Metal parts visual inspection based on production rules

Sh Hashim Haider, Satria Prabuwono Anton, Siti Norul Huda Sheikh Abdullah

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

2 Citations (Scopus)

Abstract

In manufacturing industry the automated visual inspection system (AVIS) is a method to inspect, classify and detect defects of various products. In the past, the tasks of inspection are carrying out by humans, machines or both. In this paper, we account for an AVIS model to classify mechanical parts in production line. It comprises two parts: hardware and software. The model uses a web-camera attached to an adjustable stand to capture various group of metal part images. The main objective is to develop an intelligent inspection tool based on image processing and production rules. It computes both the area and circularity of mechanical shapes as the features and hence classifies them according to ten categories such as screws, nuts, and bolts at different sizes. The result shows that the accuracy is 91.5% for group and 98.25% for individual classification of mechanical parts subsequently.

Original languageEnglish
Title of host publicationApplied Mechanics and Materials
Pages4091-4095
Number of pages5
Volume110-116
DOIs
Publication statusPublished - 2012
Event2nd International Conference on Mechanical and Aerospace Engineering, ICMAE 2011 - Bangkok
Duration: 29 Jul 201131 Jul 2011

Publication series

NameApplied Mechanics and Materials
Volume110-116
ISSN (Print)16609336
ISSN (Electronic)16627482

Other

Other2nd International Conference on Mechanical and Aerospace Engineering, ICMAE 2011
CityBangkok
Period29/7/1131/7/11

Fingerprint

Inspection
Metals
Nuts (fasteners)
Bolts
Image processing
Cameras
Hardware
Defects
Industry

Keywords

  • Mathematical morphology
  • Metal parts
  • Production rules
  • Visual inspection

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Haider, S. H., Anton, S. P., & Sheikh Abdullah, S. N. H. (2012). Metal parts visual inspection based on production rules. In Applied Mechanics and Materials (Vol. 110-116, pp. 4091-4095). (Applied Mechanics and Materials; Vol. 110-116). https://doi.org/10.4028/www.scientific.net/AMM.110-116.4091

Metal parts visual inspection based on production rules. / Haider, Sh Hashim; Anton, Satria Prabuwono; Sheikh Abdullah, Siti Norul Huda.

Applied Mechanics and Materials. Vol. 110-116 2012. p. 4091-4095 (Applied Mechanics and Materials; Vol. 110-116).

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

Haider, SH, Anton, SP & Sheikh Abdullah, SNH 2012, Metal parts visual inspection based on production rules. in Applied Mechanics and Materials. vol. 110-116, Applied Mechanics and Materials, vol. 110-116, pp. 4091-4095, 2nd International Conference on Mechanical and Aerospace Engineering, ICMAE 2011, Bangkok, 29/7/11. https://doi.org/10.4028/www.scientific.net/AMM.110-116.4091
Haider SH, Anton SP, Sheikh Abdullah SNH. Metal parts visual inspection based on production rules. In Applied Mechanics and Materials. Vol. 110-116. 2012. p. 4091-4095. (Applied Mechanics and Materials). https://doi.org/10.4028/www.scientific.net/AMM.110-116.4091
Haider, Sh Hashim ; Anton, Satria Prabuwono ; Sheikh Abdullah, Siti Norul Huda. / Metal parts visual inspection based on production rules. Applied Mechanics and Materials. Vol. 110-116 2012. pp. 4091-4095 (Applied Mechanics and Materials).
@inproceedings{4adbeb6f7b1a407ab0d015d7fb0b8725,
title = "Metal parts visual inspection based on production rules",
abstract = "In manufacturing industry the automated visual inspection system (AVIS) is a method to inspect, classify and detect defects of various products. In the past, the tasks of inspection are carrying out by humans, machines or both. In this paper, we account for an AVIS model to classify mechanical parts in production line. It comprises two parts: hardware and software. The model uses a web-camera attached to an adjustable stand to capture various group of metal part images. The main objective is to develop an intelligent inspection tool based on image processing and production rules. It computes both the area and circularity of mechanical shapes as the features and hence classifies them according to ten categories such as screws, nuts, and bolts at different sizes. The result shows that the accuracy is 91.5{\%} for group and 98.25{\%} for individual classification of mechanical parts subsequently.",
keywords = "Mathematical morphology, Metal parts, Production rules, Visual inspection",
author = "Haider, {Sh Hashim} and Anton, {Satria Prabuwono} and {Sheikh Abdullah}, {Siti Norul Huda}",
year = "2012",
doi = "10.4028/www.scientific.net/AMM.110-116.4091",
language = "English",
isbn = "9783037852620",
volume = "110-116",
series = "Applied Mechanics and Materials",
pages = "4091--4095",
booktitle = "Applied Mechanics and Materials",

}

TY - GEN

T1 - Metal parts visual inspection based on production rules

AU - Haider, Sh Hashim

AU - Anton, Satria Prabuwono

AU - Sheikh Abdullah, Siti Norul Huda

PY - 2012

Y1 - 2012

N2 - In manufacturing industry the automated visual inspection system (AVIS) is a method to inspect, classify and detect defects of various products. In the past, the tasks of inspection are carrying out by humans, machines or both. In this paper, we account for an AVIS model to classify mechanical parts in production line. It comprises two parts: hardware and software. The model uses a web-camera attached to an adjustable stand to capture various group of metal part images. The main objective is to develop an intelligent inspection tool based on image processing and production rules. It computes both the area and circularity of mechanical shapes as the features and hence classifies them according to ten categories such as screws, nuts, and bolts at different sizes. The result shows that the accuracy is 91.5% for group and 98.25% for individual classification of mechanical parts subsequently.

AB - In manufacturing industry the automated visual inspection system (AVIS) is a method to inspect, classify and detect defects of various products. In the past, the tasks of inspection are carrying out by humans, machines or both. In this paper, we account for an AVIS model to classify mechanical parts in production line. It comprises two parts: hardware and software. The model uses a web-camera attached to an adjustable stand to capture various group of metal part images. The main objective is to develop an intelligent inspection tool based on image processing and production rules. It computes both the area and circularity of mechanical shapes as the features and hence classifies them according to ten categories such as screws, nuts, and bolts at different sizes. The result shows that the accuracy is 91.5% for group and 98.25% for individual classification of mechanical parts subsequently.

KW - Mathematical morphology

KW - Metal parts

KW - Production rules

KW - Visual inspection

UR - http://www.scopus.com/inward/record.url?scp=81255184801&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81255184801&partnerID=8YFLogxK

U2 - 10.4028/www.scientific.net/AMM.110-116.4091

DO - 10.4028/www.scientific.net/AMM.110-116.4091

M3 - Conference contribution

SN - 9783037852620

VL - 110-116

T3 - Applied Mechanics and Materials

SP - 4091

EP - 4095

BT - Applied Mechanics and Materials

ER -