Abstract
The use of X-ray-based non-destructive testing (NDT) methods is widespread in the task of welding defect detection. Many scholars have turned to deep-learning computer vision models for defect detection in weld radiographic images in recent years. Before model training, annotating the collected image data is often necessary. We need to use annotation information to guide the model for effective learning. However, many researchers have been focused on developing better models or refining training strategies, often overlooking the quality of data annotation. This paper delved into the impact of eight types of low-quality annotations on the accuracy of object detection models. In comparison to accurate annotations, inaccuracies in the annotated locations significantly impact model performance, while errors in category annotations have a minor effect on model performance. Incorrect location affects both the recall and precision of the model, while incorrect categorization only impacts the precision of the model. Additionally, we observed that the extent of the impact of location errors is related to the detection accuracy of individual classes, with classes having higher original detection AP experiencing more substantial decreases in AP under location errors. Finally, we analyzed the influence of annotator habits on model performance. The study examines the effects of various types of low-quality annotations on model training and their impact on individual detection categories. Annotator habits lead to the left boundary of annotated boxes being less accurate than the right boundary, resulting in a greater impact of annotations biased to the left than those biased to the right. Based on experiments and analysis, we proposed annotation guidelines for weld defect detection tasks: prioritize the quality of location annotations over category accuracy and strive to include all objects, including those with ambiguous boundaries.
Similar content being viewed by others
Data Availability
Data are available under request to corresponding author.
References
Nafaa, N.; Redouane, D.; Amar, B (2000) Weld defect extraction and classification in radiographic testing based artificial neural networks. In Proceedings of the 15th World Conference on Non Destructive Testing, Rome, Italy, p 15–21
Zahran O, Kasban H, El-Kordy M, El-Samie FEA (2013) Automatic weld defect identification from radiographic images. NDT E Int 57:26–35. https://doi.org/10.1016/j.ndteint.2012.11.005
Boaretto N, Centeno TM (2017) Automated detection of welding defects in pipelines from radiographic images DWDI. NDT E Int 86:7–13. https://doi.org/10.1016/j.ndteint.2016.11.003
Hou W, Wei Y, Jin Y, Zhu C (2019) Deep features based on a DCNN model for classifying imbalanced weld flaw types. Measurement 131:482–489. https://doi.org/10.1016/j.measurement.2018.09.011
Sassi P, Tripicchio P, Avizzano CA (2019) A smart monitoring system for automatic welding defect detection. IEEE Trans Industr Electron 66:9641–9650. https://doi.org/10.1109/TIE.2019.2896165
Zhang Y, You D, Gao X, Zhang N, Gao PP (2019) Welding defects detection based on deep learning with multiple optical sensors during disk laser welding of thick plates. J Manuf Syst 51:87–94. https://doi.org/10.1016/j.jmsy.2019.02.004
Zhang Z, Wen G, Chen S (2019) Weld image deep learning-based on-line defects detection using convolutional neural networks for Al alloy in robotic arc welding. J Manuf Process 45:208–216. https://doi.org/10.1016/j.jmapro.2019.06.023
Yang D, Cui Y, Yu Z, Yuan H (2021) Deep learning based steel pipe weld defect detection. Appl Artif Intell 35:1237–1249. https://doi.org/10.1080/08839514.2021.1975391
Ji C, Wang H, Li H (2023) Defects detection in weld joints based on visual attention and deep learning. NDT E Int 133:102764. https://doi.org/10.1016/j.ndteint.2022.102764
Wang J, Mu C, Mu S, Zhu R, Yu H (2023) Welding seam detection and location: deep learning network-based approach. Int J Press Vessels Pip 202:104893. https://doi.org/10.1016/j.ijpvp.2023.104893
Cunningham P, Cord M, Delany SJ (2008) Supervised learning. Springer, Berlin Heidelberg
Ma J, Ushiku Y, Sagara M (2022) The effect of improving annotation quality on object detection datasets: a preliminary study. IEEE/CVF Conf Comput Vision Pattern Recog Workshop (CVPRW) 2022:4849–4858. https://doi.org/10.1109/CVPRW56347.2022.00532
Kumar A, Kaur A, Kumar M (2019) Face detection techniques: a review. Artif Intell Rev 52:927–948. https://doi.org/10.1007/s10462-018-9650-2
Mukhtar A, Xia L, Tang TB (2015) Vehicle detection techniques for collision avoidance systems: a review. IEEE Trans Intell Transp Syst 16:2318–2338. https://doi.org/10.1109/TITS.2015.2409109
Zou Z, Chen K, Shi Z, Guo Y, Ye J (2023) Object detection in 20 years: a survey. Proc IEEE 111:257–276. https://doi.org/10.1109/JPROC.2023.3238524
Zhang B, Wang X, Cui J, Wu J, Wang X, Li Y, Li J, Tan Y, Chen X, Wu W, Yu X (2023) Welding defects classification by weakly supervised semantic segmentation. NDT and E Int 138:102899. https://doi.org/10.1016/j.ndteint.2023.102899
Terven J, Córdova-Esparza D-M, Romero-González J-A (2023) A comprehensive review of YOLO architectures in computer vision: from YOLOv1 to YOLOv8 and YOLO-NAS. Mach Learn Knowl Extraction 5:1680–1716. https://doi.org/10.3390/make5040083
Tian Z, Shen C, Chen H, He T (2022) FCOS: a simple and strong anchor-free object detector. IEEE Trans Pattern Anal Mach Intell 44:1922–1933. https://doi.org/10.1109/TPAMI.2020.3032166
Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. Journal of big data 6:1–48. https://doi.org/10.1186/s40537-019-0197-0
Weiss K, Khoshgoftaar TM, Wang D (2016) A survey of transfer learning. J Big data 3:1–40. https://doi.org/10.48550/arXiv.1804.06353
Zhao Z-Q, Zheng P, S-t Xu, Wu X (2019) Object detection with deep learning: a review. IEEE Trans Neural Netw Learn Syst 30:3212–3232. https://doi.org/10.1109/TNNLS.2018.2876865
Wang J, Perez L (2017) The effectiveness of data augmentation in image classification using deep learning. Convolutional Neural Netw Vis Recognit 11:1–8. https://doi.org/10.48550/arXiv.1712.04621
Ruby U and V Yendapalli (2020) Binary cross entropy with deep learning technique for image classification. Int J Adv Trends Comput Sci Eng 9: https://doi.org/10.30534/ijatcse/2020/175942020
Li X, Wang W, Hu X, Li J, Tang J, Yang J (2021) Generalized focal loss V2: learning reliable localization quality estimation for dense object detection. IEEE. https://doi.org/10.1109/CVPR46437.2021.01146
Zheng Z, Wang P, Liu W, Li J, Ye R, Ren D (2020) Distance-IoU loss: faster and better learning for bounding box regression. Proc AAAI Conf Artif Intell 34:12993–13000. https://doi.org/10.1609/aaai.v34i07.6999
Neubeck A, Van Gool L (2006) Efficient non-maximum suppression. 18th Int Conf Pattern Recog (ICPR’06) 3:850–855. https://doi.org/10.1109/ICPR.2006.479
Sokolova M, N Japkowicz and S Szpakowicz (2006) Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. Australas Joint Conf Artif Intell 1015–1021. https://doi.org/10.1007/11941439_114
Selvaraju RR, Das A, Vedantam R, Cogswell M, Parikh D, Batra D (2016) Grad-CAM: Why did you say that? https://doi.org/10.48550/arXiv.1611.07450
Funding
This work was supported by the Natural Science Foundation of China (NSFC No. U2141216).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
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.
Recommended for publication by Commission V—NDT and Quality Assurance of Welded Products.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Cui, J., Zhang, B., Wang, X. et al. Impact of annotation quality on model performance of welding defect detection using deep learning. Weld World 68, 855–865 (2024). https://doi.org/10.1007/s40194-024-01710-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40194-024-01710-y