mk:fuzz-ieee99

Summary

Deriving Rules from Evolutionary Adapted Texture Filters by Neural Networks. Mario Köppen, Achim Zentner and Bertram Nickolay. In 1999 IEEE International Fuzzy Systems Conference Proceeding, pages 785-790, Seoul, Korea, 1999.

Abstract

The work presented in this paper is motivated by the recently proposed 2DLookup framework for the evolutionary and data-driven adaptation of texture filters. A class of images, the 2D-Lookup matrices, appears to play an important role for the performance of the adapted texture filters. Two approaches for approximating these 2D-Lookup matrices by neural networks are presented, one based on the Multilayer Backpropagation Neural Network (MBPN), and one based on the Unit RBF network. For the MBPN approach approximating 2DLookup matrices very smooth but rather rough, the Unit RBF approach approximates these images much more better, especially at specific details at a lower scale. Also, the Unit RBF approach is faster and more simple to handle, and its outcome serves a texture model based on fuzzy rules.

Bibtex entry

@INPROCEEDINGS { mk:fuzz-ieee99,
    ABSTRACT = { The work presented in this paper is motivated by the recently proposed 2DLookup framework for the evolutionary and data-driven adaptation of texture filters. A class of images, the 2D-Lookup matrices, appears to play an important role for the performance of the adapted texture filters. Two approaches for approximating these 2D-Lookup matrices by neural networks are presented, one based on the Multilayer Backpropagation Neural Network (MBPN), and one based on the Unit RBF network. For the MBPN approach approximating 2DLookup matrices very smooth but rather rough, the Unit RBF approach approximates these images much more better, especially at specific details at a lower scale. Also, the Unit RBF approach is faster and more simple to handle, and its outcome serves a texture model based on fuzzy rules. },
    ADDRESS = { Seoul, Korea },
    AUTHOR = { Mario Köppen and Achim Zentner and Bertram Nickolay },
    BOOKTITLE = { 1999 IEEE International Fuzzy Systems Conference Proceeding },
    MODIFIED = { 2008-02-28 16:40:34 +0900 },
    HASABSTRACT = { Yes },
    PAGES = { 785--790 },
    PDF = { fuzzieee99.pdf },
    TITLE = { Deriving Rules from Evolutionary Adapted Texture Filters by Neural Networks },
    VOLUME = { 2 },
    YEAR = { 1999 },
}

On small computer displays, you can hide this right bar by using the 'Hide' button above.

News

Next conferences COMPSAC 2014 (Vasteras, Sweden, July 2014), INCoS-2014 (Salerno, Italy, September 2014).

New edited book "Soft Computing in Industrial Applications", V. Snasel, P. Kroemer, M. Koeppen, G. Schaefer, Springer AISC 223, July 2013.