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

Victor Boskovitz; Hugo Guterman

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

Victor Boskovitz
, Hugo Guterman

Department of Electrical & Computer Engineering

Research output: Contribution to conference › Paper › peer-review

2 Scopus citations

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.

Original language	English
Pages	1063-1068
Number of pages	6
State	Published - 1 Jan 1997
Event	Proceedings of the 1997 6th IEEE International Conference on Fussy Systems, FUZZ-IEEE'97. Part 1 (of 3) - Barcelona, Spain Duration: 1 Jul 1997 → 5 Jul 1997

Conference

Conference	Proceedings of the 1997 6th IEEE International Conference on Fussy Systems, FUZZ-IEEE'97. Part 1 (of 3)
City	Barcelona, Spain
Period	1/07/97 → 5/07/97

ASJC Scopus subject areas

Software
Theoretical Computer Science
Artificial Intelligence
Applied Mathematics

Cite this

@conference{f7c4bc1e502d428088d11df1643e42cc,

title = "Edge detection and image segmentation: Two sides of the same coin",

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.",

author = "Victor Boskovitz and Hugo Guterman",

year = "1997",

month = jan,

day = "1",

language = "English",

pages = "1063--1068",

note = "Proceedings of the 1997 6th IEEE International Conference on Fussy Systems, FUZZ-IEEE'97. Part 1 (of 3) ; Conference date: 01-07-1997 Through 05-07-1997",

}

TY - CONF

T1 - Edge detection and image segmentation

T2 - Proceedings of the 1997 6th IEEE International Conference on Fussy Systems, FUZZ-IEEE'97. Part 1 (of 3)

AU - Boskovitz, Victor

AU - Guterman, Hugo

PY - 1997/1/1

Y1 - 1997/1/1

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/0030689421

M3 - Paper

AN - SCOPUS:0030689421

SP - 1063

EP - 1068

Y2 - 1 July 1997 through 5 July 1997

ER -

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

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this