A Classification Algorithm and Optimal Feature Selection Methodology for Automated Solder Joint Defect Inspection

Olagunju Oyeleye; E. Amine Lehtihet

doi:10.1016/s0278-6125(98)80073-3

A Classification Algorithm and Optimal Feature Selection Methodology for Automated Solder Joint Defect Inspection

Olagunju Oyeleye, E. Amine Lehtihet

Marcus Department of Industrial and Manufacturing Engineering

Research output: Contribution to journal › Article › peer-review

16 Scopus citations

Abstract

A classification algorithm and optimal feature selection methodology are developed for implementation on an automated solder defect inspection system. Computer-generated three-dimensional geometric models of solder joint defects are used to train the system and simulate defect classification. System performance is assessed through simulation and is shown to be successful at classification of dominant solder defects, including simultaneously occurring defects and overlapping defect classes.

Original language	English (US)
Pages (from-to)	251-262
Number of pages	12
Journal	Journal of Manufacturing Systems
Volume	17
Issue number	4
DOIs	https://doi.org/10.1016/s0278-6125(98)80073-3
State	Published - 1998

All Science Journal Classification (ASJC) codes

Software
Control and Systems Engineering
Hardware and Architecture
Industrial and Manufacturing Engineering

Access to Document

10.1016/s0278-6125(98)80073-3

Cite this

@article{27d886a74f1f4e939caf1949456a8e40,

title = "A Classification Algorithm and Optimal Feature Selection Methodology for Automated Solder Joint Defect Inspection",

abstract = "A classification algorithm and optimal feature selection methodology are developed for implementation on an automated solder defect inspection system. Computer-generated three-dimensional geometric models of solder joint defects are used to train the system and simulate defect classification. System performance is assessed through simulation and is shown to be successful at classification of dominant solder defects, including simultaneously occurring defects and overlapping defect classes.",

author = "Olagunju Oyeleye and Lehtihet, {E. Amine}",

year = "1998",

doi = "10.1016/s0278-6125(98)80073-3",

language = "English (US)",

volume = "17",

pages = "251--262",

journal = "Journal of Manufacturing Systems",

issn = "0278-6125",

publisher = "Elsevier",

number = "4",

}

TY - JOUR

T1 - A Classification Algorithm and Optimal Feature Selection Methodology for Automated Solder Joint Defect Inspection

AU - Oyeleye, Olagunju

AU - Lehtihet, E. Amine

PY - 1998

Y1 - 1998

N2 - A classification algorithm and optimal feature selection methodology are developed for implementation on an automated solder defect inspection system. Computer-generated three-dimensional geometric models of solder joint defects are used to train the system and simulate defect classification. System performance is assessed through simulation and is shown to be successful at classification of dominant solder defects, including simultaneously occurring defects and overlapping defect classes.

AB - A classification algorithm and optimal feature selection methodology are developed for implementation on an automated solder defect inspection system. Computer-generated three-dimensional geometric models of solder joint defects are used to train the system and simulate defect classification. System performance is assessed through simulation and is shown to be successful at classification of dominant solder defects, including simultaneously occurring defects and overlapping defect classes.

UR - http://www.scopus.com/inward/record.url?scp=0031640581&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031640581&partnerID=8YFLogxK

U2 - 10.1016/s0278-6125(98)80073-3

DO - 10.1016/s0278-6125(98)80073-3

M3 - Article

AN - SCOPUS:0031640581

SN - 0278-6125

VL - 17

SP - 251

EP - 262

JO - Journal of Manufacturing Systems

JF - Journal of Manufacturing Systems

IS - 4

ER -

A Classification Algorithm and Optimal Feature Selection Methodology for Automated Solder Joint Defect Inspection

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this