A Hard Voting Policy-Driven Deep Learning Architectural Ensemble Strategy for Industrial Products Defect Recognition and Classification
Abstract
:1. Introduction
2. Related Works
3. Theoretical Background
3.1. Deep Learning Architectures
3.2. Deep Learning Model Ensemble and Voting Policy Strategy
4. Materials and Methods
4.1. Datasets
4.2. Experimental Procedure
5. Results
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
- https://www.kaggle.com/datasets/satishpaladi11/mechanic-component-images-normal-defected, accessed on 12 August 2022.
- PCB defect dataset [53].
- https://www.kaggle.com/datasets/ravirajsinh45/real-life-industrial-dataset-of-casting-product, accessed on 12 August 2022.
Conflicts of Interest
References
- Wilson, A.; Ben-Tal, G.; Heather, J.; Oliver, R.; Valkenburg, R. Calibrating cameras in an industrial produce inspection system. Comput. Electron. Agric. 2017, 140, 386–396. [Google Scholar] [CrossRef]
- Dighvijay, G.; Vaishnav, D.S.; Mohan, R. A Faster R-CNN implementation of presence inspection for parts on industrial produce. In Proceedings of the 2021 Emerging Trends in Industry 4.0 (ETI 4.0), Raigarh, India, 19–21 May 2021; pp. 1–4. [Google Scholar]
- Stojanovic, L.; Dinic, M.; Stojanovic, N.; Stojadinovic, A. Big-data-driven anomaly detection in industry (4.0): An approach and a case study. In Proceedings of the 2016 IEEE International Conference on Big Data (Big Data), Washington, DC, USA, 5–8 December 2016; pp. 1647–1652. [Google Scholar]
- Villalba-Diez, J.; Schmidt, D.; Gevers, R.; Ordieres-Meré, J.; Buchwitz, M.; Wellbrock, W. Deep learning for industrial computer vision quality control in the printing industry 4.0. Sensors 2019, 19, 3987. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- LeCun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature 2015, 521, 436–444. [Google Scholar] [CrossRef] [PubMed]
- Zhao, Z.-Q.; Zheng, P.; Xu, S.-T.; Wu, X. Object detection with deep learning: A review. IEEE Trans. Neural Netw. Learn. Syst. 2019, 30, 3212–3232. [Google Scholar] [CrossRef] [Green Version]
- Wu, H.; Liu, Q.; Liu, X. A review on deep learning approaches to image classification and object segmentation. Comput. Mater. Contin 2019, 60, 575–597. [Google Scholar] [CrossRef] [Green Version]
- Li, S.; Song, W.; Fang, L.; Chen, Y.; Ghamisi, P.; Benediktsson, J.A. Deep learning for hyperspectral image classification: An overview. IEEE Trans. Geosci. Remote Sens. 2019, 57, 6690–6709. [Google Scholar] [CrossRef] [Green Version]
- Stephen, O.; Maduh, U.J.; Sain, M. A Machine Learning Method for Detection of Surface Defects on Ceramic Tiles Using Convolutional Neural Networks. Electronics 2021, 11, 55. [Google Scholar] [CrossRef]
- Kamath, U.; Liu, J.; Whitaker, J. Deep Learning for NLP and Speech Recognition; Springer: Berlin/Heidelberg, Germany, 2019; Volume 84. [Google Scholar]
- Chen, W.; Gao, Y.; Gao, L.; Li, X. A new ensemble approach based on deep convolutional neural networks for steel surface defect classification. Procedia CIRP 2018, 72, 1069–1072. [Google Scholar] [CrossRef]
- Ganaie, M.; Hu, M. Ensemble deep learning: A review. arXiv 2021, arXiv:2104.02395. [Google Scholar] [CrossRef]
- Zhou, T.; Lu, H.; Yang, Z.; Qiu, S.; Huo, B.; Dong, Y. The ensemble deep learning model for novel COVID-19 on CT images. Appl. Soft Comput. 2021, 98, 106885. [Google Scholar] [CrossRef]
- Wang, J.; Fu, P.; Gao, R.X. Machine vision intelligence for product defect inspection based on deep learning and Hough transform. J. Manuf. Syst. 2019, 51, 52–60. [Google Scholar] [CrossRef]
- Jiang, J.; Wong, W. Fundamentals of common computer vision techniques for textile quality control. In Applications of Computer Vision in Fashion and Textiles; Elsevier: Amsterdam, The Netherlands, 2018; pp. 3–15. [Google Scholar]
- Jeyaraj, P.R.; Nadar, E.R.S. Computer vision for automatic detection and classification of fabric defect employing deep learning algorithm. Int. J. Cloth. Sci. Technol. 2019, 31, 510–521. [Google Scholar] [CrossRef]
- Liong, S.-T.; Zheng, D.; Huang, Y.-C.; Gan, Y.S. Leather defect classification and segmentation using deep learning architecture. Int. J. Comput. Integr. Manuf. 2020, 33, 1105–1117. [Google Scholar] [CrossRef]
- Liqun, W.; Jiansheng, W.; Dingjin, W. Research on vehicle parts defect detection based on deep learning. In Journal of Physics: Conference Series; IOP Publishing: Bristol, UK, 2020; p. 012004. [Google Scholar]
- Qu, Z.; Shen, J.; Li, R.; Liu, J.; Guan, Q. Partsnet: A unified deep network for automotive engine precision parts defect detection. In Proceedings of the Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence, Shenzhen, China, 8–10 December 2018; pp. 594–599.
- Zhou, H.; Zhuang, Z.; Liu, Y.; Liu, Y.; Zhang, X. Defect classification of green plums based on deep learning. Sensors 2020, 20, 6993. [Google Scholar] [CrossRef]
- Di, H.; Ke, X.; Peng, Z.; Dongdong, Z. Surface defect classification of steels with a new semi-supervised learning method. Opt. Lasers Eng. 2019, 117, 40–48. [Google Scholar] [CrossRef]
- Liu, Y.; Yuan, Y.; Balta, C.; Liu, J. A light-weight deep-learning model with multi-scale features for steel surface defect classification. Materials 2020, 13, 4629. [Google Scholar] [CrossRef]
- Ajmi, C.; Zapata, J.; Martínez-Álvarez, J.J.; Doménech, G.; Ruiz, R. Using deep learning for defect classification on a small weld X-ray image dataset. J. Nondestruct. Eval. 2020, 39, 68. [Google Scholar] [CrossRef]
- Iandola, F.N.; Han, S.; Moskewicz, M.W.; Ashraf, K.; Dally, W.J.; Keutzer, K. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size. arXiv 2016, arXiv:1602.07360. [Google Scholar]
- Sandler, M.; Howard, A.; Zhu, M.; Zhmoginov, A.; Chen, L.-C. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–22 June 2018; pp. 4510–4520.
- Liu, Y.; Yuan, Y.; Liu, J. Deep learning model for imbalanced multi-label surface defect classification. Meas. Sci. Technol. 2021, 33, 035601. [Google Scholar] [CrossRef]
- Zhao, B.; Dai, M.; Li, P.; Xue, R.; Ma, X. Defect detection method for electric multiple units key components based on deep learning. IEEE Access 2020, 8, 136808–136818. [Google Scholar] [CrossRef]
- Alturki, A.; Gable, G.G.; Bandara, W. A design science research roadmap. In International Conference on Design Science Research in Information Systems; Springer: Berlin/Heidelberg, Germany, 2011; pp. 107–123. [Google Scholar]
- Chaudhary, V.; Dave, I.R.; Upla, K.P. Automatic visual inspection of printed circuit board for defect detection and classification. In Proceedings of the 2017 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), Chennai, India, 22–24 March 2017; pp. 732–737. [Google Scholar]
- Zitova, B.; Flusser, J. Image registration methods: A survey. Image Vis. Comput. 2003, 21, 977–1000. [Google Scholar] [CrossRef]
- Bhattacharyya, S. A brief survey of color image preprocessing and segmentation techniques. J. Pattern Recognit. Res. 2011, 1, 120–129. [Google Scholar] [CrossRef]
- Cheng, H.-D.; Jiang, X.H.; Sun, Y.; Wang, J. Color image segmentation: Advances and prospects. Pattern Recognit. 2001, 34, 2259–2281. [Google Scholar] [CrossRef]
- Kim, J.; Ko, J.; Choi, H.; Kim, H. Printed circuit board defect detection using deep learning via a skip-connected convolutional autoencoder. Sensors 2021, 21, 4968. [Google Scholar] [CrossRef] [PubMed]
- Adibhatla, V.A.; Chih, H.-C.; Hsu, C.-C.; Cheng, J.; Abbod, M.F.; Shieh, J.-S. Defect detection in printed circuit boards using you-only-look-once convolutional neural networks. Electronics 2020, 9, 1547. [Google Scholar] [CrossRef]
- Bhattacharya, A.; Cloutier, S.G. End-to-end deep learning framework for printed circuit board manufacturing defect classification. Sci. Rep. 2022, 12, 12559. [Google Scholar] [CrossRef] [PubMed]
- Khalilian, S.; Hallaj, Y.; Balouchestani, A.; Karshenas, H.; Mohammadi, A. Pcb defect detection using denoising convolutional autoencoders. In Proceedings of the 2020 International Conference on Machine Vision and Image Processing (MVIP), Qom, Iran, 18–20 February 2020; pp. 1–5. [Google Scholar]
- Tang, S.; Zhu, Y.; Yuan, S. An adaptive deep learning model towards fault diagnosis of hydraulic piston pump using pressure signal. Eng. Fail. Anal. 2022, 138, 106300. [Google Scholar] [CrossRef]
- Wang, S.; Xiang, J.; Zhong, Y.; Tang, H. A data indicator-based deep belief networks to detect multiple faults in axial piston pumps. Mech. Syst. Signal Process. 2018, 112, 154–170. [Google Scholar] [CrossRef]
- Zhu, Y.; Li, G.; Wang, R.; Tang, S.; Su, H.; Cao, K. Intelligent fault diagnosis of hydraulic piston pump based on wavelet analysis and improved alexnet. Sensors 2021, 21, 549. [Google Scholar] [CrossRef]
- Tang, S.; Zhu, Y.; Yuan, S.; Li, G. Intelligent diagnosis towards hydraulic axial piston pump using a novel integrated CNN model. Sensors 2020, 20, 7152. [Google Scholar] [CrossRef]
- Lin, J.; Yao, Y.; Ma, L.; Wang, Y. Detection of a casting defect tracked by deep convolution neural network. Int. J. Adv. Manuf. Technol. 2018, 97, 573–581. [Google Scholar] [CrossRef]
- Duan, L.; Yang, K.; Ruan, L. Research on automatic recognition of casting defects based on deep learning. IEEE Access 2020, 9, 12209–12216. [Google Scholar] [CrossRef]
- Ferguson, M.; Ak, R.; Lee, Y.-T.T.; Law, K.H. Automatic localization of casting defects with convolutional neural networks. In Proceedings of the 2017 IEEE International Conference on Big Data (Big Data), Boston, MA, USA, 11–14 December 2017; pp. 1726–1735. [Google Scholar]
- Mery, D. Aluminum casting inspection using deep learning: A method based on convolutional neural networks. J. Nondestruct. Eval. 2020, 39, 12. [Google Scholar] [CrossRef]
- Nikolić, F.; Štajduhar, I.; Čanađija, M. Casting Defects Detection in Aluminum Alloys Using Deep Learning: A Classification Approach. Int. J. Met. 2022, 1–13. [Google Scholar] [CrossRef]
- Wu, B.; Zhou, J.; Yang, H.; Huang, Z.; Ji, X.; Peng, D.; Yin, Y.; Shen, X. An ameliorated deep dense convolutional neural network for accurate recognition of casting defects in X-ray images. Knowl. Based Syst. 2021, 226, 107096. [Google Scholar] [CrossRef]
- Murphy, J. An Overview of Convolutional Neural Network Architectures for Deep Learning; Microway Inc.: Plymouth, MA, USA, 2016; pp. 1–22. Available online: https://www.semanticscholar.org/paper/An-Overview-of-Convolutional-Neural-Network-for-Murphy/64db333bb1b830f937b47d786921af4a6c2b3233#related-papers (accessed on 12 August 2022).
- Szegedy, C.; Vanhoucke, V.; Ioffe, S.; Shlens, J.; Wojna, Z. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 2818–2826. [Google Scholar]
- Chollet, F. Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 1251–1258. [Google Scholar]
- Huang, G.; Liu, Z.; Van Der Maaten, L.; Weinberger, K.Q. Densely connected convolutional networks. In Proceedings of the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 4700–4708. [Google Scholar]
- Howard, A.G.; Zhu, M.; Chen, B.; Kalenichenko, D.; Wang, W.; Weyand, T.; Andreetto, M.; Adam, H. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv 2017, arXiv:1704.04861. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778. [Google Scholar]
- Tang, S.; He, F.; Huang, X.; Yang, J. Online PCB defect detector on a new PCB defect dataset. arXiv 2019, arXiv:1902.06197. [Google Scholar]
- Paladi, S. Mechanic Component Images (Normal/Defected) Dataset. Available online: https://www.kaggle.com/datasets/satishpaladi11/mechanic-component-images-normal-defected (accessed on 12 August 2022).
- Dabhi, R. Casting Product Image Data for Quality Inspection. Available online: https://www.kaggle.com/datasets/ravirajsinh45/real-life-industrial-dataset-of-casting-product (accessed on 12 August 2022).
Layer Type | Output Shape | Parameters |
---|---|---|
Conv2D | None, 45, 45, 32 | 320 |
MaxPooling2D | None, 22, 22, 32 | 0 |
Conv2D | None, 11, 11, 64 | 18,496 |
MaxPooling2D | None, 5, 5, 64 | 0 |
Flatten | None, 1600 | 0 |
Dense | None, 128 | 204,928 |
Dense | None, 1 | 129 |
Sensitivity | Specificity | Cohen_Kappa | Test Accuracy | Test Loss | Weights | |
---|---|---|---|---|---|---|
CNN | 8.50 × 10−1 | 9.60 × 10−1 | 8.22 × 10−1 | 9.29 × 10−1 | 2.66 × 10−1 | 5 MB |
Inceptionv3 | 9.00 × 10−1 | 9.60 × 10−1 | 8.60 × 10−1 | 9.43 × 10−1 | 3.28 × 10−1 | 20 MB |
Xception | 0.00 | 1.00 | 0.00 | 7.14 × 10−1 | 5.04 × 10−1 | 18 MB |
MobileNet | 9.00 × 10−1 | 7.20 × 10−1 | 5.25 × 10−1 | 7.71 × 10−1 | 1.84 | 8 MB |
ResNet50 | 1.00 | 0.00 | 0.00 | 2.86 × 10−1 | 3.76 | 21 MB |
Den_Voted | 9.00 × 10−1 | 1.00 | 9.28 × 10−1 | 9.71 × 10−1 | 5.24 × 10−2 | 12 MB |
Sensitivity | Specificity | Cohen_Kappa | Test Accuracy | Test Loss | Weights | |
---|---|---|---|---|---|---|
CNN | 2.89 × 10−1 | 1.78 × 10−1 | −5.33 × 10−1 | 2.33 × 10−1 | 1.43 | 8 MB |
Inceptionv3 | 9.89 × 10−1 | 9.56 × 10−1 | 9.44 × 10−1 | 9.72 × 10−1 | 1.34 × 10−1 | 22 MB |
Xception | 9.78 × 10−1 | 9.78 × 10−1 | 9.56 × 10−1 | 9.78 × 10−1 | 6.24 × 10−2 | 20 MB |
MobileNet | 1.00 | 8.89 × 10−1 | 8.89 × 10−1 | 9.44 × 10−1 | 1.45 × 10−1 | 11 MB |
ResNet50 | 5.56 × 10−2 | 1.00 | 5.56 × 10−2 | 5.28 × 10−1 | 7.15 | 25 MB |
Den_Voted | 9.89 × 10−1 | 1.00 | 9.89 × 10−1 | 9.94 × 10−1 | 3.80 × 10−2 | 18 MB |
Sensitivity | Specificity | Cohen_Kappa | Test Accuracy | Test Loss | Weights | |
---|---|---|---|---|---|---|
Inceptionv3 | 1.00 | 9.96 × 10−1 | 9.94 × 10−1 | 9.97 × 10−1 | 7.55 × 10−3 | 28 MB |
Xception | 9.96 × 10−1 | 9.93 × 10−1 | 9.88 × 10−1 | 9.94 × 10−1 | 1.28 × 10−2 | 23 MB |
Densenet | 9.96 × 10−1 | 9.96 × 10−1 | 9.91 × 10−1 | 9.96 × 10−1 | 1.61 × 10−2 | 24 MB |
MobileNet | 9.96 × 10−1 | 9.96 × 10−1 | 9.91 × 10−1 | 9.96 × 10−1 | 1.33 × 10−2 | 13 MB |
ResNet50 | 9.89 × 10−1 | 9.96 × 10−1 | 9.85 × 10−1 | 9.93 × 10−1 | 1.91 × 10−2 | 31 MB |
CNN_voted | 9.96 × 10−1 | 1.00 | 9.97 × 10−1 | 9.99 × 10−1 | 6.44 × 10−3 | 15 MB |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Stephen, O.; Madanian, S.; Nguyen, M. A Hard Voting Policy-Driven Deep Learning Architectural Ensemble Strategy for Industrial Products Defect Recognition and Classification. Sensors 2022, 22, 7846. https://doi.org/10.3390/s22207846
Stephen O, Madanian S, Nguyen M. A Hard Voting Policy-Driven Deep Learning Architectural Ensemble Strategy for Industrial Products Defect Recognition and Classification. Sensors. 2022; 22(20):7846. https://doi.org/10.3390/s22207846
Chicago/Turabian StyleStephen, Okeke, Samaneh Madanian, and Minh Nguyen. 2022. "A Hard Voting Policy-Driven Deep Learning Architectural Ensemble Strategy for Industrial Products Defect Recognition and Classification" Sensors 22, no. 20: 7846. https://doi.org/10.3390/s22207846
APA StyleStephen, O., Madanian, S., & Nguyen, M. (2022). A Hard Voting Policy-Driven Deep Learning Architectural Ensemble Strategy for Industrial Products Defect Recognition and Classification. Sensors, 22(20), 7846. https://doi.org/10.3390/s22207846