Title :
Design of multilayer discrete time cellular neural networks for image processing tasks based on genetic algorithms
Author :
Lopez, P. ; Vilarino, D.L. ; Cabello, D.
Author_Institution :
Dept. of Electron. & Comput. Sci., Santiago de Compostela Univ., Spain
Abstract :
Genetic algorithms are applied to design multilayer discrete-time cellular neural networks for image processing tasks, To this end not only the templates of the different layers will be optimized, but also the network structure itself, that is, number of layers and iterations per layer. As a difference with traditional strategies, both the definition of the optimum network size and the template optimization are done simultaneously
Keywords :
cellular neural nets; feature extraction; genetic algorithms; image segmentation; iterative methods; multilayer perceptrons; genetic algorithms; image processing tasks; iterations; multilayer discrete time cellular neural networks; network structure; optimum network size; template optimization; templates; Algorithm design and analysis; Cellular neural networks; Computer architecture; Computer networks; Computer science; Electronic mail; Genetic algorithms; Image processing; Multi-layer neural network; Nonhomogeneous media;
Conference_Titel :
Circuits and Systems, 2000. Proceedings. ISCAS 2000 Geneva. The 2000 IEEE International Symposium on
Conference_Location :
Geneva
Print_ISBN :
0-7803-5482-6
DOI :
10.1109/ISCAS.2000.858706
