Automated Surface Defect Inspection Based on Autoencoders and Fully Convolutional Neural Networks
Source abstract
Abstract
This study aims to develop a novel automated computer vision algorithm for quality inspection of surfaces with complex patterns. The proposed algorithm is based on both an autoencoder (AE) and a fully convolutional neural network (FCN). The AE is adopted for the self-generation of templates from test targets for defect detection. Because the templates are produced from the test targets, the position alignment issues for the matching operations between templates and test targets can be alleviated. The FCN is employed for the segmentation of a template into a number of coherent regions. Because the AE has the limitation that its capacities for the regeneration of each coherent region in the template may be different, the segmentation of the template by FCN is beneficial for allowing the inspection of each region to be independently carried out. In this way, more accurate detection results can be achieved. Experimental results reveal that the proposed algorithm has the advantages of simplicity for training data collection, high accuracy for defect detection, and high flexibility for online inspection. The proposed algorithm is therefore an effective alternative for the automated inspection in smart factories with a growing demand for the reliability for high quality production.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Surface Roughness and Optical Measurements · Infrastructure Maintenance and Monitoring
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei 117, Taiwan
Funding
Ministry of Science and Technology, Taiwan
References (28)
Show source-provided references
1. Szeliski, R. (2011). Computer Vision: Algorithms and Applications, Springer.10.1007/978-1-84882-935-0 ↗
2. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
3. Modeling the interactions among neighboring nanostructures for local feature characterization and defect detection10.1109/TASE.2012.2209417 ↗
4. A Generic Deep-Learning-Based Approach for Automated Surface Inspection10.1109/TCYB.2017.2668395 ↗
5. Steel surface defect detection using a new Haar–Weibull-Variance model in unsupervised manner10.1109/TIM.2017.2712838 ↗
6. Saliency-based defect detection in industrial images by using phase spectrum10.1109/TII.2014.2359416 ↗
7. A two-stage fault detection and isolation platform for industrial systems using residual evaluation10.1109/TIM.2016.2575179 ↗
8. Performance of machine learning algorithms for class-imbalanced process fault detection problems10.1109/TSM.2016.2602226 ↗
9. A high-efficiency fully convolutional networks for pixel-wise surface defect detection10.1109/ACCESS.2019.2894420 ↗
10. Perez, H., Tah, J.H.M., and Mosavi, A. (2019). Deep Learning for Detecting Building Defects Using Convolutional Neural Networks. Sensors, 19.10.20944/preprints201908.0068.v1 ↗
11. Machine vision-based defect detection in IC images using the partial information correlation coefficient10.1109/TSM.2013.2261566 ↗
12. Asymmetric correlation: A noise robust similarity measure for template matching10.1109/TIP.2013.2257811 ↗
13. A Simple Guidance Template-Based Defect Detection Method for Strip Steel Surfaces10.1109/TII.2018.2887145 ↗
14. Sakurada, M., and Yairi, T. (2014, January 2). Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction. Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis, Gold Coast, Queensland, Australia.10.1145/2689746.2689747 ↗
15. Youkachen, S., Ruchanurucks, M., Phatrapomnant, T., and Kaneko, H. (2019, January 25–27). Defect segmentation of hot-rolled steel strip surface by using convolutional auto-encoder and conventional image processing. Proceedings of the 2019 10th International Conference of Information and Communication Technology for Embedded Systems (IC-ICTES), Bangkok, Thailand.10.1109/ICTEmSys.2019.8695928 ↗
16. Multiscale Feature-Clustering-Based Fully Convolutional Autoencoder for Fast Accurate Visual Inspection of Texture Surface Defects10.1109/TASE.2018.2886031 ↗
17. Corso, J.J., and Hager, G.D. (2005, January 20–25). Coherent Regions for Concise and Stable Image Description. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, CA, USA.
18. Gould, S., Gao, T., and Koller, D. (2009, January 7–9). Region-Based Segmentation and Object Detection. Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS), Vancouver, Canada.
19. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully Convolutional Networks for Semantic Segmentation. Proceedings of the Computer Vision Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298965 ↗
20. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-Net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
21. Gagliano, S., Stella, G., and Bucolo, M. (2020). Real-Time Detection of Slug Velocity in Microchannels. Micromachines, 11.10.3390/mi11030241 ↗
22. Teng, Y., and Choromanska, A. (2019). Invertible Autoencoder for Domain Adaptation. Computation, 70.10.3390/computation7020020 ↗
23. Vasudevan, A., Anderson, A., and Gregg, D. (2017, January 10–12). Parallel Multi Channel convolution using General Matrix Multiplication. Proceedings of the IEEE International Conference Application-Specific Systems, Architectures and Processors, Seattle, WA, USA.10.1109/ASAP.2017.7995254 ↗
24. Bengio, Y., Yao, L., Alain, G., and Vincent, P. (2013). Generalized denoising auto-encoders as generative models. arXiv.
25. A Survey on Deep Learning Empowered IoT Applications10.1109/ACCESS.2019.2958962 ↗
26. Yun, J.P., Shin, W.C., Koo, G., Kim, M.S., Lee, C., and Lee, S.J. (2020). Automated defect inspection system for metal surfaces based on deeplearning and data augmentation. J. Manuf. Syst., 317–324.10.1016/j.jmsy.2020.03.009 ↗
27. Chollet, F. (2021, April 10). Keras. [Online]. Available online: http://github.com/fchollet/keras.
28. An introduction to ROC analysis10.1016/j.patrec.2005.10.010 ↗