Multi-feature sparse-based defect detection and classification in semiconductor units

Bashar Haddad, Lina Karam, Jieping Ye, Nital Patel, Martin Braun

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

Abstract

Automated inspection systems have been used extensively for high-speed defect detection, gaging and quality control. In the semiconductor manufacturing industry, assembly and testing processes are getting more complex resulting in a greater tendency of defects to impact the production process. Currently available defect detection and classification systems are customized and hard-wired to the detection of particular classes of defects and cannot deal with new unknown classes. Shortage of defective units, similarities within different classes of defects, wide variations within the same defect class, and data imbalance are the basic challenges for this problem. This paper presents a novel stacking-based multi-feature, sparse-based defect detection and classification method that is robust to data imbalance and low number of training samples. Experimental results on real-world data from Intel show that the proposed approach results in a high classification accuracy as compared to existing methods.

Original languageEnglish (US)
Title of host publication2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
PublisherIEEE Computer Society
Pages754-758
Number of pages5
Volume2016-August
ISBN (Electronic)9781467399616
DOIs
StatePublished - Aug 3 2016
Event23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, United States
Duration: Sep 25 2016Sep 28 2016

Other

Other23rd IEEE International Conference on Image Processing, ICIP 2016
CountryUnited States
CityPhoenix
Period9/25/169/28/16

Fingerprint

Semiconductor materials
Defects
Gaging
Quality control
Inspection
Defect detection
Testing
Industry

Keywords

  • Automation
  • Data mining
  • Feature extraction
  • Image classification
  • Sparse coding
  • Stacking

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Haddad, B., Karam, L., Ye, J., Patel, N., & Braun, M. (2016). Multi-feature sparse-based defect detection and classification in semiconductor units. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings (Vol. 2016-August, pp. 754-758). [7532458] IEEE Computer Society. https://doi.org/10.1109/ICIP.2016.7532458

Multi-feature sparse-based defect detection and classification in semiconductor units. / Haddad, Bashar; Karam, Lina; Ye, Jieping; Patel, Nital; Braun, Martin.

2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August IEEE Computer Society, 2016. p. 754-758 7532458.

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

Haddad, B, Karam, L, Ye, J, Patel, N & Braun, M 2016, Multi-feature sparse-based defect detection and classification in semiconductor units. in 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. vol. 2016-August, 7532458, IEEE Computer Society, pp. 754-758, 23rd IEEE International Conference on Image Processing, ICIP 2016, Phoenix, United States, 9/25/16. https://doi.org/10.1109/ICIP.2016.7532458
Haddad B, Karam L, Ye J, Patel N, Braun M. Multi-feature sparse-based defect detection and classification in semiconductor units. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August. IEEE Computer Society. 2016. p. 754-758. 7532458 https://doi.org/10.1109/ICIP.2016.7532458
Haddad, Bashar ; Karam, Lina ; Ye, Jieping ; Patel, Nital ; Braun, Martin. / Multi-feature sparse-based defect detection and classification in semiconductor units. 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August IEEE Computer Society, 2016. pp. 754-758
@inproceedings{7298abf654b84d7b8f1f585d81bb9828,
title = "Multi-feature sparse-based defect detection and classification in semiconductor units",
abstract = "Automated inspection systems have been used extensively for high-speed defect detection, gaging and quality control. In the semiconductor manufacturing industry, assembly and testing processes are getting more complex resulting in a greater tendency of defects to impact the production process. Currently available defect detection and classification systems are customized and hard-wired to the detection of particular classes of defects and cannot deal with new unknown classes. Shortage of defective units, similarities within different classes of defects, wide variations within the same defect class, and data imbalance are the basic challenges for this problem. This paper presents a novel stacking-based multi-feature, sparse-based defect detection and classification method that is robust to data imbalance and low number of training samples. Experimental results on real-world data from Intel show that the proposed approach results in a high classification accuracy as compared to existing methods.",
keywords = "Automation, Data mining, Feature extraction, Image classification, Sparse coding, Stacking",
author = "Bashar Haddad and Lina Karam and Jieping Ye and Nital Patel and Martin Braun",
year = "2016",
month = "8",
day = "3",
doi = "10.1109/ICIP.2016.7532458",
language = "English (US)",
volume = "2016-August",
pages = "754--758",
booktitle = "2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - Multi-feature sparse-based defect detection and classification in semiconductor units

AU - Haddad, Bashar

AU - Karam, Lina

AU - Ye, Jieping

AU - Patel, Nital

AU - Braun, Martin

PY - 2016/8/3

Y1 - 2016/8/3

N2 - Automated inspection systems have been used extensively for high-speed defect detection, gaging and quality control. In the semiconductor manufacturing industry, assembly and testing processes are getting more complex resulting in a greater tendency of defects to impact the production process. Currently available defect detection and classification systems are customized and hard-wired to the detection of particular classes of defects and cannot deal with new unknown classes. Shortage of defective units, similarities within different classes of defects, wide variations within the same defect class, and data imbalance are the basic challenges for this problem. This paper presents a novel stacking-based multi-feature, sparse-based defect detection and classification method that is robust to data imbalance and low number of training samples. Experimental results on real-world data from Intel show that the proposed approach results in a high classification accuracy as compared to existing methods.

AB - Automated inspection systems have been used extensively for high-speed defect detection, gaging and quality control. In the semiconductor manufacturing industry, assembly and testing processes are getting more complex resulting in a greater tendency of defects to impact the production process. Currently available defect detection and classification systems are customized and hard-wired to the detection of particular classes of defects and cannot deal with new unknown classes. Shortage of defective units, similarities within different classes of defects, wide variations within the same defect class, and data imbalance are the basic challenges for this problem. This paper presents a novel stacking-based multi-feature, sparse-based defect detection and classification method that is robust to data imbalance and low number of training samples. Experimental results on real-world data from Intel show that the proposed approach results in a high classification accuracy as compared to existing methods.

KW - Automation

KW - Data mining

KW - Feature extraction

KW - Image classification

KW - Sparse coding

KW - Stacking

UR - http://www.scopus.com/inward/record.url?scp=85006825746&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006825746&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2016.7532458

DO - 10.1109/ICIP.2016.7532458

M3 - Conference contribution

VL - 2016-August

SP - 754

EP - 758

BT - 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings

PB - IEEE Computer Society

ER -