Surface Anomaly Detection Using Feature-Based Transfer Learning for IoT-Enabled Smart Manufacturing

Muhammad Ateeq; Matilda Isaac; Hadyan Hafizh; Bintao Hu; Ismail Mohd Khairuddin; Mohd Amirul Abdullah; Anwar P.P.Abdul Majeed

doi:10.1007/978-981-97-3847-2_3

Surface Anomaly Detection Using Feature-Based Transfer Learning for IoT-Enabled Smart Manufacturing

Muhammad Ateeq, Matilda Isaac, Hadyan Hafizh, Bintao Hu, Ismail Mohd Khairuddin, Mohd Amirul Abdullah, Anwar P.P.Abdul Majeed^*

^*Corresponding author for this work

School of Internet of Things

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

Abstract

Owing to the advancement of computational technology, the employment of deep learning architecture for defect detection in the manufacturing industry has gained considerable attention. Traditional means of defect detection through manual visual inspection by operators are laborious as well as susceptible to mistakes. In the present study, a feature-based transfer learning approach is used to classify surface defects. The KolektorSDD database is used in the present study. Two pipelines were developed to investigate their efficacy in detecting the defects, namely the InceptionV3-SVM and VGG19-SVM pipelines, respectively. It was demonstrated from the study that the VGG19-SVM pipeline could provide desirable results compared to the InceptionV3-SVM pipeline, suggesting that the VGG19 is a better feature extractor for the evaluated surface defects. It could be concluded that the proposed pipeline is suitable for the classification of surface defects.

Original language	English
Title of host publication	Proceedings of the 7th International Conference on Electrical, Control and Computer Engineering - InECCE 2023
Editors	Zainah Md. Zain, Norizam Sulaiman, Mahfuzah Mustafa, Mohammed Nazmus Shakib, Waheb A. Jabbar
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	25-32
Number of pages	8
ISBN (Print)	9789819738465
DOIs	https://doi.org/10.1007/978-981-97-3847-2_3
Publication status	Published - 2024
Event	7th International Conference on Electrical, Control, and Computer Engineering, InECCE 2023 - Kuala Lumpur, Malaysia Duration: 22 Aug 2023 → 22 Aug 2023

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	1212 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	7th International Conference on Electrical, Control, and Computer Engineering, InECCE 2023
Country/Territory	Malaysia
City	Kuala Lumpur
Period	22/08/23 → 22/08/23

Keywords

Deep learning
Defect detection
Feature-based transfer learning
Industrial IoT
Industry 4.0
Learning
Machine
Metal surfaces defects
Smart manufacturing

Access to Document

10.1007/978-981-97-3847-2_3

Cite this

Ateeq, M., Isaac, M., Hafizh, H., Hu, B., Khairuddin, I. M., Abdullah, M. A., & Majeed, A. P. P. A. (2024). Surface Anomaly Detection Using Feature-Based Transfer Learning for IoT-Enabled Smart Manufacturing. In Z. Md. Zain, N. Sulaiman, M. Mustafa, M. N. Shakib, & W. A. Jabbar (Eds.), Proceedings of the 7th International Conference on Electrical, Control and Computer Engineering - InECCE 2023 (pp. 25-32). (Lecture Notes in Electrical Engineering; Vol. 1212 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-97-3847-2_3

Ateeq, Muhammad ; Isaac, Matilda ; Hafizh, Hadyan et al. / Surface Anomaly Detection Using Feature-Based Transfer Learning for IoT-Enabled Smart Manufacturing. Proceedings of the 7th International Conference on Electrical, Control and Computer Engineering - InECCE 2023. editor / Zainah Md. Zain ; Norizam Sulaiman ; Mahfuzah Mustafa ; Mohammed Nazmus Shakib ; Waheb A. Jabbar. Springer Science and Business Media Deutschland GmbH, 2024. pp. 25-32 (Lecture Notes in Electrical Engineering).

@inproceedings{7c918f50c4284ee4981458006ccbc369,

title = "Surface Anomaly Detection Using Feature-Based Transfer Learning for IoT-Enabled Smart Manufacturing",

abstract = "Owing to the advancement of computational technology, the employment of deep learning architecture for defect detection in the manufacturing industry has gained considerable attention. Traditional means of defect detection through manual visual inspection by operators are laborious as well as susceptible to mistakes. In the present study, a feature-based transfer learning approach is used to classify surface defects. The KolektorSDD database is used in the present study. Two pipelines were developed to investigate their efficacy in detecting the defects, namely the InceptionV3-SVM and VGG19-SVM pipelines, respectively. It was demonstrated from the study that the VGG19-SVM pipeline could provide desirable results compared to the InceptionV3-SVM pipeline, suggesting that the VGG19 is a better feature extractor for the evaluated surface defects. It could be concluded that the proposed pipeline is suitable for the classification of surface defects.",

keywords = "Deep learning, Defect detection, Feature-based transfer learning, Industrial IoT, Industry 4.0, Learning, Machine, Metal surfaces defects, Smart manufacturing",

author = "Muhammad Ateeq and Matilda Isaac and Hadyan Hafizh and Bintao Hu and Khairuddin, {Ismail Mohd} and Abdullah, {Mohd Amirul} and Majeed, {Anwar P.P.Abdul}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.; 7th International Conference on Electrical, Control, and Computer Engineering, InECCE 2023 ; Conference date: 22-08-2023 Through 22-08-2023",

year = "2024",

doi = "10.1007/978-981-97-3847-2_3",

language = "English",

isbn = "9789819738465",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "25--32",

editor = "{Md. Zain}, Zainah and Norizam Sulaiman and Mahfuzah Mustafa and Shakib, {Mohammed Nazmus} and {A. Jabbar}, Waheb",

booktitle = "Proceedings of the 7th International Conference on Electrical, Control and Computer Engineering - InECCE 2023",

}

Ateeq, M , Isaac, M, Hafizh, H, Hu, B, Khairuddin, IM, Abdullah, MA & Majeed, APPA 2024, Surface Anomaly Detection Using Feature-Based Transfer Learning for IoT-Enabled Smart Manufacturing. in Z Md. Zain, N Sulaiman, M Mustafa, MN Shakib & W A. Jabbar (eds), Proceedings of the 7th International Conference on Electrical, Control and Computer Engineering - InECCE 2023. Lecture Notes in Electrical Engineering, vol. 1212 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 25-32, 7th International Conference on Electrical, Control, and Computer Engineering, InECCE 2023, Kuala Lumpur, Malaysia, 22/08/23. https://doi.org/10.1007/978-981-97-3847-2_3

Surface Anomaly Detection Using Feature-Based Transfer Learning for IoT-Enabled Smart Manufacturing. / Ateeq, Muhammad ; Isaac, Matilda; Hafizh, Hadyan et al.
Proceedings of the 7th International Conference on Electrical, Control and Computer Engineering - InECCE 2023. ed. / Zainah Md. Zain; Norizam Sulaiman; Mahfuzah Mustafa; Mohammed Nazmus Shakib; Waheb A. Jabbar. Springer Science and Business Media Deutschland GmbH, 2024. p. 25-32 (Lecture Notes in Electrical Engineering; Vol. 1212 LNEE).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - Surface Anomaly Detection Using Feature-Based Transfer Learning for IoT-Enabled Smart Manufacturing

AU - Ateeq, Muhammad

AU - Isaac, Matilda

AU - Hafizh, Hadyan

AU - Hu, Bintao

AU - Khairuddin, Ismail Mohd

AU - Abdullah, Mohd Amirul

AU - Majeed, Anwar P.P.Abdul

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

PY - 2024

Y1 - 2024

N2 - Owing to the advancement of computational technology, the employment of deep learning architecture for defect detection in the manufacturing industry has gained considerable attention. Traditional means of defect detection through manual visual inspection by operators are laborious as well as susceptible to mistakes. In the present study, a feature-based transfer learning approach is used to classify surface defects. The KolektorSDD database is used in the present study. Two pipelines were developed to investigate their efficacy in detecting the defects, namely the InceptionV3-SVM and VGG19-SVM pipelines, respectively. It was demonstrated from the study that the VGG19-SVM pipeline could provide desirable results compared to the InceptionV3-SVM pipeline, suggesting that the VGG19 is a better feature extractor for the evaluated surface defects. It could be concluded that the proposed pipeline is suitable for the classification of surface defects.

AB - Owing to the advancement of computational technology, the employment of deep learning architecture for defect detection in the manufacturing industry has gained considerable attention. Traditional means of defect detection through manual visual inspection by operators are laborious as well as susceptible to mistakes. In the present study, a feature-based transfer learning approach is used to classify surface defects. The KolektorSDD database is used in the present study. Two pipelines were developed to investigate their efficacy in detecting the defects, namely the InceptionV3-SVM and VGG19-SVM pipelines, respectively. It was demonstrated from the study that the VGG19-SVM pipeline could provide desirable results compared to the InceptionV3-SVM pipeline, suggesting that the VGG19 is a better feature extractor for the evaluated surface defects. It could be concluded that the proposed pipeline is suitable for the classification of surface defects.

KW - Deep learning

KW - Defect detection

KW - Feature-based transfer learning

KW - Industrial IoT

KW - Industry 4.0

KW - Learning

KW - Machine

KW - Metal surfaces defects

KW - Smart manufacturing

UR - http://www.scopus.com/inward/record.url?scp=105004721246&partnerID=8YFLogxK

U2 - 10.1007/978-981-97-3847-2_3

DO - 10.1007/978-981-97-3847-2_3

M3 - Conference Proceeding

AN - SCOPUS:105004721246

SN - 9789819738465

T3 - Lecture Notes in Electrical Engineering

SP - 25

EP - 32

BT - Proceedings of the 7th International Conference on Electrical, Control and Computer Engineering - InECCE 2023

A2 - Md. Zain, Zainah

A2 - Sulaiman, Norizam

A2 - Mustafa, Mahfuzah

A2 - Shakib, Mohammed Nazmus

A2 - A. Jabbar, Waheb

PB - Springer Science and Business Media Deutschland GmbH

T2 - 7th International Conference on Electrical, Control, and Computer Engineering, InECCE 2023

Y2 - 22 August 2023 through 22 August 2023

ER -

Ateeq M , Isaac M, Hafizh H, Hu B, Khairuddin IM, Abdullah MA et al. Surface Anomaly Detection Using Feature-Based Transfer Learning for IoT-Enabled Smart Manufacturing. In Md. Zain Z, Sulaiman N, Mustafa M, Shakib MN, A. Jabbar W, editors, Proceedings of the 7th International Conference on Electrical, Control and Computer Engineering - InECCE 2023. Springer Science and Business Media Deutschland GmbH. 2024. p. 25-32. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-97-3847-2_3

Surface Anomaly Detection Using Feature-Based Transfer Learning for IoT-Enabled Smart Manufacturing

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this