TY - GEN
T1 - A Feature-Based Transfer Learning Method for Surface Defect Detection in Smart Manufacturing
AU - Ateeq, Muhammad
AU - P. P. Abdul Majeed, Anwar
AU - Hafizh, Hadyan
AU - Mohd Razman, Mohd Azraai
AU - Mohd Khairuddin, Ismail
AU - Noordin, Nurul Hazlina
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.
PY - 2024
Y1 - 2024
N2 - The employment of deep learning architecture for defect detection in the manufacturing industry has gained due attention owing to the advancement of computational technology. Conventional means of defect detection by manual visual inspection by operators are often deemed laborious as well as prone 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 its efficacy in detecting the defects, namely the VGG16-kNN and VGG16-SVM pipelines, respectively. It was demonstrated from the study that the VGG16-SVM pipeline was more superior compared to the VGG16-kNN pipeline as no misclassification transpired in either the test or the validation dataset. It could be concluded that the proposed pipeline is suitable for the classification of surface defects.
AB - The employment of deep learning architecture for defect detection in the manufacturing industry has gained due attention owing to the advancement of computational technology. Conventional means of defect detection by manual visual inspection by operators are often deemed laborious as well as prone 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 its efficacy in detecting the defects, namely the VGG16-kNN and VGG16-SVM pipelines, respectively. It was demonstrated from the study that the VGG16-SVM pipeline was more superior compared to the VGG16-kNN pipeline as no misclassification transpired in either the test or the validation dataset. It could be concluded that the proposed pipeline is suitable for the classification of surface defects.
KW - Deep learning
KW - Feature-based transfer learning
KW - Industrial IoT
KW - IoT
KW - Machine learning
KW - Smart manufacturing
KW - Surface defects detection
UR - http://www.scopus.com/inward/record.url?scp=85192161059&partnerID=8YFLogxK
U2 - 10.1007/978-981-99-8819-8_37
DO - 10.1007/978-981-99-8819-8_37
M3 - Conference Proceeding
AN - SCOPUS:85192161059
SN - 9789819988181
T3 - Lecture Notes in Networks and Systems
SP - 455
EP - 461
BT - Intelligent Manufacturing and Mechatronics - Selected Articles from iM3F 2023
A2 - Mohd Isa, Wan Hasbullah
A2 - Mohd Khairuddin, Ismail
A2 - Mohd Razman, Mohd Azraai
A2 - Saruchi, Sarah 'Atifah
A2 - Teh, Sze-Hong
A2 - Liu, Pengcheng
PB - Springer Science and Business Media Deutschland GmbH
T2 - 4th International conference on Innovative Manufacturing, Mechatronics and Materials Forum, iM3F2023
Y2 - 7 August 2023 through 8 August 2023
ER -