Edge detection of the low contrast welded joint image corrupted by noise

Xuming Zhang; Yin Zhouping; Xiong Youlun

doi:10.1109/ICEMI.2007.4350820

Edge detection of the low contrast welded joint image corrupted by noise

Xuming Zhang, Yin Zhouping, Xiong Youlun

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

8 Citations (Scopus)

Abstract

To extract the edges from the low-contrast welded joint image corrupted by noise, the morphological filter is firstly proposed to remove the noise from the image. Then the improved fuzzy edge detection (FED) algorithm is adopted to realize the multi-level fuzzy enhancement of the filtered image and extract the edges from the enhanced image using multi-directional edge detection operator. Experimental results demonstrate that the improved FED algorithm can extract the continuous and thin edges and remove the false edges from the image, which leads to its better performance than the Sobel operator, Canny operator, traditional FED algorithm and fast FED algorithm.

Original language	English
Title of host publication	2007 8th International Conference on Electronic Measurement and Instruments, ICEMI
Pages	2876-2879
Number of pages	4
DOIs	https://doi.org/10.1109/ICEMI.2007.4350820
Publication status	Published - 1 Dec 2007
Externally published	Yes
Event	2007 8th International Conference on Electronic Measurement and Instruments, ICEMI - Xian, China Duration: 16 Aug 2007 → 18 Aug 2007

Conference

Conference	2007 8th International Conference on Electronic Measurement and Instruments, ICEMI
Country/Territory	China
City	Xian
Period	16/08/07 → 18/08/07

Keywords

Edge detection
Fuzzy enhancement
Morphological filter
Welded joint image

ASJC Scopus subject areas

Electrical and Electronic Engineering

More information

10.1109/ICEMI.2007.4350820

Cite this

@inproceedings{f7f0c5e368e54299825ad233f924859b,

title = "Edge detection of the low contrast welded joint image corrupted by noise",

abstract = "To extract the edges from the low-contrast welded joint image corrupted by noise, the morphological filter is firstly proposed to remove the noise from the image. Then the improved fuzzy edge detection (FED) algorithm is adopted to realize the multi-level fuzzy enhancement of the filtered image and extract the edges from the enhanced image using multi-directional edge detection operator. Experimental results demonstrate that the improved FED algorithm can extract the continuous and thin edges and remove the false edges from the image, which leads to its better performance than the Sobel operator, Canny operator, traditional FED algorithm and fast FED algorithm.",

keywords = "Edge detection, Fuzzy enhancement, Morphological filter, Welded joint image",

author = "Xuming Zhang and Yin Zhouping and Xiong Youlun",

year = "2007",

month = dec,

day = "1",

doi = "10.1109/ICEMI.2007.4350820",

language = "English",

isbn = "1424411351",

pages = "2876--2879",

booktitle = "2007 8th International Conference on Electronic Measurement and Instruments, ICEMI",

note = "2007 8th International Conference on Electronic Measurement and Instruments, ICEMI ; Conference date: 16-08-2007 Through 18-08-2007",

}

Zhang, X, Zhouping, Y & Youlun, X 2007, Edge detection of the low contrast welded joint image corrupted by noise. in 2007 8th International Conference on Electronic Measurement and Instruments, ICEMI., 4350820, pp. 2876-2879, 2007 8th International Conference on Electronic Measurement and Instruments, ICEMI, Xian, China, 16/08/07. https://doi.org/10.1109/ICEMI.2007.4350820

Edge detection of the low contrast welded joint image corrupted by noise. / Zhang, Xuming; Zhouping, Yin; Youlun, Xiong.
2007 8th International Conference on Electronic Measurement and Instruments, ICEMI. 2007. p. 2876-2879 4350820.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Edge detection of the low contrast welded joint image corrupted by noise

AU - Zhang, Xuming

AU - Zhouping, Yin

AU - Youlun, Xiong

PY - 2007/12/1

Y1 - 2007/12/1

N2 - To extract the edges from the low-contrast welded joint image corrupted by noise, the morphological filter is firstly proposed to remove the noise from the image. Then the improved fuzzy edge detection (FED) algorithm is adopted to realize the multi-level fuzzy enhancement of the filtered image and extract the edges from the enhanced image using multi-directional edge detection operator. Experimental results demonstrate that the improved FED algorithm can extract the continuous and thin edges and remove the false edges from the image, which leads to its better performance than the Sobel operator, Canny operator, traditional FED algorithm and fast FED algorithm.

AB - To extract the edges from the low-contrast welded joint image corrupted by noise, the morphological filter is firstly proposed to remove the noise from the image. Then the improved fuzzy edge detection (FED) algorithm is adopted to realize the multi-level fuzzy enhancement of the filtered image and extract the edges from the enhanced image using multi-directional edge detection operator. Experimental results demonstrate that the improved FED algorithm can extract the continuous and thin edges and remove the false edges from the image, which leads to its better performance than the Sobel operator, Canny operator, traditional FED algorithm and fast FED algorithm.

KW - Edge detection

KW - Fuzzy enhancement

KW - Morphological filter

KW - Welded joint image

UR - http://www.scopus.com/inward/record.url?scp=51349120276&partnerID=8YFLogxK

U2 - 10.1109/ICEMI.2007.4350820

DO - 10.1109/ICEMI.2007.4350820

M3 - Conference article published in proceeding or book

SN - 1424411351

SN - 9781424411351

SP - 2876

EP - 2879

BT - 2007 8th International Conference on Electronic Measurement and Instruments, ICEMI

T2 - 2007 8th International Conference on Electronic Measurement and Instruments, ICEMI

Y2 - 16 August 2007 through 18 August 2007

ER -

Edge detection of the low contrast welded joint image corrupted by noise

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this