Neuro-fuzzy system for adaptive multilevel image segmentation

Author

Boskovitz, Victor ; Guterman, Hugo

Author_Institution

Dept. of Electr. & Comput. Eng., Ben-Gurion Univ. of the Negev, Beer-Sheva, Israel

fYear

1996

Firstpage

208

Lastpage

211

Abstract

An auto-adaptive neuro-fuzzy segmentation architecture is presented. The system consists of a multilayer perceptron (MLP) network that performs adaptive thresholding of the input image using labels automatically preselected by a fuzzy clustering technique. The proposed architecture is feedforward, but unlike the conventional MLP the learning is unsupervised. The output status of the network is described as a fuzzy set. Fuzzy entropy is used as a measure of the error of the system

Keywords

adaptive signal processing; entropy; error analysis; feedforward neural nets; fuzzy neural nets; fuzzy set theory; image segmentation; unsupervised learning; adaptive multilevel image segmentation; adaptive thresholding; auto-adaptive neuro-fuzzy segmentation architecture; error; feedforward; fuzzy clustering; fuzzy entropy; fuzzy set; input image; multilayer perceptron; output status; unsupervised learning; Adaptive systems; Entropy; Fuzzy neural networks; Fuzzy sets; Fuzzy systems; Image segmentation; Multi-layer neural network; Multilayer perceptrons; Neural networks; Pixel;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Electronics Engineers in Israel, 1996., Nineteenth Convention of

Conference_Location

Jerusalem

Print_ISBN

0-7803-3330-6

Type

conf

DOI

10.1109/EEIS.1996.566931

Filename

566931