Finding and quantitative evaluation of minute flaws on metal surface using hairline

Jianing Zhu, Mamoru Minami

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In this research, a method to detect minute flaws on metal parts is proposed to remove the defective parts before assembling in a factory. The input gray-scale images of metal parts are used directly to recognize the flaw without any image conversion to shorten the recognition time. The recognition problem to find flaws and detect its position on the metal parts is converted here to another problem to search for the maximum peak and the variables giving the peak. Then the recognition problem can be treated as optimization problem, and this conversion allow us to utilize the high performances of GA in the optimization. The effectivenesses and problems of proposed method are studied on standing points of the recognition speed and the quantitative recognition ability. Based on the analysis, we furthermore improved our system to increase the detecion rate of the flaws, that is, the lignting direction is changed to find the best lighting condition that can emphasize the contrast between the metal surface and the bruise by using the reflection character of the hairline on the metal resulted by polishing process.

Original languageEnglish
Title of host publicationIECON Proceedings (Industrial Electronics Conference)
Pages1240-1245
Number of pages6
Volume2
Publication statusPublished - 2004
Externally publishedYes
EventIECON 2004 - 30th Annual Conference of IEEE Industrial Electronics Society - Busan, Korea, Republic of
Duration: Nov 2 2004Nov 6 2004

Other

OtherIECON 2004 - 30th Annual Conference of IEEE Industrial Electronics Society
CountryKorea, Republic of
CityBusan
Period11/2/0411/6/04

Fingerprint

Defects
Metals
Polishing
Industrial plants
Lighting

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Zhu, J., & Minami, M. (2004). Finding and quantitative evaluation of minute flaws on metal surface using hairline. In IECON Proceedings (Industrial Electronics Conference) (Vol. 2, pp. 1240-1245). [TC4-3]

Finding and quantitative evaluation of minute flaws on metal surface using hairline. / Zhu, Jianing; Minami, Mamoru.

IECON Proceedings (Industrial Electronics Conference). Vol. 2 2004. p. 1240-1245 TC4-3.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhu, J & Minami, M 2004, Finding and quantitative evaluation of minute flaws on metal surface using hairline. in IECON Proceedings (Industrial Electronics Conference). vol. 2, TC4-3, pp. 1240-1245, IECON 2004 - 30th Annual Conference of IEEE Industrial Electronics Society, Busan, Korea, Republic of, 11/2/04.
Zhu J, Minami M. Finding and quantitative evaluation of minute flaws on metal surface using hairline. In IECON Proceedings (Industrial Electronics Conference). Vol. 2. 2004. p. 1240-1245. TC4-3
Zhu, Jianing ; Minami, Mamoru. / Finding and quantitative evaluation of minute flaws on metal surface using hairline. IECON Proceedings (Industrial Electronics Conference). Vol. 2 2004. pp. 1240-1245
@inproceedings{1c120b26e3054f34bbb11904194f4152,
title = "Finding and quantitative evaluation of minute flaws on metal surface using hairline",
abstract = "In this research, a method to detect minute flaws on metal parts is proposed to remove the defective parts before assembling in a factory. The input gray-scale images of metal parts are used directly to recognize the flaw without any image conversion to shorten the recognition time. The recognition problem to find flaws and detect its position on the metal parts is converted here to another problem to search for the maximum peak and the variables giving the peak. Then the recognition problem can be treated as optimization problem, and this conversion allow us to utilize the high performances of GA in the optimization. The effectivenesses and problems of proposed method are studied on standing points of the recognition speed and the quantitative recognition ability. Based on the analysis, we furthermore improved our system to increase the detecion rate of the flaws, that is, the lignting direction is changed to find the best lighting condition that can emphasize the contrast between the metal surface and the bruise by using the reflection character of the hairline on the metal resulted by polishing process.",
author = "Jianing Zhu and Mamoru Minami",
year = "2004",
language = "English",
volume = "2",
pages = "1240--1245",
booktitle = "IECON Proceedings (Industrial Electronics Conference)",

}

TY - GEN

T1 - Finding and quantitative evaluation of minute flaws on metal surface using hairline

AU - Zhu, Jianing

AU - Minami, Mamoru

PY - 2004

Y1 - 2004

N2 - In this research, a method to detect minute flaws on metal parts is proposed to remove the defective parts before assembling in a factory. The input gray-scale images of metal parts are used directly to recognize the flaw without any image conversion to shorten the recognition time. The recognition problem to find flaws and detect its position on the metal parts is converted here to another problem to search for the maximum peak and the variables giving the peak. Then the recognition problem can be treated as optimization problem, and this conversion allow us to utilize the high performances of GA in the optimization. The effectivenesses and problems of proposed method are studied on standing points of the recognition speed and the quantitative recognition ability. Based on the analysis, we furthermore improved our system to increase the detecion rate of the flaws, that is, the lignting direction is changed to find the best lighting condition that can emphasize the contrast between the metal surface and the bruise by using the reflection character of the hairline on the metal resulted by polishing process.

AB - In this research, a method to detect minute flaws on metal parts is proposed to remove the defective parts before assembling in a factory. The input gray-scale images of metal parts are used directly to recognize the flaw without any image conversion to shorten the recognition time. The recognition problem to find flaws and detect its position on the metal parts is converted here to another problem to search for the maximum peak and the variables giving the peak. Then the recognition problem can be treated as optimization problem, and this conversion allow us to utilize the high performances of GA in the optimization. The effectivenesses and problems of proposed method are studied on standing points of the recognition speed and the quantitative recognition ability. Based on the analysis, we furthermore improved our system to increase the detecion rate of the flaws, that is, the lignting direction is changed to find the best lighting condition that can emphasize the contrast between the metal surface and the bruise by using the reflection character of the hairline on the metal resulted by polishing process.

UR - http://www.scopus.com/inward/record.url?scp=20544450196&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=20544450196&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:20544450196

VL - 2

SP - 1240

EP - 1245

BT - IECON Proceedings (Industrial Electronics Conference)

ER -