{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:16:21Z","timestamp":1760148981638,"version":"build-2065373602"},"reference-count":43,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T00:00:00Z","timestamp":1687219200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002641","name":"Konkuk University","doi-asserted-by":"publisher","award":["2018"],"award-info":[{"award-number":["2018"]}],"id":[{"id":"10.13039\/501100002641","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Defect inspection is important to ensure consistent quality and efficiency in industrial manufacturing. Recently, machine vision systems integrating artificial intelligence (AI)-based inspection algorithms have exhibited promising performance in various applications, but practically, they often suffer from data imbalance. This paper proposes a defect inspection method using a one-class classification (OCC) model to deal with imbalanced datasets. A two-stream network architecture consisting of global and local feature extractor networks is presented, which can alleviate the representation collapse problem of OCC. By combining an object-oriented invariant feature vector with a training-data-oriented local feature vector, the proposed two-stream network model prevents the decision boundary from collapsing to the training dataset and obtains an appropriate decision boundary. The performance of the proposed model is demonstrated in the practical application of automotive-airbag bracket-welding defect inspection. The effects of the classification layer and two-stream network architecture on the overall inspection accuracy were clarified by using image samples collected in a controlled laboratory environment and from a production site. The results are compared with those of a previous classification model, demonstrating that the proposed model can improve the accuracy, precision, and F1 score by up to 8.19%, 10.74%, and 4.02%, respectively.<\/jats:p>","DOI":"10.3390\/s23125768","type":"journal-article","created":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T02:30:51Z","timestamp":1687314651000},"page":"5768","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Two-Stream Network One-Class Classification Model for Defect Inspections"],"prefix":"10.3390","volume":"23","author":[{"given":"Seunghun","family":"Lee","sequence":"first","affiliation":[{"name":"Division of Mechanical and Aerospace Engineering, Konkuk University, 120 Neungdong-ro, Gwangjin-gu, Seoul 05029, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenglong","family":"Luo","sequence":"additional","affiliation":[{"name":"Division of Mechanical and Aerospace Engineering, Konkuk University, 120 Neungdong-ro, Gwangjin-gu, Seoul 05029, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungkwan","family":"Lee","sequence":"additional","affiliation":[{"name":"Sambo Technology, 90 Centum Jungang-ro, Haeundae-gu, Busan 48059, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7080-6630","authenticated-orcid":false,"given":"Hoeryong","family":"Jung","sequence":"additional","affiliation":[{"name":"Division of Mechanical and Aerospace Engineering, Konkuk University, 120 Neungdong-ro, Gwangjin-gu, Seoul 05029, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,6,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1016\/j.jmsy.2021.05.008","article-title":"A Review on Recent Advances in Vision-based Defect Recognition towards Industrial Intelligence","volume":"62","author":"Gao","year":"2022","journal-title":"J. Manuf. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/TII.2020.2985159","article-title":"Nondestructive Defect Detection in Castings by Using Spatial Attention Bilinear Convolutional Neural Network","volume":"17","author":"Tang","year":"2020","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Muresan, M.P., Cireap, D.G., and Giosan, I. (2020, January 3\u20135). Automatic vision inspection solution for the manufacturing process of automotive components through plastic injection molding. Proceedings of the 16th International Conference on Intelligent Computer Communication and Processing (ICCP), Cluj-Napoca, Romania.","DOI":"10.1109\/ICCP51029.2020.9266249"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhang, K., and Wang, L. (2021). Metal Surface Defect Detection Using Modified YOLO. Algorithms, 14.","DOI":"10.3390\/a14090257"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"21777","DOI":"10.1038\/s41598-021-01084-x","article-title":"Real-time detection of particleboard surface defects based on improved YOLOV5 target detection","volume":"11","author":"Zhao","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Aber Ronaghi, A., Ren, J., and El-Gindy, M. (2023). Defect Detection Methods for Industrial Products Using Deep Learning Techniques: A Review. Algorithms, 16.","DOI":"10.3390\/a16020095"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"114088","DOI":"10.1109\/ACCESS.2020.3003588","article-title":"A Generic Semi-Supervised Deep Learning-Based Approach for Automated Surface Inspection","volume":"8","author":"Zheng","year":"2020","journal-title":"IEEE Access"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"9623","DOI":"10.1109\/JIOT.2020.2983050","article-title":"Modified DenseNet for Automatic Fabric Defect Detection With Edge Computing for Minimizing Latency","volume":"7","author":"Zhu","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_9","first-page":"1","article-title":"Pixel-Wise Semisupervised Fabric Defect Detection Method Combined With Multitask Mean Teacher","volume":"71","author":"Shao","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"116827","DOI":"10.1016\/j.eswa.2022.116827","article-title":"Fabric defect detection based on completed local quartet patterns and majority decision algorithm","volume":"198","author":"Pourkaramdel","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1177\/0040517519884124","article-title":"Effective textile quality processing and an accurate inspection system using the advanced deep learning technique","volume":"90","author":"Jeyaraj","year":"2020","journal-title":"Text. Res. J."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Huang, Y.C., Hung, K.C., and Lin, J.C. (2022). Automated Machine Learning System for Defect Detection on Cylindrical Metal Surfaces. Sensors, 22.","DOI":"10.3390\/s22249783"},{"key":"ref_13","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., and Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., and Mei, T. (2017, January 22\u201329). Learning spatio-temporal representation with pseudo-3d residual networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Leibe, B., Matas, J., Sebe, N., and Welling, M. (2016). Computer Vision\u2014ECCV 2016, Springer International Publishing.","DOI":"10.1007\/978-3-319-46478-7"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for MobileNetV3. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1007\/s11554-020-01023-5","article-title":"Real-time implementation of fabric defect detection based on variational automatic encoder with structure similarity","volume":"18","author":"Wei","year":"2021","journal-title":"J. Real-Time Image Process."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1237","DOI":"10.1080\/08839514.2021.1975391","article-title":"Deep Learning Based Steel Pipe Weld Defect Detection","volume":"35","author":"Yang","year":"2021","journal-title":"Appl. Artif. Intell."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Kim, J., Ko, J., Choi, H., and Kim, H. (2021). Printed circuit board defect detection using deep learning via a skip-connected convolutional autoencoder. Sensors, 21.","DOI":"10.3390\/s21154968"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Tang, T.W., Hsu, H., Huang, W.R., and Li, K.M. (2022). Industrial Anomaly Detection with Skip Autoencoder and Deep Feature Extractor. Sensors, 22.","DOI":"10.2139\/ssrn.4109686"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Upadhyay, A., Li, J., King, S., and Addepalli, S. (2023). A Deep-Learning-Based Approach for Aircraft Engine Defect Detection. Machines, 11.","DOI":"10.3390\/machines11020192"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/j.jmsy.2020.03.009","article-title":"Automated defect inspection system for metal surfaces based on deep learning and data augmentation","volume":"55","author":"Yun","year":"2020","journal-title":"J. Manuf. Syst."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.neunet.2018.07.011","article-title":"A systematic study of the class imbalance problem in convolutional neural networks","volume":"106","author":"Buda","year":"2017","journal-title":"Neural Netw."},{"key":"ref_24","unstructured":"Bendre, N., Mar\u00edn, H.T., and Najafirad, P. (2020). Learning from Few Samples: A Survey. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1546","DOI":"10.3844\/jcssp.2020.1546.1557","article-title":"A Survey of Methods for Managing the Classification and Solution of Data Imbalance Problem","volume":"16","author":"Hasib","year":"2020","journal-title":"J. Comput. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"101272","DOI":"10.1016\/j.aei.2021.101272","article-title":"Autoencoder-based anomaly detection for surface defect inspection","volume":"48","author":"Tsai","year":"2021","journal-title":"Adv. Eng. Inform."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.neucom.2021.02.007","article-title":"Outlier exposure with confidence control for out-of-distribution detection","volume":"441","author":"Papadopoulos","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wang, S., Liu, W., Wu, J., Cao, L., Meng, Q., and Kennedy, P.J. (2016, January 24\u201329). Training deep neural networks on imbalanced data sets. Proceedings of the 2016 International Joint Conference on Neural Networks, Vancouver, BC, Canada.","DOI":"10.1109\/IJCNN.2016.7727770"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Mao, W.L., Chiu, Y.Y., Lin, B.H., Wang, C.C., Wu, Y.T., You, C.Y., and Chien, Y.R. (2022). Integration of Deep Learning Network and Robot Arm System for Rim Defect Inspection Application. Sensors, 22.","DOI":"10.3390\/s22103927"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1023\/B:MACH.0000008084.60811.49","article-title":"Support Vector Data Description","volume":"54","author":"Tax","year":"2004","journal-title":"Mach. Learn."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1016\/j.cie.2005.01.009","article-title":"One-class support vector machines\u2014An application in machine fault detection and classification","volume":"48","author":"Shin","year":"2005","journal-title":"Comput. Ind. Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1016\/j.jprocont.2009.07.011","article-title":"Fault detection and diagnosis in process data using one-class support vector machines","volume":"19","author":"Mahadevan","year":"2009","journal-title":"J. Process Control."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1109\/TKDE.2012.235","article-title":"Uncertain one-class learning and concept summarization learning on uncertain data streams","volume":"26","author":"Liu","year":"2014","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_34","unstructured":"Ruff, L., G\u00f6rnitz, N., Deecke, L., Siddiqui, S., Vandermeulen, R.A., Binder, A., M\u00fcller, E., and Kloft, M. Deep One-Class Classification; In Proceedings of International Conference on Machine Learning (ICML), Stockholmsm\u00e4ssan, Stockholm, Sweden, 10\u201315 July 2018."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"5450","DOI":"10.1109\/TIP.2019.2917862","article-title":"Learning Deep Features for One-Class Classification","volume":"28","author":"Perera","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/j.jmsy.2020.10.013","article-title":"Fault detection based on one-class deep learning for manufacturing applications limited an imbalanced database","volume":"57","author":"Lee","year":"2020","journal-title":"J. Manuf. Syst."},{"key":"ref_37","unstructured":"Goyal, S., Raghunathan, A., Jain, M., Simhadri, H.V., and Jain, P. (2020, January 13\u201318). DROCC: Deep robust one-class classification. Proceedings of the International Conference on Machine Learning, Virtual."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.ins.2021.01.069","article-title":"Less complexity one-class classification approach using construction error of convolutional image transformation network","volume":"560","author":"Hayashi","year":"2021","journal-title":"Inf. Sci."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.ins.2022.09.027","article-title":"OCSTN: One-class time-series classification approach using a signal transformation network into a goal signal","volume":"614","author":"Hayashi","year":"2022","journal-title":"Inf. Sci."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"17073","DOI":"10.1007\/s10489-021-02671-1","article-title":"One-class ensemble classifier for data imbalance problems","volume":"52","author":"Hayashi","year":"2022","journal-title":"Appl. Intell."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2015, January 7\u201312). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017, January 21\u201326). Xception: Deep Learning with Depthwise Separable Convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Defard, T., Setkov, A., Loesch, A., and Audigier, R. (2020). PaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization. arXiv.","DOI":"10.1007\/978-3-030-68799-1_35"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/12\/5768\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:57:26Z","timestamp":1760126246000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/12\/5768"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,20]]},"references-count":43,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["s23125768"],"URL":"https:\/\/doi.org\/10.3390\/s23125768","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2023,6,20]]}}}