|
|
基于Resnet50的电芯蓝膜缺陷检测
|
Abstract:
在新能源电芯工业生产过程中，要确保成品质量，电芯蓝膜的表面质量检测是一项主要的任务。针对蓝膜缺陷细小，准确率以及效率较低的问题，本文提出了一种基于Resnet50残差网络的图像分割算法。算法为了提高电芯蓝膜缺陷检测能力，将拍摄得到的蓝膜原图像进行初步切割，判断各个切割区域是否存在表面缺陷；其次再采用Resnet50残差网络在切割得到的区域进行二次图像分割，极大的提高了电芯蓝膜缺陷检测的效率以及准确性。实验表明，该方法针对电芯蓝膜缺陷检测取得了优异的效果。
In the industrial production process of new energy cells, the surface quality inspection of the blue film of the cells is an important task to ensure the quality of the finished product. To solve the problem of small blue film defects and low accuracy and efficiency, an image segmentation algorithm based on Resnet50 residual network is proposed in this paper. In order to improve the detection capability of the blue film defects of the cores, the algorithm first cuts the original image of the blue film obtained from the shooting to determine whether there are surface defects in each cut area; secondly, it uses the Resnet50 residual network to perform secondary image segmentation in the area obtained from the cut d, which greatly improves the efficiency and accuracy of the blue film defect detection of the cores. The experiments show that the method achieves excellent results for the detection of blue film defects in the cores.
| [1] | 陶显, 侯伟, 徐德. 基于深度学习的表面缺陷检测方法综述[J]. 自动化学报, 2021, 47(5): 1017-1034. |
| [2] | Kang, G.Q., Gao, S.B., Yu, L. and Zhang, D.K. (2019) Deep Architecture for High-Speed Railway Insulator Surface Defect Detection: Denoising Autoencoder with Multitask Learning. IEEE Transactions on Instrumentation and Measurement, 68, 2679-2690. https://doi.org/10.1109/TIM.2018.2868490 |
| [3] | Youkachen, S., Ruchanurucks, M., Phatrapomnant, T. and Kaneko, H. (2019) Defect Segmentation of Hot-Rolled Steel Strip Surface by Using Convolutional Autoencoder and Conventional Image Processing. Proceedings of the 10th International Conference of Information and Communication Technology for Embedded Systems (ICICTES), Bangkok, Thailand, 25-27 March 2019, 1-5. https://doi.org/10.1109/ICTEmSys.2019.8695928 |
| [4] | Zhao, Z.X., Li, B., Dong, R. and Zhao, P. (2018) A Surface Defect Detection Method Based on Positive Samples. Proceedings of the 15th Pacific Rim International Conference on Artificial Intelligence, Nanjing, China, 28-31 August 2018, 473-481. |
| [5] | Shen, H., Li, S.X., Gu, D.Y. and Chang, H.X. (2012) Bearing Defect Inspection Based on Machine Vision. Measurement, 45, 719-733. https://doi.org/10.1016/j.measurement.2011.12.018 |
| [6] | Pearl, J. (2013) Direct and Indirect Effects. https://arxiv.org/abs/1301.2300 |
| [7] | Rumelhart, D.E., Hinton, G.E. and Williams, R.J. (1986) Learning Representations by Back-Propagating Errors. Nature, 323, 533-536. https://doi.org/10.1038/323533a0 |
| [8] | Bourlard, H. and Kamp, Y. (1988) Auto-Association by Multilayer Perceptrons and Singular Value Decomposition. Biological Cybernetics, 59, 291-294. https://doi.org/10.1007/BF00332918 |
| [9] | He, K.M., Zhang, X.Y., Ren, S.Q. and Sun, J. (2016) Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27-30 June 2016, 770-778.
https://doi.org/10.1109/CVPR.2016.90 |
| [10] | Mei, S., Yang, H. and Yin, Z.P. (2018) An Unsupervised-Learning-Based Approach for Automated Defect Inspection on Textured Surfaces. IEEE Transactions on Instrumentation and Measurement, 67, 1266-1277.
https://doi.org/10.1109/TIM.2018.2795178 |
| [11] | 司明明, 陈玮, 胡春燕, 尹钟. 融合Resnet50和U-Net的眼底彩色血管图像分割[J]. 电子科技, 2021, 34(8): 19-24. |
| [12] | Qin, X., Zhang, Z., Huang, C., et al. (2020) U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection. Pattern Recognition, 106, Article No. 107404. https://doi.org/10.1016/j.patcog.2020.107404 |
| [13] | Milletari, F., Navab, N., Ahmadi, S.-A. (2016) V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. 2016 Fourth International Conference on 3D Vision (3DV), Stanford, CA, USA, 25-28 October 2016. https://doi.org/10.1109/3DV.2016.79 |
