An introduction to morphological neural networks

• Published in: Proceedings of 13th International Conference on Pattern Recognition Vol. 4; pp. 709 - 717 vol.4
• Main Authors: Ritter, G.X., Sussner, P.
• Format: Conference Proceeding
• Language: English; Japanese
• Published: IEEE 1996
• Subjects: Algebra; Artificial neural networks; Biological system modeling; Computer networks; Ear; Electric potential; Lattices; Multi-layer neural network; Neural networks; Neurons
• ISBN: 9780818672828; 081867282X
• ISSN: 1051-4651
• DOI: 10.1109/ICPR.1996.547657

The theory of artificial neural networks has been successfully applied to a wide variety of pattern recognition problems. In this paper we introduce a novel class of neural networks, called morphological neural networks, in which the operations of multiplication and addition are replaced by addition and maximum (or minimum), respectively. By taking the maximum (or minimum) of sums instead of the sum of products, morphological network computation is nonlinear before thresholding. As a consequence, the properties of morphological neural networks are drastically different than those of traditional neural network models. In this paper we consider some of these differences and examine the computing capabilities of morphological neural networks. As particular examples of a morphological neural network we discuss morphological associative memories and morphological perceptrons.