Surface defect detection : A feature-based transfer learning approach
Surface defect detection is critical for maintaining product quality in manufacturing. In this work, we apply a feature-based transfer learning approach for surface defect classification on the NEU surface defect database. The database contains defects across 6 categories captured under various cond...
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
Institute of Physics
2024
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/41728/ http://umpir.ump.edu.my/id/eprint/41728/1/Surface%20defect%20detection_A%20feature-based%20transfer%20learning%20approach.pdf |
| _version_ | 1848826415162589184 |
|---|---|
| author | Abdul Majeed, Anwar P. P. Muhammad Amirul, Abdullah Ahmad Fakhri, Ab Nasir Mohd Azraai, Mohd Razman Chen, Wei Yap, Eng Hwa |
| author_facet | Abdul Majeed, Anwar P. P. Muhammad Amirul, Abdullah Ahmad Fakhri, Ab Nasir Mohd Azraai, Mohd Razman Chen, Wei Yap, Eng Hwa |
| author_sort | Abdul Majeed, Anwar P. P. |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | Surface defect detection is critical for maintaining product quality in manufacturing. In this work, we apply a feature-based transfer learning approach for surface defect classification on the NEU surface defect database. The database contains defects across 6 categories captured under various conditions. We utilised two pretrained convolutional neural network (CNN) architectures - VGG16 and InceptionV3 - by removing the final classification layer and using the CNN as a fixed feature extractor. The output feature vectors were classified using a logistic regression (LR) model. The data was split into train, validation, and test sets with a 70:15:15 ratio. The VGG16-LR model achieved classification accuracy (CA) of 100%, 98%, and 99% for the train, validation, and test sets respectively. The InceptionV3-LR model attained CA of 100%, 91%, and 92% for train, validation, and test. The results demonstrate the effectiveness of transfer learning with CNN feature extraction for surface defect detection on challenging multi-category industrial datasets. Further work includes tuning hyperparameters and evaluating additional architectures. |
| first_indexed | 2025-11-15T03:44:27Z |
| format | Conference or Workshop Item |
| id | ump-41728 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T03:44:27Z |
| publishDate | 2024 |
| publisher | Institute of Physics |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-417282024-07-31T03:30:33Z http://umpir.ump.edu.my/id/eprint/41728/ Surface defect detection : A feature-based transfer learning approach Abdul Majeed, Anwar P. P. Muhammad Amirul, Abdullah Ahmad Fakhri, Ab Nasir Mohd Azraai, Mohd Razman Chen, Wei Yap, Eng Hwa QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) TA Engineering (General). Civil engineering (General) TJ Mechanical engineering and machinery Surface defect detection is critical for maintaining product quality in manufacturing. In this work, we apply a feature-based transfer learning approach for surface defect classification on the NEU surface defect database. The database contains defects across 6 categories captured under various conditions. We utilised two pretrained convolutional neural network (CNN) architectures - VGG16 and InceptionV3 - by removing the final classification layer and using the CNN as a fixed feature extractor. The output feature vectors were classified using a logistic regression (LR) model. The data was split into train, validation, and test sets with a 70:15:15 ratio. The VGG16-LR model achieved classification accuracy (CA) of 100%, 98%, and 99% for the train, validation, and test sets respectively. The InceptionV3-LR model attained CA of 100%, 91%, and 92% for train, validation, and test. The results demonstrate the effectiveness of transfer learning with CNN feature extraction for surface defect detection on challenging multi-category industrial datasets. Further work includes tuning hyperparameters and evaluating additional architectures. Institute of Physics 2024 Conference or Workshop Item PeerReviewed pdf en cc_by_4 http://umpir.ump.edu.my/id/eprint/41728/1/Surface%20defect%20detection_A%20feature-based%20transfer%20learning%20approach.pdf Abdul Majeed, Anwar P. P. and Muhammad Amirul, Abdullah and Ahmad Fakhri, Ab Nasir and Mohd Azraai, Mohd Razman and Chen, Wei and Yap, Eng Hwa (2024) Surface defect detection : A feature-based transfer learning approach. In: Journal of Physics: Conference Series. 2023 International Symposium on Structural Dynamics of Aerospace, ISSDA 2023 , 9-10 September 2023 , Xi'an. pp. 1-7., 2762 (012088). ISSN 1742-6588 (Published) https://doi.org/10.1088/1742-6596/2762/1/012088 |
| spellingShingle | QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) TA Engineering (General). Civil engineering (General) TJ Mechanical engineering and machinery Abdul Majeed, Anwar P. P. Muhammad Amirul, Abdullah Ahmad Fakhri, Ab Nasir Mohd Azraai, Mohd Razman Chen, Wei Yap, Eng Hwa Surface defect detection : A feature-based transfer learning approach |
| title | Surface defect detection : A feature-based transfer learning approach |
| title_full | Surface defect detection : A feature-based transfer learning approach |
| title_fullStr | Surface defect detection : A feature-based transfer learning approach |
| title_full_unstemmed | Surface defect detection : A feature-based transfer learning approach |
| title_short | Surface defect detection : A feature-based transfer learning approach |
| title_sort | surface defect detection : a feature-based transfer learning approach |
| topic | QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) TA Engineering (General). Civil engineering (General) TJ Mechanical engineering and machinery |
| url | http://umpir.ump.edu.my/id/eprint/41728/ http://umpir.ump.edu.my/id/eprint/41728/ http://umpir.ump.edu.my/id/eprint/41728/1/Surface%20defect%20detection_A%20feature-based%20transfer%20learning%20approach.pdf |