Research on a Surface Defect Detection Algorithm Based on MobileNet-SSD
Source abstract
Abstract
This paper aims to achieve real-time and accurate detection of surface defects by using a deep learning method. For this purpose, the Single Shot MultiBox Detector (SSD) network was adopted as the meta structure and combined with the base convolution neural network (CNN) MobileNet into the MobileNet-SSD. Then, a detection method for surface defects was proposed based on the MobileNet-SSD. Specifically, the structure of the SSD was optimized without sacrificing its accuracy, and the network structure and parameters were adjusted to streamline the detection model. The proposed method was applied to the detection of typical defects like breaches, dents, burrs and abrasions on the sealing surface of a container in the filling line. The results show that our method can automatically detect surface defects more accurately and rapidly than lightweight network methods and traditional machine learning methods. The research results shed new light on defect detection in actual industrial scenarios.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Advanced Neural Network Applications · Vehicle License Plate Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Key Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou University, Guiyang 550025, China
Funding
Natural Science Foundation in Guizhou Province；the major project of science and technology in Guizhou Province
References (38)
Show source-provided references
1. Uddin, M.T., and Uddiny, M.A. (2015, January 21–23). Human activity recognition from wearable sensors using extremely randomized trees. Proceedings of the International Conference on Electrical Engineering and Information Communication Technology, Dhaka, Bangladesh.10.1109/ICEEICT.2015.7307384 ↗
2. Human Activity Recognition via Recognized Body Parts of Human Depth Silhouettes for Residents Monitoring Services at Smart Home10.1177/1420326X12469714 ↗
3. Wearable sensor-based human activity recognition from environmental background sounds10.1007/s12652-012-0122-2 ↗
4. Jalal, A. (2008, January 12–13). Security Architecture for Third Generation (3G) using GMHS Cellular Network. Proceedings of the International Conference on Emerging Technologies, Islamabad, Pakistan.10.1109/ICET.2007.4516319 ↗
5. Shire, A.N., Khanapurkar, M.M., and Mundewadikar, R.S. (2012, January 18–20). Plain Ceramic Tiles Surface Defect Detection Using Image Processing. Proceedings of the International Conference on Emerging Trends in Engineering and Technology, Port Louis, Mauritius.10.1109/ICETET.2011.63 ↗
6. Shang, L., Yang, Q., Wang, J., Li, S., and Lei, W. (2018, January 11–14). Detection of rail surface defects based on CNN image recognition and classification. Proceedings of the International Conference on Advanced Communication Technology, Chuncheon-si, Korea.10.23919/ICACT.2018.8323641 ↗
7. Advanced Performance Achievement using Multi-Algorithmic Approach of Video Transcoder for Low Bitrate Wireless Communication
8. Deutschl, E., Gasser, C., Niel, A., and Werschonig, J. (2004, January 14–17). Defect detection on rail surfaces by a vision based system. Proceedings of the Intelligent Vehicles Symposium, Parma, Italy.
9. Yazdchi, M., Yazdi, M., and Mahyari, A.G. (2009, January 7–9). Steel Surface Defect Detection Using Texture Segmentation Based on Multifractal Dimension. Proceedings of the International Conference on Digital Image Processing, Bangkok, Thailand.10.1109/ICDIP.2009.68 ↗
10. Depth Images-based Human Detection, Tracking and Activity Recognition Using Spatiotemporal Features and Modified HMM10.5370/JEET.2016.11.6.1857 ↗
11. Global Security Using Human Face Understanding under Vision Ubiquitous Architecture System
12. Patil, K., Kulkarni, M., Sriraman, A., and Karande, S. (2017, January 18–21). Deep Learning Based Car Damage Classification. Proceedings of the IEEE International Conference on Machine Learning and Applications, Cancun, Mexico.10.1109/ICMLA.2017.0-179 ↗
13. Zhang, Z., Alonzo, R., and Athitsos, V. (2011, January 25). Experiments with computer vision methods for hand detection. Proceedings of the Petra 2011 International Conference on Pervasive Technologies Related to Assistive Environments, Crete, Greece.10.1145/2141622.2141648 ↗
14. Steel-surface defect detection using a switching-lighting scheme10.1364/AO.55.000047 ↗
15. Applied multiresolution analysis to infrared images for defects detection in materials10.1016/j.ndteint.2017.07.014 ↗
16. Wheel Defect Detection with Machine Learning10.1109/TITS.2017.2720721 ↗
17. Research on surface defect detection of ceramic ball based on fringe reflection
18. Automatic Surface Defect Detection for Mobile Phone Screen Glass Based on Machine Vision10.1016/j.asoc.2016.10.030 ↗
19. A Contrast Adjustment Thresholding Method for Surface Defect Detection Based on Mesoscopy10.1109/TII.2015.2417676 ↗
20. Deep learning10.1038/nature14539 ↗
21. Dermatologist-level classification of skin cancer with deep neural networks10.1038/nature21056 ↗
22. A survey on deep learning in medical image analysis10.1016/j.media.2017.07.005 ↗
23. Solar Cells Surface Defects Detection Based on Deep Learning
24. Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks10.1111/mice.12263 ↗
25. Han, K., Sun, M., Zhou, X., Zhang, G., Dang, H., and Liu, Z. (2017, January 6–9). A new method in wheel hub surface defect detection: Object detection algorithm based on deep learning. Proceedings of the International Conference on Advanced Mechatronic Systems, Xiamen, China.10.1109/ICAMechS.2017.8316494 ↗
26. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11–14). SSD: Single Shot MultiBox Detector. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
27. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (arXiv, 2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, arXiv.
28. Simonyan, K., and Zisserman, A. (arXiv, 2014). Very Deep Convolutional Networks for Large-Scale Image Recognition, arXiv.
29. Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks10.1109/LSP.2016.2603342 ↗
30. Faceness-Net: Face Detection through Deep Facial Part Responses10.1109/TPAMI.2017.2738644 ↗
31. Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., and Keutzer, K. (arXiv, 2016). SqueezeNet: AlexNet-level accuracy with 50 × fewer parameters and <0.5 MB model size, arXiv.
32. Hong, S., Roh, B., Kim, K.H., Cheon, Y., and Park, M. (arXiv, 2016). PVANet: Lightweight Deep Neural Networks for Real-time Object Detection, arXiv.
33. Hunt, M.A., Karnowski, T.P., Kiest, C., and Villalobos, L. (2000, January 12–14). Optimizing automatic defect classification feature and classifier performance for post. Proceedings of the 2000 IEEE/SEMI Advanced Semiconductor Manufacturing Conference and Workshop, Boston, MA, USA.
34. A depth video sensor-based life-logging human activity recognition system for elderly care in smart indoor environments10.3390/s140711735 ↗
35. Robust human activity recognition from depth video using spatiotemporal multi-fused features10.1016/j.patcog.2016.08.003 ↗
36. Jalal, A., Kamal, S., and Kim, D. (2015, January 28–30). Individual detection-tracking-recognition using depth activity images. Proceedings of the 2015 12th International Conference on IEEE Ubiquitous Robots and Ambient Intelligence (URAI), Goyang, Korea.10.1109/URAI.2015.7358903 ↗
37. Wu, H., Pan, W., Xiong, X., and Xu, S. (2014, January 28–30). Human activity recognition based on the combined svm&hmm. Proceedings of the 2014 IEEE International Conference on Information and Automation (ICIA), Hailar, China.10.1109/ICInfA.2014.6932656 ↗
38. Islam, M.A., Akhter, S., Mursalin, T.E., and Amin, M.A. (2006, January 3–6). A suitable neural network to detect textile defects. Proceedings of the International Conference on Neural Information Processing, Hong Kong, China.10.1007/11893257_48 ↗