Edge detection and image segmentation: two sides of the same coin

Author

Boskovitz, Victor ; Guterman, Hugo

Author_Institution

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

Volume

2

fYear

1997

fDate

1-5 Jul 1997

Firstpage

1063

Abstract

An auto-adaptive neuro-fuzzy segmentation and edge detection architecture is presented. The system consists of a multilayer perceptron (MLP) network that performs image segmentation by 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 segmentation system as well as a criterion for determining potential edge pixels

Keywords

edge detection; entropy; fuzzy neural nets; fuzzy set theory; image segmentation; multilayer perceptrons; unsupervised learning; edge detection; fuzzy clustering; fuzzy entropy; fuzzy neural nets; fuzzy set theory; image segmentation; multilayer perceptron; neuro-fuzzy segmentation; unsupervised learning; Adaptive systems; Entropy; Fuzzy neural networks; Fuzzy sets; Fuzzy systems; Image edge detection; Image processing; Image segmentation; Multilayer perceptrons; Neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Systems, 1997., Proceedings of the Sixth IEEE International Conference on

Conference_Location

Barcelona

Print_ISBN

0-7803-3796-4

Type

conf

DOI

10.1109/FUZZY.1997.622857

Filename

622857