Automatic Metallic Surface Defect Detection using ShuffleDefectNet
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Steel production requires high-quality surfaces with minimal defects. Therefore, the detection algorithms for the surface defects of steel strip should have good generalization performance. To meet the growing demand for high-quality products, the use of intelligent visual inspection systems is becoming essential in production lines. In this paper, we proposed a ShuffleDefectNet defect detection system based on deep learning. The proposed defect detection system exceeds state-of-the-art performance for defect detection on the Northeastern University (NEU) dataset obtaining a mean average accuracy of 99.75%. We train the best performing detection with different amounts of training data and observe the performance of detection. We notice that accuracy and speed improve significantly when use the overall architecture of ShuffleDefectNet.
Abstract
Steel production requires high-quality surfaces with minimal defects. Therefore, the detection algorithms for the surface defects of steel strip should have good generalization performance. To meet the growing demand for high-quality products, the use of intelligent visual inspection systems is becoming essential in production lines. In this paper, we proposed a ShuffleDefectNet defect detection system based on deep learning. The proposed defect detection system exceeds state-of-the-art performance for defect detection on the Northeastern University (NEU) dataset obtaining a mean average accuracy of 99.75%. We train the best performing detection with different amounts of training data and observe the performance of detection. We notice that accuracy and speed improve significantly when use the overall architecture of ShuffleDefectNet.
참고문헌 (27)
- R. Rajkolhe, "Defects, causes and their remediesin casting process: A review", 2(3), pp.375~383
- X. Li, "Improving automatic detection of defects in castings by applying wavelet technique", 53(6), pp.1927~1934
- S. Ghorai, "Automatic defect detection on hot-rolled flat steel products", 62(3), pp.612~621
- LeCun, Y., "Deep learning", nature, 521(7553), pp.436~ (2015)
- Ningning Ma, "ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design", ~ (2018)
- Sandler, M., "L.C.:Inverted residuals and linear bottlenecks: Mobile networks for classification, detection, and segmentation", arXiv preprint arXiv:1801.04381, ~ (2018)
- Zhang, X., "Shufflenet: An extremely efficient convolutional neural network for mobile devices", arXiv preprint arXiv:1707.01083, ~ (2017)
- Chollet, F., "Xception: Deep learning with depthwise separable convolutions", arXiv preprint, ~ (2016)
- Ciresan, D., "Multi-column deep neural networks for im-age classification", Proc. of Conference on Computer Vision and Pattern Recognition (CVPR), pp.3642~3649 (2012)
- Arel, I., "Deep machine learning - a new frontier inartificial intelligence research", IEEE Computational Intelligence Magazine, 5(4), pp.13~18 (2010)
- Simard, P.Y., "Best practices for convolutional neural networks applied to visual document analysis", Proc. of International Conference on Document Analysis and Recognition (ICDAR), pp.958~963 (2003)
- Coates, A., "An analysis of single-layer networks in unsupervised feature learning", Proc. of International Conference on Artificial intelligence and statistics (AISTATS) (2011)
- Soukup, D., "Convolutional neural networks for steel surface defect detection from photometric stereo images", Advances in Visual Computing, 8887, pp.668~677 (2014)
- Ke, W., "Banknote Image Defect Recognition Method Based on Convolution Neural Network", International Journal of Security and Its Applications, 10(6), pp.269~280 (2016)
- Faghih-Roohi, S., "Deep convolutional neural networks for detection of rail surface defects", 2016 International Joint Conference on Neural Networks (IJCNN), pp.2584~2589 (2016)
- 박제강, "Machine Learning-Based Imaging System for Surface Defect Inspection", International Journal of Precision Engineering and Manufacturing-Green Technology, 3(3), pp.303~310 (2016), 한국정밀공학회
- Weimer, D., "Design of deep convolutional neural network architectures for automated feature extraction in industrial inspection", CIRP Annals - Manufacturing Technology, 65(1), pp.417~420 (2016)
- K. Song, "A noise-robust method based on completed local binary patterns for hot-rolled steel strip surface defects", Appl. Surface Sci, 285, pp.858~864 (2013)
- Sandler, M., "Inverted residuals and linear bottlenecks: Mobile networks for classification, detection, and segmentation", arXiv preprint arXiv:1801.04381, ~ (2018)
- A. Krizhevsky, "Imagenet classification with deep convolutional neural networks", Advances in neural information processing systems, pp.1097~1105 (2012)
- S. Xie, "Aggregated residual transformations for deep neural networks", Computer Vision and Pattern Recognition (CVPR), 2017 IEEE Conference on, pp.5987~5995 (2017), IEEE
- Yu He, "An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical Features", IEEE Transactions on Instrumentation and Measurement, 69(4), pp.1493~1504 (2020), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- K. Song, "A noise-robust method based on completed local binary patterns for hot-rolled steel strip surface defects", Appl. Surface Sci, 285, pp.858~864 (2013)
- M. Xiao, "An evolutionary classifier for steel surface defects with a small sample set", EURASIP J. Image Vid. Process, 2017(1), pp.48~61 (2017)
- P. Chen, "Is over feat useful for image-based surface defect classification tasks?", Proc. IEEE Int. Conf. Image Process. (ICIP), pp.749~753 (2016)
- R. Ren, "A generic deep-learning-based approach for automated surface inspection", IEEE Trans. Cybern, 48(3), pp.929~940 (2018)
- Y. Lecun, "Deep learning", Nature, 521(7553), pp.436~444 (2015)