Multiscale fully convolutional network with application to industrial inspection
Abstract
In recent years, deep learning, particularly Convolutional Neural Network (CNN), has shown great efficacy for solving various vision tasks. In image segmentation, it has been demonstrated that a CNN can greatly outperform other approaches. However, special attention has to be paid towards setting various parameters in the CNN that affects the scale of the feature map generated at the last convolutional layer, where scale here refers to the ratio of the number of pixels in the original input image that correspond to each pixel in the feature map. Quite often, the optimal settings are tied to the specific problem on hand and can be fairly challenging to determine. To overcome such an issue, this paper proposes a multiscale Fully Convolutional Network (FCN) that combines networks trained at various scales, thereby allowing for conducting segmentation more generically. Moreover, such a multiscale architecture allows for incremental fine-tuning as more training images become available later on and new networks can be trained and added to the combined network. Such flexibility has great utility in applications such as industrial inspection, where training images may not be readily available initially, but yet requires a high level of accuracy. This paper will validate our findings by reporting the results that we have obtained by applying multiscale FCN to the inspection of aircraft engine part.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
There is a lack of recent applications of classical image processing techniques to blade inspection.
“There is a lack of recent applications of these techniques to blade inspection. In fact, the field is somewhat weak and has been dominated by the neural networks and deep learning approaches instead [9,19,47,85].”
From Automated Defect Detection and Decision-Support in Gas Turbine Blade Inspection (2021) · cites this paper as [47]
All these CNN applications required large quantities of training data.
“Additionally, all these applications required large quantities of training data.”
From Automated Defect Detection and Decision-Support in Gas Turbine Blade Inspection (2021) · cites this paper as [47]
The training examples used in CNN approaches were of advanced damage that is clearly visible to the human eye.
“However, the training examples were of advanced damage that is clearly visible to the human eye.”
From Automated Defect Detection and Decision-Support in Gas Turbine Blade Inspection (2021) · cites this paper as [47]
CNN approaches for crack and erosion detection typically achieved high accuracy of detection.
“All of these approaches use some form of feature extraction or segmentation techniques to normalise the input into a trained CNN and typically achieved a high accuracy of detection.”
From Automated Defect Detection and Decision-Support in Gas Turbine Blade Inspection (2021) · cites this paper as [47]
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · see citing works
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · see citing works
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834 · see citing works
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684 · see citing works
Linear spatial pyramid matching using sparse coding for image classification
Yang, J., Yu, K., Gong, Y., & Huang, T. S. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2009.5206757 · Cited by 2,895 · see citing works
Learning Hierarchical Features for Scene Labeling
Farabet, C., Couprie, C., Najman, L., & LeCun, Y. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.231 · Cited by 2,620 · see citing works
Learning Rich Features from RGB-D Images for Object Detection and Segmentation
Gupta, S., Girshick, R., Arbeláez, P., & Malik, J. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10584-0_23 · Cited by 1,528 · see citing works
Hypercolumns for object segmentation and fine-grained localization
Hariharan, B., Arbelaez, P., Girshick, R., & Malik, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298642 · Cited by 1,511 · see citing works
Joint Training of a Convolutional Network and a Graphical Model for Human Pose EstimationPreprint
Tompson, J., Jain, A., LeCun, Y., & Bregler, C. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1406.2984 · Cited by 1,317 · see citing works
(2012) · neural information processing systems · Cited by 1,291 · see citing works
Part-Based R-CNNs for Fine-Grained Category Detection
Zhang, N., Donahue, J., Girshick, R., & Darrell, T. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10590-1_54 · Cited by 1,212 · see citing works
Sampling Strategies for Bag-of-Features Image Classification
Nowak, E., Jurie, F., & Triggs, B. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744085_38 · Cited by 927 · see citing works
Recurrent Convolutional Neural Networks for Scene Labeling
Pinheiro, P. O., & Collobert, R. (2014) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Cited by 621 · see citing works
$$N^4$$-Fields: Neural Network Nearest Neighbor Fields for Image Transforms
Ganin, Y., & Lempitsky, V. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16808-1_36 · Cited by 262 · see citing works
Toward automatic phenotyping of developing embryos from videos
Ning, F., Delhomme, D., LeCun, Y., Piano, F., Bottou, L., & Barbano, P. E. (2005) · IEEE Transactions on Image Processing · doi:10.1109/tip.2005.852470 · Cited by 260 · see citing works
Multi-Digit Recognition Using a Space Displacement Neural Network
Matan, O., Burges, C. J. C., LeCun, Y., & Denker, J. S. (1991) · Cited by 126 · see citing works
Postal Address Block Location Using a Convolutional Locator Network
Wolf, R., & Platt, J. C. (1993) · Cited by 32 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Fink, O., Wang, Q., Svensén, M., Dersin, P., Lee, W.-J., & Ducoffe, M. (2020) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2020.103678 · Cited by 549 · see citing works
A Compact Convolutional Neural Network for Surface Defect Inspection
Huang, Y., Qiu, C., Wang, X., Wang, S., & Yuan, K. (2020) · Sensors · doi:10.3390/s20071974 · Cited by 85 · see citing works
Fully Convolutional Networks for Surface Defect Inspection in Industrial Environment
Yu, Z., Wu, X., & Gu, X. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-68345-4_37 · Cited by 77 · see citing works
Automated Defect Detection and Decision-Support in Gas Turbine Blade Inspection
Aust, J., Shankland, S., Pons, D., Mukundan, R., & Mitrovic, A. (2021) · Aerospace · doi:10.3390/aerospace8020030 · Cited by 66 · see citing works
“Other research using CNN techniques have explored detection of cracking in wind turbine blades [46], cracking on the surfaces of compressor blades in jet engines [9] and detection of surface erosion on turbine blades in jet engines [47].”
BackgroundMethodDeep Neural Networks Analysis of Borescope Images
Svensen, M., Powrie, H. E. G., & Hardwick, D. S. (2018) · PHM Society European Conference · doi:10.36001/phme.2018.v4i1.401 · Cited by 17 · see citing works
- Authors
- Bian, X., Lim, S. N., & Zhou, N.
- Affiliations
- General Electric (United States) (US)
- ORCID
- Venue
- 2016 IEEE Winter Conference on Applications of Computer Vision (WACV)
- Publisher
- IEEE
- Published
- 2016-03
- Pages
- 1-8
- ISSN
- 2472-6737 (ISSN-L)
- OpenAlex
- W2404464147
- Cited by
- 72
- References
- 18
- Citations by year
- 2026: 3 · 2025: 4 · 2024: 4 · 2023: 6 · 2022: 6 · 2021: 12 · 2020: 16 · 2019: 12 · 2018: 5 · 2017: 4
- FWCI
- 2.43
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Winter Conference on Applications of Computer Vision (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
- Keywords
- image segmentation, industrial inspection, convolutional neural network architecture
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
