Visual inspection by capturing a rotating industrial part

Tomoya Kaichi, Shohei Mori, Hideo Saito, Junichi Sugano, Hideyuki Adachi

Research output: Contribution to journalArticle

Abstract

Visual inspection is a vital step for maintaining the quality of industrial parts. In visual inspection, the relation between the three factors, camera pose, lights direction and normal vector of a part is very important to detect abnormalities on industrial part. We propose a visual inspection method for industrial parts using an image sequence captured while rotating an industrial part using a rotating table. By rotating a part, we can easily change the relation between three factors. We track the points on part's surfaces in an image sequence. We discriminate abnormal surface points such as scratches from the normal ones based on pixel value transitions in an image sequence. For accurately tracking the points on the part surface, we propose a novel camera calibration method of the rotating tabic and the camera with a telocentric lens and a pose estimation method for the rotating part. We use angular invariant feature vectors for improving robustness against types and shapes of industrial parts to be inspected. We presented experimental results using real data of industrial parts and verified that the proposed method could detect scratches on surfaces.

Original languageEnglish
Pages (from-to)1184-1191
Number of pages8
JournalSeimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering
Volume83
Issue number12
DOIs
Publication statusPublished - 2017 Jan 1

Fingerprint

Inspection
Cameras
Lenses
Pixels
Calibration

Keywords

  • Defect detection
  • Industrial parts
  • Multi-view images
  • Surface inspection
  • Telecentric lens

ASJC Scopus subject areas

  • Mechanical Engineering

Cite this

Visual inspection by capturing a rotating industrial part. / Kaichi, Tomoya; Mori, Shohei; Saito, Hideo; Sugano, Junichi; Adachi, Hideyuki.

In: Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering, Vol. 83, No. 12, 01.01.2017, p. 1184-1191.

Research output: Contribution to journalArticle

Kaichi, Tomoya ; Mori, Shohei ; Saito, Hideo ; Sugano, Junichi ; Adachi, Hideyuki. / Visual inspection by capturing a rotating industrial part. In: Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering. 2017 ; Vol. 83, No. 12. pp. 1184-1191.
@article{5cf638b2cfb34c0abb6a39fb0abcf629,
title = "Visual inspection by capturing a rotating industrial part",
abstract = "Visual inspection is a vital step for maintaining the quality of industrial parts. In visual inspection, the relation between the three factors, camera pose, lights direction and normal vector of a part is very important to detect abnormalities on industrial part. We propose a visual inspection method for industrial parts using an image sequence captured while rotating an industrial part using a rotating table. By rotating a part, we can easily change the relation between three factors. We track the points on part's surfaces in an image sequence. We discriminate abnormal surface points such as scratches from the normal ones based on pixel value transitions in an image sequence. For accurately tracking the points on the part surface, we propose a novel camera calibration method of the rotating tabic and the camera with a telocentric lens and a pose estimation method for the rotating part. We use angular invariant feature vectors for improving robustness against types and shapes of industrial parts to be inspected. We presented experimental results using real data of industrial parts and verified that the proposed method could detect scratches on surfaces.",
keywords = "Defect detection, Industrial parts, Multi-view images, Surface inspection, Telecentric lens",
author = "Tomoya Kaichi and Shohei Mori and Hideo Saito and Junichi Sugano and Hideyuki Adachi",
year = "2017",
month = "1",
day = "1",
doi = "10.2493/jjspe.83.1184",
language = "English",
volume = "83",
pages = "1184--1191",
journal = "Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering",
issn = "0912-0289",
publisher = "Japan Society for Precision Engineering",
number = "12",

}

TY - JOUR

T1 - Visual inspection by capturing a rotating industrial part

AU - Kaichi, Tomoya

AU - Mori, Shohei

AU - Saito, Hideo

AU - Sugano, Junichi

AU - Adachi, Hideyuki

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Visual inspection is a vital step for maintaining the quality of industrial parts. In visual inspection, the relation between the three factors, camera pose, lights direction and normal vector of a part is very important to detect abnormalities on industrial part. We propose a visual inspection method for industrial parts using an image sequence captured while rotating an industrial part using a rotating table. By rotating a part, we can easily change the relation between three factors. We track the points on part's surfaces in an image sequence. We discriminate abnormal surface points such as scratches from the normal ones based on pixel value transitions in an image sequence. For accurately tracking the points on the part surface, we propose a novel camera calibration method of the rotating tabic and the camera with a telocentric lens and a pose estimation method for the rotating part. We use angular invariant feature vectors for improving robustness against types and shapes of industrial parts to be inspected. We presented experimental results using real data of industrial parts and verified that the proposed method could detect scratches on surfaces.

AB - Visual inspection is a vital step for maintaining the quality of industrial parts. In visual inspection, the relation between the three factors, camera pose, lights direction and normal vector of a part is very important to detect abnormalities on industrial part. We propose a visual inspection method for industrial parts using an image sequence captured while rotating an industrial part using a rotating table. By rotating a part, we can easily change the relation between three factors. We track the points on part's surfaces in an image sequence. We discriminate abnormal surface points such as scratches from the normal ones based on pixel value transitions in an image sequence. For accurately tracking the points on the part surface, we propose a novel camera calibration method of the rotating tabic and the camera with a telocentric lens and a pose estimation method for the rotating part. We use angular invariant feature vectors for improving robustness against types and shapes of industrial parts to be inspected. We presented experimental results using real data of industrial parts and verified that the proposed method could detect scratches on surfaces.

KW - Defect detection

KW - Industrial parts

KW - Multi-view images

KW - Surface inspection

KW - Telecentric lens

UR - http://www.scopus.com/inward/record.url?scp=85037119880&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037119880&partnerID=8YFLogxK

U2 - 10.2493/jjspe.83.1184

DO - 10.2493/jjspe.83.1184

M3 - Article

AN - SCOPUS:85037119880

VL - 83

SP - 1184

EP - 1191

JO - Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering

JF - Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering

SN - 0912-0289

IS - 12

ER -