A study on FDNN applying the hybrid fuzzy membership function and the genetic algorithm

Author

Byun, Oh Sung ; Cho, Soo Hyung ; Seo, Chun Hwa ; Moon, Sung Ryong

Author_Institution

Dept. of Electron. Eng., Wonkwang Univ., Chonbuk, South Korea

Volume

2

fYear

1999

fDate

12/1/1999 12:00:00 AM

Firstpage

1307

Abstract

We apply the hybrid method fuzzy membership function in order to obtain the result that is likely to the original image, and the generic algorithm in order to find the optimal image to the FDNN. If some of the data is input, it is selected as a local winner to find a basis image of the largest similarity. We realize the hierarchical FDNN obtaining the last output value selection to a global winner among a local winner. In this paper the noise is removed from an image using FDNN to which is applied both the hybrid fuzzy membership function and the genetic algorithm, also the superiority of the proposed algorithm to the conventional FDNN is found. As a result of the comparison by the MSE for each image, we show the superiority of the FDNN to which is applied both the hybrid fuzzy membership function and the genetic algorithm

Keywords

fuzzy neural nets; genetic algorithms; image processing; mean square error methods; noise; FDNN; MSE; genetic algorithm; global winner; hierarchical FDNN; hybrid fuzzy membership function; local winner; noise; optimal image; original image; Artificial neural networks; Decoding; Equations; Fuzzy neural networks; Fuzzy sets; Genetic algorithms; Genetic engineering; Image processing; Moon; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

TENCON 99. Proceedings of the IEEE Region 10 Conference

Print_ISBN

0-7803-5739-6

Type

conf

DOI

10.1109/TENCON.1999.818669

Filename

818669