{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T16:50:59Z","timestamp":1767891059810,"version":"3.49.0"},"reference-count":29,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T00:00:00Z","timestamp":1669939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018YFF01013203"],"award-info":[{"award-number":["2018YFF01013203"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Surface defect detection of micro-electromechanical system (MEMS) acoustic thin film plays a crucial role in MEMS device inspection and quality control. The performances of deep learning object detection models are significantly affected by the number of samples in the training dataset. However, it is difficult to collect enough defect samples during production. In this paper, an improved YOLOv5 model was used to detect MEMS defects in real time. Mosaic and one more prediction head were added into the YOLOv5 baseline model to improve the feature extraction capability. Moreover, Wasserstein divergence for generative adversarial networks with deep convolutional structure (WGAN-DIV-DC) was proposed to expand the number of defect samples and to make the training samples more diverse, which improved the detection accuracy of the YOLOv5 model. The optimal detection model achieved 0.901 mAP, 0.856 F1 score, and a real-time speed of 75.1 FPS. As compared with the baseline model trained using a non-augmented dataset, the mAP and F1 score of the optimal detection model increased by 8.16% and 6.73%, respectively. This defect detection model would provide significant convenience during MEMS production.<\/jats:p>","DOI":"10.3390\/s22239400","type":"journal-article","created":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T03:28:04Z","timestamp":1669951684000},"page":"9400","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Defect Detection of MEMS Based on Data Augmentation, WGAN-DIV-DC, and a YOLOv5 Model"],"prefix":"10.3390","volume":"22","author":[{"given":"Zhenman","family":"Shi","sequence":"first","affiliation":[{"name":"School of Precision Instrument and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China"},{"name":"Key Laboratory of Opto-Electronics Information Technology, Ministry of Education, Tianjin 300072, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7120-0980","authenticated-orcid":false,"given":"Mei","family":"Sang","sequence":"additional","affiliation":[{"name":"School of Precision Instrument and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China"},{"name":"Key Laboratory of Opto-Electronics Information Technology, Ministry of Education, Tianjin 300072, China"}]},{"given":"Yaokang","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Precision Instrument and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China"},{"name":"Key Laboratory of Opto-Electronics Information Technology, Ministry of Education, Tianjin 300072, China"}]},{"given":"Lun","family":"Xing","sequence":"additional","affiliation":[{"name":"School of Precision Instrument and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China"},{"name":"Key Laboratory of Opto-Electronics Information Technology, Ministry of Education, Tianjin 300072, China"}]},{"given":"Tiegen","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Precision Instrument and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China"},{"name":"Key Laboratory of Opto-Electronics Information Technology, Ministry of Education, Tianjin 300072, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,12,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1615\/NanoSciTechnolIntJ.2020033817","article-title":"A review of lattice boltzmann method computational domains for micro-and nanoregime applications","volume":"11","author":"Narendran","year":"2020","journal-title":"Nanosci. Technol. Int. J."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Liu, H.-F., Luo, Z.-C., Hu, Z.-K., Yang, S.-Q., Tu, L.-C., Zhou, Z.-B., and Kraft, M. (2022). A review of high-performance MEMS sensors for resource exploration and geophysical applications. Pet. Sci.","DOI":"10.1016\/j.petsci.2022.06.005"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"103718","DOI":"10.1016\/j.dsp.2022.103718","article-title":"A wafer surface defect detection method built on generic object detection network","volume":"130","author":"Wang","year":"2022","journal-title":"Digit. Signal Process."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"022022","DOI":"10.1088\/1742-6596\/1168\/2\/022022","article-title":"An Overview of Overfitting and Its Solutions","volume":"1168","author":"Ying","year":"2019","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"117731","DOI":"10.1016\/j.eswa.2022.117731","article-title":"Geometric transformation-based data augmentation on defect classification of segmented images of semiconductor materials using a ResNet50 convolutional neural network","volume":"206","author":"Morales","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"ref_7","first-page":"2672","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Chen, S.-H., Kang, C.-H., and Perng, D.-B. (2020). Detecting and measuring defects in wafer die using gan and yolov3. Appl. Sci., 10.","DOI":"10.3390\/app10238725"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"107646","DOI":"10.1016\/j.patcog.2020.107646","article-title":"Tackling mode collapse in multi-generator GANs with orthogonal vectors","volume":"110","author":"Li","year":"2021","journal-title":"Pattern Recognit."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"103314","DOI":"10.1016\/j.cviu.2021.103314","article-title":"HSGAN: Reducing mode collapse in GANs by the latent code distance of homogeneous samples","volume":"214","author":"Yu","year":"2022","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_11","unstructured":"Arjovsky, M., Chintala, S., and Bottou, L. (2017). Wasserstein gan. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"104540","DOI":"10.1016\/j.compbiomed.2021.104540","article-title":"Cancer diagnosis using generative adversarial networks based on deep learning from imbalanced data","volume":"135","author":"Xiao","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1109\/TSM.2018.2825482","article-title":"Deep-structured machine learning model for the recognition of mixed-defect patterns in semiconductor fabrication processes","volume":"31","author":"Tello","year":"2018","journal-title":"IEEE Trans. Semicond. Manuf."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Amini, A., Kanfoud, J., and Gan, T.-H. (2021). An Artificial-Intelligence-Driven Predictive Model for Surface Defect Detections in Medical MEMS. Sensors, 21.","DOI":"10.3390\/s21186141"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Deepan, P., and Sudha, L. (2021). Effective utilization of YOLOv3 model for aircraft detection in Remotely Sensed Images. Mater. Today: Proc., in press.","DOI":"10.1016\/j.matpr.2021.02.831"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wu, W.-S., and Lu, Z.-M. (2022). A Real-Time Cup-Detection Method Based on YOLOv3 for Inventory Management. Sensors, 22.","DOI":"10.3390\/s22186956"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhu, X., Lyu, S., Wang, X., and Zhao, Q. (2021, January 10\u201317). TPH-YOLOv5: Improved YOLOv5 based on Transformer Prediction Head for Object Detection on Drone-Captured Scenarios. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"105031","DOI":"10.1016\/j.compbiomed.2021.105031","article-title":"An efficient real-time colonic polyp detection with YOLO algorithms trained by using negative samples and large datasets","volume":"141","author":"Pacal","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref_19","unstructured":"Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv."},{"key":"ref_20","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., and Courville, A.C. (2017). Improved training of wasserstein gans. Adv. Neural Inf. Process. Syst., 30."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wu, J., Huang, Z., Thoma, J., Acharya, D., and Van Gool, L. (2018, January 8\u201314). Wasserstein divergence for gans. Proceedings of the European conference on computer vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01228-1_40"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., and Lopez-Paz, D. (2017). mixup: Beyond empirical risk minimization. arXiv.","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Liao, H.-Y.M., Wu, Y.-H., Chen, P.-Y., Hsieh, J.-W., and Yeh, I.-H. (2020, January 13\u201319). CSPNet: A new backbone that can enhance learning capability of CNN. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA.","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21\u201326). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., and Jia, J. (2018, January 18\u201323). Path aggregation network for instance segmentation. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., and Savarese, S. (2019, January 15\u201320). Generalized intersection over union: A metric and a loss for bounding box regression. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref_27","unstructured":"Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv."},{"key":"ref_28","unstructured":"Arjovsky, M., and Bottou, L. (2017). Towards principled methods for training generative adversarial networks. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"114962","DOI":"10.1016\/j.engstruct.2022.114962","article-title":"Autonomous surface crack identification of concrete structures based on an improved one-stage object detection algorithm","volume":"272","author":"Wu","year":"2022","journal-title":"Eng. Struct."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/23\/9400\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:32:34Z","timestamp":1760146354000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/23\/9400"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,2]]},"references-count":29,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["s22239400"],"URL":"https:\/\/doi.org\/10.3390\/s22239400","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,2]]}}}