Abstract
The prerequisite for realizing robotic self-adaptive grinding of the car body welding slags is to accurately identify the small and randomly distributed welding slags, and to segment their contour from the complex background. In this paper, an improved SegNet network model is proposed to address the challenging problems in small target detection and contour extraction. Both the ability to capture image features and to perceive global and local information is enhanced by adding the context extractor into the SegNet network. Furthermore, the residual structure and BN layer are used to optimize the decoder of the SegNet network, and the Dropout layer is employed to effectively avoid overfitting of the training model. Based on these strategies, the adaptability of the network to multi-scale targets is further enhanced. Experiments on car body welding slags detection indicate that the accuracy rate of the improved SegNet network model can reach 99.5%, which is 2.7% higher than that before improvement. Meanwhile, the boundary pixels at connection area among welding slags, metal plate, and background are accurately segmented, which provides data support for the subsequent robotic grinding of car body welding slags.
Similar content being viewed by others
Data availability
The data and materials of this manuscript are available from the corresponding authors on reasonable request.
References
Zhu D, Feng X, Xu X, Yang Z, Li W, Yan S, Ding H (2020) Robotic grinding of complex components: a step towards efficient and intelligent machining - challenges, solutions, and applications. Rob Comput Integr Manuf 65:101908
Patra S, Gautam R, Singla A (2014) A novel context sensitive multilevel thresholding for image segmentation. Appl Soft Comput 23:122–127
Niu Z, Li H (2019) Research and analysis of threshold segmentation algorithms in image processing. J Phys Conf Ser 1237(2):022122
Zhang Y, Li T, Li Q (2013) Defect detection for tire laser shearography image using curvelet transform based edge detector. Opt Laser Technol 47:64–71
Banharnsakun A (2019) Artificial bee colony algorithm for enhancing image edge detection. Evol Syst 10(4):679–687
Mirapeix J, García-Allende PB, Cobo A, Conde OM, López-Higuera JM (2007) Real-time arc-welding defect detection and classification with principal component analysis and artificial neural networks. NDT E Int 40:315–323
Wang T, Chen Y, Qiao M, Snoussi H (2017) A fast and robust convolutional neural network-based defect detection model in product quality control. Int J Adv Manuf Technol 94:3465–3471
Lin J, Yao Y, Ma L, Wang Y (2018) Detection of a casting defect tracked by deep convolution neural network. Int J Adv Manuf Technol 97:573–581
Gu J, Wang Z, Kuen J, Ma L, Shahroudy A, Shuai B, Liu T, Wang X, Wang G, Cai J (2018) Recent advances in convolutional neural networks. Pattern Recogn 77:354–377
Wang Z, Zhu D (2019) An accurate detection method for surface defects of complex components based on support vector machine and spreading algorithm. Measurement 147:106886
Kim H, Lee H, Kim JS, Ahn SH (2020) Image-based failure detection for material extrusion process using a convolutional neural network. Int J Adv Manuf Technol 111:1291–1302
Wei X, Yang Z, Liu Y, Wei D, Jia L, Li Y (2019) Railway track fastener defect detection based on image processing and deep learning techniques: a comparative study. Eng Appl Artif Intel 80:66–81
Ren R, Hung T, Tan KC (2018) A generic deep-learning-based approach for automated surface inspection. IEEE Trans Cybern 48:929–940
Tabernik D, Šela S, Skvarč J, Skočaj D (2019) Segmentation-based deep-learning approach for surface-defect detection. J Intell Manuf 31:759–776
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-assisted Intervention, Springer, pp. 234–241
Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881–2890
Chen LC, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:05587
Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE T Pattern Anal 39:2481–2495
Gu Z, Cheng J, Fu H, Zhou K, Hao H, Zhao Y, Zhang T, Gao S, Liu J (2019) CE-Net: context encoder network for 2D medical image segmentation. IEEE T Med Imaging 38:2281–2292
Lin M, Chen Q, Yan S (2013) Network in network. arXiv preprint arXiv:1312.4400
Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov RR (2012) Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580
Wu S, Wang G, Tang P, Chen F, Shi L (2019) Convolution with even-sized kernels and symmetric padding. arXiv preprint arXiv:1903.08385
Zhou ZH, Yu Y, Qian C (2019) Evolutionary learning: advances in theories and algorithms. Springer
Zhou Y, Wang X, Zhang M, Zhu J, Zheng R, Wu Q (2019) MPCE: a maximum probability based cross entropy loss function for neural network classification. IEEE Access 7:146331–146341
Chen LC, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder-decoder with Atrous separable convolution for semantic image segmentation. Proceedings of the European Conference on Computer Vision (ECCV), pp. 801–818
Funding
This study was funded by the National Natural Science Foundation of China (No. 51975443), the Hubei Province Key R&D Program (No. 2020BAA025) and the “111” Project (No. B17034).
Author information
Authors and Affiliations
Contributions
Dahu Zhu: conceptualization, funding acquisition, writing. Chen Qian: methodology, investigation, software. Chao Qu: methodology, validation, writing. Minqi He: writing — reviewing and editing. Shuwen Zhang: investigation, software. Qiuping Tu: methodology, investigation, software. Wenting Wei: methodology, writing — reviewing and editing.
Corresponding author
Ethics declarations
Ethics approval
The authors claim that none of the contents in this manuscript has been published or considered for publication elsewhere. Besides, the research contents of the article do not violate ethics.
Consent to participate
The research does not involve human participants or animals, and the authors warrant that the manuscript fulfills the ethical standards of the journal.
Consent for publication
All the authors give consent to publish this manuscript in the International Journal of Advanced Manufacturing Technology.
Competing interests
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhu, D., Qian, C., Qu, C. et al. An improved SegNet network model for accurate detection and segmentation of car body welding slags. Int J Adv Manuf Technol 120, 1095–1105 (2022). https://doi.org/10.1007/s00170-022-08836-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-022-08836-7