An automated feature selection method for visual inspection systems

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

Automated visual inspection (AVI) systems these days are considered essential in the assembly of surface-mounted devices (SMDs) in the electronics industry. This industry has faced the problem of rapid introduction and retirement of SMD-based products with the consequent obsolescence of the inspection systems already in the assembly lines. The constant introduction of new products has caused AVI systems to become rapidly obsolete. The general goal of this research centers on developing self-training AVI systems for the inspection of SMD components. The premise is that these systems would be less prone to obsolescence. In this paper, the authors describe the methodology being used for automatically selecting the features to inspect new components. In particular, this paper explores the use of multivariate stepwise discriminant analysis techniques, such as Wilks' Lambda, in order to automate the feature selection process. All of these techniques are applied to a case study of the inspection of SMD components.

Original languageEnglish (US)
Article number1707957
Pages (from-to)394-406
Number of pages13
JournalIEEE Transactions on Automation Science and Engineering
Volume3
Issue number4
DOIs
StatePublished - Oct 2006

Fingerprint

Feature extraction
Surface mount technology
Inspection
Obsolescence
Electronics industry
Discriminant analysis
Industry

Keywords

  • Automated visual inspection (AVI)
  • Feature selection
  • Quadratic vector classifier

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

An automated feature selection method for visual inspection systems. / Garcia, Hugo C.; Villalobos, Jesus; Runger, George.

In: IEEE Transactions on Automation Science and Engineering, Vol. 3, No. 4, 1707957, 10.2006, p. 394-406.

Research output: Contribution to journalArticle

@article{ad5c72a778544d2b82659b33f284b7eb,
title = "An automated feature selection method for visual inspection systems",
abstract = "Automated visual inspection (AVI) systems these days are considered essential in the assembly of surface-mounted devices (SMDs) in the electronics industry. This industry has faced the problem of rapid introduction and retirement of SMD-based products with the consequent obsolescence of the inspection systems already in the assembly lines. The constant introduction of new products has caused AVI systems to become rapidly obsolete. The general goal of this research centers on developing self-training AVI systems for the inspection of SMD components. The premise is that these systems would be less prone to obsolescence. In this paper, the authors describe the methodology being used for automatically selecting the features to inspect new components. In particular, this paper explores the use of multivariate stepwise discriminant analysis techniques, such as Wilks' Lambda, in order to automate the feature selection process. All of these techniques are applied to a case study of the inspection of SMD components.",
keywords = "Automated visual inspection (AVI), Feature selection, Quadratic vector classifier",
author = "Garcia, {Hugo C.} and Jesus Villalobos and George Runger",
year = "2006",
month = "10",
doi = "10.1109/TASE.2006.877399",
language = "English (US)",
volume = "3",
pages = "394--406",
journal = "IEEE Transactions on Automation Science and Engineering",
issn = "1545-5955",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - An automated feature selection method for visual inspection systems

AU - Garcia, Hugo C.

AU - Villalobos, Jesus

AU - Runger, George

PY - 2006/10

Y1 - 2006/10

N2 - Automated visual inspection (AVI) systems these days are considered essential in the assembly of surface-mounted devices (SMDs) in the electronics industry. This industry has faced the problem of rapid introduction and retirement of SMD-based products with the consequent obsolescence of the inspection systems already in the assembly lines. The constant introduction of new products has caused AVI systems to become rapidly obsolete. The general goal of this research centers on developing self-training AVI systems for the inspection of SMD components. The premise is that these systems would be less prone to obsolescence. In this paper, the authors describe the methodology being used for automatically selecting the features to inspect new components. In particular, this paper explores the use of multivariate stepwise discriminant analysis techniques, such as Wilks' Lambda, in order to automate the feature selection process. All of these techniques are applied to a case study of the inspection of SMD components.

AB - Automated visual inspection (AVI) systems these days are considered essential in the assembly of surface-mounted devices (SMDs) in the electronics industry. This industry has faced the problem of rapid introduction and retirement of SMD-based products with the consequent obsolescence of the inspection systems already in the assembly lines. The constant introduction of new products has caused AVI systems to become rapidly obsolete. The general goal of this research centers on developing self-training AVI systems for the inspection of SMD components. The premise is that these systems would be less prone to obsolescence. In this paper, the authors describe the methodology being used for automatically selecting the features to inspect new components. In particular, this paper explores the use of multivariate stepwise discriminant analysis techniques, such as Wilks' Lambda, in order to automate the feature selection process. All of these techniques are applied to a case study of the inspection of SMD components.

KW - Automated visual inspection (AVI)

KW - Feature selection

KW - Quadratic vector classifier

UR - http://www.scopus.com/inward/record.url?scp=33750089325&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750089325&partnerID=8YFLogxK

U2 - 10.1109/TASE.2006.877399

DO - 10.1109/TASE.2006.877399

M3 - Article

AN - SCOPUS:33750089325

VL - 3

SP - 394

EP - 406

JO - IEEE Transactions on Automation Science and Engineering

JF - IEEE Transactions on Automation Science and Engineering

SN - 1545-5955

IS - 4

M1 - 1707957

ER -