|
|
基于宽度学习的图像重建与缺陷检测方法
|
Abstract:
针对在训练中缺乏足量的缺陷样本会导致有监督的深度学习检测方法难以展开，并且常见的无监督缺陷检测方法面临着精度不足，效率低等问题。我们提出了一种基于宽度学习的图像重建与缺陷检测方法，该方法基于宽度学习系统改进，使其具有重构完整图像的能力，通过将测试图像与重构图像进行对比，确定测试图像中的缺陷。实验结果表明，该方法具有较好的重构精度，在BTAD数据集具有更好的效果。该模型的平均训练时间在325 s左右，运行速度达到60帧/s，优于常见的深度学习检测方法，基本能够满足实时检测的需求。
The lack of sufficient defect samples in training will make it difficult to develop supervised deep learning detection methods, and common unsupervised defect detection methods face problems such as insufficient accuracy and low efficiency. We propose an image reconstruction and defect detection method based on broad learning, which improves the broad learning system to make it achieves the ability to reconstruct the complete image, and determine the defects in the test image by comparing it with the reconstructed image. The experimental results show that the proposed method has good reconstruction accuracy and better effect in BTAD dataset. The average training time of the model is about 325 s, and the running speed reaches 60 frames per second, which is better than common deep learning detection methods and can basically meet the needs of real-time detection.
| [1] | Wang, C.D. and Lai, J.H. (2013) Position Regularized Support Vector Domain Description. Pattern Recognition, 46, 875-884. https://doi.org/10.1016/j.patcog.2012.09.018 |
| [2] | 郭龙源, 段厚裕, 周武威, 等. 基于Mask R-CNN的磁瓦表面缺陷检测算法[J]. 计算机集成制造系统, 2022, 28(5): 1393. |
| [3] | Cheng, Y. and Wang, S. (2022) Im-provements to YOLOv4 for Steel Surface Defect Detection. 2022 5th International Conference on Intelligent Autono-mous Systems (ICoIAS) IEEE, Dalian, 23-25 September 2022, 48-53.
https://doi.org/10.1109/ICoIAS56028.2022.9931299 |
| [4] | 周新龙, 张宏伟, 吴燕子, 等. 基于ContrastGAN的色织物缺陷检测[J]. 棉纺织技术, 2022, 50(11): 1-8. |
| [5] | 张宏伟, 谭全露, 陆帅, 等. U型去噪卷积自编码器色织衬衫裁片缺陷检测[J]. 西安电子科技大学学报, 2021, 48(3): 123-130. |
| [6] | Youkachen, S., Ruchanurucks, M., Phatrapornnant, T. and Kaneko, H. (2019) Defect Segmentation of Hot-Rolled Steel Strip Surface by Using Convolu-tional Auto-Encoder and Conventional Image Processing. 2019 10th International Conference of Information and Com-munication Technology for Embedded Systems (IC-ICTES), Bangkok, 25-27 March 2019, 1-5. https://doi.org/10.1109/ICTEmSys.2019.8695928 |
| [7] | Collin, A.S. and De Vleeschouwer, C. (2021) Improved Anomaly Detection by Training an Autoencoder with Skip Connections on Images Corrupted with Stain-Shaped Noise. 2020 25th International Conference on Pattern Recognition (ICPR) IEEE, Milan, 10-15 January 2021, 7915-7922. https://doi.org/10.1109/ICPR48806.2021.9412842 |
| [8] | Venkataramanan, S., Peng, K.C., Singh, R.V., et al. (2020) Attention Guided Anomaly Localization in Images. Computer Vision—ECCV 2020: 16th European Conference, Glas-gow, 23-28 August 2020, 485-503.
https://doi.org/10.1007/978-3-030-58520-4_29 |
| [9] | Schlegl, T., Seeb？ck, P., Waldstein, S.M., et al. (2017) Unsu-pervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery. Information Processing in Medical Imaging: 25th International Conference, IPMI 2017, Boone, 25-30 June 2017, 146-157. https://doi.org/10.1007/978-3-319-59050-9_12 |
| [10] | Lai, Y.T.K. and Hu, J.S. (2018) A Texture Generation Ap-proach for Detection of Novel Surface Defects. 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC) IEEE, Miyazaki, 7-10 October 2018, 4357-4362.
https://doi.org/10.1109/SMC.2018.00736 |
| [11] | Ruff, L., Vandermeulen, R., Goernitz, N., et al. (2018) Deep One-Class Classification. International Conference on Machine Learning PMLR, Stockholm, 10-15 July 2018, 4393-4402. |
| [12] | Yi, J. and Yoon, S. (2020) Patch SVDD: Patch-Level SVDD for Anomaly Detection and Segmenta-tion. 15th Asian Conference on Computer Vision, Kyoto, 30 November-4 December 2020, 375-390. |
| [13] | Chen, C.L.P. and Liu, Z. (2017) Broad Learning System: An Effective and Efficient Incremental Learning System without the Need for Deep Architecture. IEEE Transactions on Neural Networks and Learning Systems, 29, 10-24.
https://doi.org/10.1109/TNNLS.2017.2716952 |
| [14] | Doersch, C., Gupta, A. and Efros, A.A. (2015) Unsupervised Visual Representation Learning by Context Prediction. Proceedings of the IEEE International Conference on Computer Vision, Santiago, 7-13 December 2015, 1422-1430.
https://doi.org/10.1109/ICCV.2015.167 |
| [15] | Tsai, C.C., Wu, T.H. and Lai, S.H. (2022) Multi-Scale Patch-Based Representation Learning for Image Anomaly Detection and Segmentation. Proceedings of the IEEE/CVF Winter Confer-ence on Applications of Computer Vision, Waikoloa, 3-8 January 2022, 3992-4000. https://doi.org/10.1109/WACV51458.2022.00312 |
