A Data Augmentation Method for Deep Learning Based on Multi-Degree of Freedom (DOF) Automatic Image Acquisition
Source abstract
Abstract
Deep learning technology is outstanding in visual inspection. However, in actual industrial production, the use of deep learning technology for visual inspection requires a large number of training data with different acquisition scenarios. At present, the acquisition of such datasets is very time-consuming and labor-intensive, which limits the further development of deep learning in industrial production. To solve the problem of image data acquisition difficulty in industrial production with deep learning, this paper proposes a data augmentation method for deep learning based on multi-degree of freedom (DOF) automatic image acquisition and designs a multi-DOF automatic image acquisition system for deep learning. By designing random acquisition angles and random illumination conditions, different acquisition scenes in actual production are simulated. By optimizing the image acquisition path, a large number of accurate data can be obtained in a short time. In order to verify the performance of the dataset collected by the system, the fabric is selected as the research object after the system is built, and the dataset comparison experiment is carried out. The dataset comparison experiment confirms that the dataset obtained by the system is rich and close to the real application environment, which solves the problem of dataset insufficient in the application process of deep learning to a certain extent.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Image and Object Detection Techniques · Surface Roughness and Optical Measurements
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
State Key Laboratory of Precision Measuring Technology & Instrumuments, Centre of MicroNano Manufacturing Technology, Tianjin University, Tianjin 300072, China
References (28)
Show source-provided references
1. Deep learning10.1038/nature14539 ↗
2. Kim, K.-I., and Lee, K.M. (2020). Convolutional Neural Network-Based Gear Type Identification from Automatic Identification System Trajectory Data. Appl. Sci., 10.10.3390/app10114010 ↗
3. Li, H., Xu, H., Tian, X., Wang, Y., Cai, H., Cui, K., and Chen, X. (2020). Bridge Crack Detection Based on SSENets. Appl. Sci., 10.10.3390/app10124230 ↗
4. Ochoa-Ruiz, G., Angulo-Murillo, A.A., Ochoa-Zezzatti, A., Aguilar-Lobo, L.M., Vega-Fernández, J.A., and Natraj, S. (2020). An Asphalt Damage Dataset and Detection System Based on RetinaNet for Road Conditions Assessment. Appl. Sci., 10.10.3390/app10113974 ↗
5. Ruan, S., Tang, C., Xu, Z., Jin, Z., Chen, S., Wen, H., Liu, H., and Tang, D. (2020). Multi-Pose Face Recognition Based on Deep Learning in Unconstrained Scene. Appl. Sci., 10.10.3390/app10134669 ↗
6. Shibata, T., Teramoto, A., Yamada, H., Ohmiya, N., Saito, K., and Fujita, H. (2020). Automated Detection and Segmentation of Early Gastric Cancer from Endoscopic Images Using Mask R-CNN. Appl. Sci., 10.10.3390/app10113842 ↗
7. Yan, K., Chang, L., Andrianakis, M., Tornari, V., and Yu, Y. (2020). Deep Learning-Based Wrapped Phase Denoising Method for Application in Digital Holographic Speckle Pattern Interferometry. Appl. Sci., 10.10.3390/app10114044 ↗
8. In-Bed Pose Estimation: Deep Learning with Shallow Dataset10.1109/JTEHM.2019.2892970 ↗
9. Automatic Large-Scale Data Acquisition via Crowdsourcing for Crosswalk Classification: A Deep Learning Approach10.1016/j.cag.2017.08.004 ↗
10. Berriel, R.F., Torres, L.T., Cardoso, V.B., Guidolini, R., and Oliveira-Santos, T. (2018, January 8–13). Heading Direction Estimation Using Deep Learning with Automatic Large-scale Data Acquisition. Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil.10.1109/IJCNN.2018.8489154 ↗
11. Machine Vision Detection Method for Surface Defects of Automobile Stamping Parts
12. Automatic Automobile Parts Recognition and Classification System Based on Machine Vision
13. Tian-Jian, L. (2012). The Detection System of Automobile Spare Parts Based on Robot Vision. J. Jiamusi Univ. Nat. Sci. Ed., 718–722.
14. Unsupervised fabric defect detection based on a deep convolutional generative adversarial network10.1177/0040517519862880 ↗
15. Jing, J., Wang, Z., Rätsch, M., and Zhang, H. (2020). Mobile-Unet: An efficient convolutional neural network for fabric defect detection. Text. Res. J., 0040517520928604.
16. Computer-vision-based fabric defect detection: A survey10.1109/TIE.1930.896476 ↗
17. Automated fabric defect detection—A review10.1016/j.imavis.2011.02.002 ↗
18. Mikołajczyk, A., and Grochowski, M. (2018, January 9–12). Data augmentation for improving deep learning in image classification problem. Proceedings of the 2018 International Interdisciplinary Ph.D. Workshop (IIPhDW), Swinoujście, Poland.10.1109/IIPHDW.2018.8388338 ↗
19. A survey on image data augmentation for deep learning10.1186/s40537-019-0197-0 ↗
20. (2020, June 01). GitHub. Available online: https://github.com/aleju/imgaug.
21. Zhong, Z., Zheng, L., Kang, G., Li, S., and Yang, Y. (2020). Random Erasing Data Augmentation. Proc. AAAI, 13001–13008.10.1609/aaai.v34i07.7000 ↗
22. Inoue, H. (2018). Data augmentation by pairing samples for images classification. arXiv.
23. Zhang, H., Cisse, M., Dauphin, Y.N., and Lopez-Paz, D. (2017). Mixup: Beyond Empirical Risk Minimization. arXiv.10.1007/978-1-4899-7687-1_79 ↗
24. Doersch, C. (2016). Tutorial on variational autoencoders. arXiv.
25. Generative adversarial nets
26. Zhu, X., Liu, Y., Qin, Z., and Li, J. (2017). Data augmentation in emotion classification using generative adversarial networks. arXiv.10.1007/978-3-319-93040-4_28 ↗
27. Solution of a large-scale traveling-salesman problem
28. He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗