Abstract
The area of artificial neural networks has recently seen an explosion of theoretical and practical results. In this paper, we present an artificial neural network that is algebraically distinct from the classical artificial neural networks, and several applications which are different from the typical ones. In fact, this new class of networks, calledmorphology neural networks, is a special case of a general theory of artificial neural nets, which includes the classical neural nets. The main difference between a classical neural net and a morphology neural net lies in the way each node algebraically combines the numerical information. Each node in a classical neural net combines information by multiplying output values and corresponding weights and summing, while in a morphology neural net, the combining operation consists of adding values and corresponding weights, and taking the maximum value. We lay a theoretical foundation for morphology neural nets, describe their roots, and give several applications in image processing. In addition, theoretical results on the convergence issues for two networks are presented.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
G. Birkhoff and J. Lipson, Heterogeneous algebras,J. Combinatorial Theory, vol. 8, pp. 115–133, 1970.
R. Cuninghame-Green,Minimax Algebra: Lecture Notes in Economics and Mathematical Systems 166, New York: Springer-Verlag, 1979.
J. Davidson,Lattices Structures in the Image Algebra and Applications to Image Processing, Ph.D. thesis, Department of Mathematics, University of Florida, Gainesville, FL, August 1989.
J. Davidson and K. Sun, Template learning in morphological neural nets,SPIE — Proc. Soc. Photo-Optical Instr. Eng., vol. 1568, pp. 176–187, July 1991.
J. Davidson and K. Sun, Opening template learning in morphological neural nets, Heuristics,The Journal of Knowledge Engineering, vol. 5 No. 2, pp. 28–36, Summer 1992.
H. Hadwiger, Minkowskische addition und Subtraktion beliebiger punktmengen und die theoreme von Erhard Schmidt,Mathematische Zeitschrift, vol. 53, pp. 210–218, 1950.
R. P. Lippmann, An introduction to computing with neural nets,IEEE Magazine on Acoust. Speech Signal Proc, vol. ASSP-4, pp. 4–22, 1987.
H. Minkowski, Volumen und Oberfläche,Mathematische Annalen, vol. 57, pp. 447–495, 1903.
G. Ritter and J. Davidson, Recursion and feedback in image algebra,SPIE 19th AIPR Wkshp Image Understanding in the 90's, vol. 1406, pp. 74–86, October 1990.
G. Ritter, D. Li, and J. Wilson, Image algebra and its relationship to neural networks,Proc. 1989 SPIE Tech. Symp. Optics, Elec.-Opt. Sensors, March 1989.
G. Ritter, M. Shrader-Frechette, and J. Wilson, Image algebra: A rigorous and translucent way of expressing all image processing operations,Proc. 1987 SPIE Tech. Symp. Optics, Elec.-Opt. Sensors, pp. 116–121, May 1987.
G. Ritter and J. Wilson, Image algebra: A unified approach to image processing,Proc. SPIE Med. Imag. Conf.; vol. 767, pp. 338–345, February 1987.
G. Ritter, J. Wilson, and J. Davidson, Image algebra: An overview,Comp. Vis., Graphics, Image Proc., vol. 49, pp. 297–331, March 1990.
J. Serra,Image Analysis and Mathematical Morphology, Academic Press, London, 1982.
S. Sternberg, Grayscale morphology,Comp. Vis., Graph, Image Proc., vol. 35, pp. 333–355, 1986.
S. Wilson, Morphological networks,Proc. 1989 SPIE Vis. Comm. Image Proc., IV, November 1989.
Author information
Authors and Affiliations
Additional information
This research was supported in part by National Science Foundation, Contract No. ECS-9010403.
Rights and permissions
About this article
Cite this article
Davidson, J.L., Hummer, F. Morphology neural networks: An introduction with applications. Circuits Systems and Signal Process 12, 177–210 (1993). https://doi.org/10.1007/BF01189873
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF01189873