Convolutional networks for voting-based anomaly classification in metal surface inspection
Open accessAbstract
Automated Visual Inspection (AVI) systems for metal surface inspection is increasingly used in industries to aid human visual inspectors for classification of possible anomalies. For classification, the challenge lies in having a small and specific dataset that may easily result in over-fitting. As a solution, we propose to use deep Convolutional Neural Networks (ConvNets) learnt from the large ImageNet dataset [9] for image representations via transfer learning. Since a small dataset cannot be used to fine-tune a ConvNet due to overfitting, we also propose a Majority Voting Mechanism (MVM), which fuses the features extracted from the last three layers of ConvNets using Support Vector Machine (SVM) classifiers. This classification framework is effective where no prior knowledge of the best performing ConvNet layers is needed. This also allows flexibility in the choice of ConvNet used for feature extraction. The proposed method not only outperforms state-of-the-art traditional hand-crafted features in terms of classification but also obtains good results compared to other deep ConvNet features extracted from a pre-selected best layer on several anomaly and texture datasets.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Transfer learning makes full use of previously labelled data and guarantees the precision of the model on new tasks with limited training samples, broadening the application prospect of the CNN.
“At present, transfer learning makes full use of the previously labelled data and guarantees the precision of the model on new tasks with limited training samples [107], which broadens the application prospect of the CNN.”
From Automated Visual Defect Classification for Flat Steel Surface: A Survey (2020) · cites this paper as [107]
Compared with a fully connected network, CNN reduces many parameters and simplifies calculation by adopting local connection, weight sharing and down sampling operations.
“Compare with fully connected network, it reduces many parameters and simplifies the calculation by adopting local connection, weight sharing and down sampling operations.”
From Automated Visual Defect Classification for Flat Steel Surface: A Survey (2020) · cites this paper as [107]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · see citing works
How transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061 · see citing works
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.222 · Cited by 3,150 · see citing works
Describing Textures in the Wild
Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., & Vedaldi, A. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.461 · Cited by 2,438 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical Features
He, Y., Song, K., Meng, Q., & Yan, Y. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2019.2915404 · Cited by 1,341 · see citing works
Dong, H., Song, K., He, Y., Xu, J., Yan, Y., & Meng, Q. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2958826 · Cited by 559 · see citing works
Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks
Tao, X., Zhang, D., Ma, W., Liu, X., & Xu, D. (2018) · Applied Sciences · doi:10.3390/app8091575 · Cited by 471 · see citing works
Steel Surface Defect Recognition: A Survey
Wen, X., Shan, J., He, Y., & Song, K. (2022) · Coatings · doi:10.3390/coatings13010017 · Cited by 191 · see citing works
Automated Visual Defect Classification for Flat Steel Surface: A Survey
Luo, Q., Fang, X., Su, J., Zhou, J., Zhou, B., Yang, C., Liu, L., Gui, W., & Tian, L. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3030167 · Cited by 148 · see citing works
A Semi-Supervised Inspection Approach of Textured Surface Defects under Limited Labeled Samples
He, Y., Wen, X., & Xu, J. (2022) · Coatings · doi:10.3390/coatings12111707 · Cited by 14 · see citing works
- Authors
- Natarajan, V., Hung, T.-Y., Vaikundam, S., & Chia, L.-T.
- Affiliations
- Nanyang Technological University (SG)
- ORCID
- Hung, Tzu-Yi
- Venue
- 2017 IEEE International Conference on Industrial Technology (ICIT)
- Publisher
- IEEE
- Published
- 2017-03
- Pages
- 986-991
- OpenAlex
- W2612454721
- Cited by
- 79
- References
- 5
- Citations by year
- 2026: 1 · 2025: 6 · 2024: 4 · 2023: 12 · 2022: 17 · 2021: 14 · 2020: 11 · 2019: 11 · 2018: 3
- FWCI
- 10.04
- Type
- conference paper
- Language
- en
- Open access
- green
- hdl.handle.net
- Locations
- IEEE International Conference on Industrial Technology (ICIT) (publishedVersion)
- DR-NTU (Nanyang Technological University) (submittedVersion)
- Funders
- National Research Foundation
- Topics
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- metal surface inspection, anomaly classification, convolutional neural networks, transfer learning, majority voting, feature fusion, support vector machine, automated visual inspection, overfitting, ImageNet pre-trained models, texture classification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
