Abstract
A parallel-sequential unsupervised learning method for image smoothing is presented which can be implemented with a Multi Layer Neural Network. In contrast to older work of the author which has used 4-connectivity of processing elements (neurons) leading to a very big number of recursions now each neuron of network layer t+1 is connected with (2M+1)✻(2M+1) neurons of layer t guaranteeing a significant reduction of network layers with the same good smoothing results.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
H. Jahn; “Image preprocessing and segmentation with a cellular neural network”; SPIE Proceedings, Vol. 3304, pp. 120–131, 1998
H. Jahn; “Dot pattern clustering using a cellular neural network”; SPIE Proceedings 3346, pp. 298–307, 1998
H. Jahn;A Neural Network for Image Smoothing and Segmentation; Lecture Notes in Computer Science 1451, pp. 329–338, 1998
H. Jahn, W. Halle; “Texture segmentation with a neural network”; SPIE Proceedings, Vol. 3646, “Nonlinear Image Processing X”, pp. 92–99, 1999
L.O. Chua and L. Yang; “Cellular neural networks: Theory”; IEEE Trans. on Circuits and Systems, Vol. 35, pp. 1257–1272, 1988
B. Müller, J. Reinhardt; Neural Networks; Springer, Berlin, 1991
B. Kosko; Neural Networks and Fuzzy Systems; Prentice-Hall Inc., Englewood Cliffs,New Jersey, 1992
D. Hubel; Eye, Brain, and Vision; Scientific American Library New York, 1995
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jahn, H. (1999). Unsupervised Learning of Local Mean Gray Values for Image Pre-processing. In: Perner, P., Petrou, M. (eds) Machine Learning and Data Mining in Pattern Recognition. MLDM 1999. Lecture Notes in Computer Science(), vol 1715. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48097-8_6
Download citation
DOI: https://doi.org/10.1007/3-540-48097-8_6
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66599-1
Online ISBN: 978-3-540-48097-6
eBook Packages: Springer Book Archive