).
G. Sagerer. Automatisches Verstehen gesprochener Sprache, volume 74 of Reihe Informatik. Bibliographisches Institut, Mannheim, 1990.
G. Sagerer. Neuronal, Statistisch, Wissensbasiert: Ein Beitrag zur Paradigmendiskussion für die Mustererkennung. In S.J. Pöppl and H. Handels, editors,Mustererkennung 1993, pages 158–177. Springer-Verlag, Berlin Heidelberg New York, 1993.
J. Schürmann and U. Kreßel. Mustererkennung mit statistischen Methoden. Vorlesungsskript SS 1992. Daimler-Benz AG, Forschungszentrum Ulm, Institut für Informationstechnik, 1992.
R. Schuster. Adaptive modeling in color image sequences. In W.G. Kropatsch and H. Bischof, editors,Mustererkennung 1994, pages 161–169. Technische Universität, Wien, 1994.
R. Schuster and S. Ahmad. Modellbasierte Beschreibung von Farbhistogrammen und Segmentation von Farbbildern. In S. J. Pöppl and H. Handels, editors,Mustererkennung 1993, pages 305–311. Springer-Veriag, Berlin Heidelberg New York, 1993.
G. Wyszecki and W.S. Stiles. Color Science — Concepts and Methods, Quantitative Data and Formulae. Wiley, New York, 2nd edition, 1982.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Littmann, E., Ritter, H. (1995). Neural and Statistical Methods for Adaptive Color Segmentation — A Comparison. In: Sagerer, G., Posch, S., Kummert, F. (eds) Mustererkennung 1995. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-79980-8_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-79980-8_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60293-4
Online ISBN: 978-3-642-79980-8
eBook Packages: Springer Book Archive