DocumentCode :
344605
Title :
Deriving rules from evolutionary adapted texture filters by neural networks
Author :
Köppen, Mario ; Zentner, Achim ; Nickolay, Bertram
Author_Institution :
Dept. of Pattern Recognition, Fraunhofer-Inst. IPK, Berlin, Germany
Volume :
2
fYear :
1999
fDate :
22-25 Aug. 1999
Firstpage :
785
Abstract :
This work is motivated by the recently proposed 2D-lookup 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 the other based on the unit RBF network. While the MBPN approach gives only a rough approximation of the 2D-lookup matrices, the unit RBF approach approximates these images better, especially for 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.
Keywords :
backpropagation; filtering theory; function approximation; fuzzy logic; image texture; radial basis function networks; table lookup; 2D-lookup matrix; backpropagation; data-driven adaptation; function approximation; fuzzy rules; image processing; image texture; multilayer neural network; texture filters; unit RBF network; Algorithm design and analysis; Backpropagation; Electronic mail; Evolutionary computation; Filters; Gray-scale; Neural networks; Pattern recognition; Radial basis function networks; Shape;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Fuzzy Systems Conference Proceedings, 1999. FUZZ-IEEE '99. 1999 IEEE International
Conference_Location :
Seoul, South Korea
ISSN :
1098-7584
Print_ISBN :
0-7803-5406-0
Type :
conf
DOI :
10.1109/FUZZY.1999.793048
Filename :
793048
Link To Document :
بازگشت