Abstract
Automatic classification of textured images is crucial for both surface inspection problems in quality control systems and medical imaging applications. It requires sophisticated textural image features in order to distinguish between different defects or image classes. In the following paper, we report on experiments in which we automatically select adequate subsets of textural features from a large set of potential candidates. For the underlying problem of tumor cell identification, conventional selection techniques as well as genetic algorithms have been investigated on. The Gallops PVM package has been running on up to 48 machines in order to find the best feature subset.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Blanz, W. E.: Design and Implementation of a Low-Level Image Segmentation Architecture — LISA. In: Machine Vision Applications (1993), Nr. 6, S. 181–190
Chen, Y.; Nixon, M.; Thomas, D.: Statistical Geometrical Features for Texture Classification. In: Pattern Recognition 28 (1995), Nr. 4, S. 537–552
Galloway, M. M.: Texture analysis using gray level run lengths. In: Computer Graphics and Image Processing 4 (1975), S. 172–179
Goldberg, David E.: Genetic algorithms in search, optimization and machine learning. Reading, MA: Addison-Wesley, 1989
Goodman, Erik D.: An Introduction to Galopps/Michigan State University. 1995 (95-06-01).-Tech. Report
Haralick, M.; Shanmugam, K.; Dinstein, I.: Textural Features for Image Classification. In: IEEE Transactions on Systems, Man and Cybernetics SMC-3 (1973), Nr. 6, S. 610–621
Kittler, J. Feature Selection and Extraction. 1986
Kreyszig, Erwin: Statistische Methoden und ihre Anwendungen. Goettingen: Vandenhoeck und Ruprecht, 1975
Laine, A.; Fun, J.: Texture Classification by Wavelet Packet Signatures. In: IEEE Ttransactions on Pattern Analysis and Machine Intelligence 15 (1993), Nr. 11, S. 1186–1191
Niemann, H.: Klassifikation von Mustern. Berlin/Heidelberg: Springer, 1983
Ro, Th.; Handels, H.; Busche, H.; Kreusch, J.; Wolff, H. H.; Pppl, S. J.: Automatische Klassifikation hochaufgelster Oberflchenprofile von Hauttumoren mit neuronalen Netzen. In: Sagerer, G. (Hrsg.); Posch, S. (Hrsg.); Kummert, F. (Hrsg.): Mustererkennung 1995. Bielefeld: Spinger Verlag, 1995
Unser, Michael: Sum and Difference Histograms for Texture Analysis. In: IEEE Transactions on Pattern Analysis ans Machine Intelligence 8 (1986), S. 118–125
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wagner, T., Kueblbeck, C., Schittko, C. (1996). Genetic selection and generation of textural features with PVM. In: Bode, A., Dongarra, J., Ludwig, T., Sunderam, V. (eds) Parallel Virtual Machine — EuroPVM '96. EuroPVM 1996. Lecture Notes in Computer Science, vol 1156. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3540617795_39
Download citation
DOI: https://doi.org/10.1007/3540617795_39
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61779-2
Online ISBN: 978-3-540-70741-7
eBook Packages: Springer Book Archive