Abstract
In view of the unpredictable defects in the industrial lead frame production line, many factories invest a lot of manpower resources and material re-sources to participate in the inspection process, which will cause huge losses to the producers, and the human eyes have the problems such as easy fatigue and low efficiency. In this paper, for the research on defect detection in lead frame exposure production line, the Efficient Channel Attention module is added to YOLOX algorithm to optimize the backbone network to improve the feature extraction capability and detection efficiency of the algorithm, and Varifocal Loss is introduced to solve the problem of very few defect samples in industry. After a lot of experiments, it has been proved that the evaluation indicator mAP@0.5 of the model trained by the improved YOLOX algorithm is increased by 2.10%, which is lightweight and has a higher accuracy.
This work is supported by Science Research Plan of Shaanxi Provincial Department of Education under Grant No. 19JC036.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Shumin, D., Zhoufeng, L., Chunlei, L.: AdaBoost learning for fabric defect detection based on HOG and SVM. In: International Conference on Multimedia Technology. pp. 2903–2906 (2011)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 2117–2125 (2017)
Karunakaran, V.: Deep learning based object detection using mask RCNN. In: International Conference on Communication and Electronics Systems (ICCES). pp. 1684–1690(2021)
Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems, 29 (2016)
Ge, Z., Liu, S., Wang, F., Li, Z., & Sun, J.: YOLOX: Exceeding YOLO series in 2021. ar**v preprint ar**v: 2107.08430 (2021)
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., Berg, A.C.: SSD: Single shot multibox detector. In: European Conference on Computer Vision. Springer, Cham. pp. 21–37 (2016)
Li, C., Cai, J., Qiu, S., Liang, H.: Defects detection of steel based on YOLOv4. In: China Automation Congress (CAC). IEEE, pp. 5836–5839 (2021)
Li, W., Dong, T., Shi, H., Ye, L.: Defect detection algorithm of wire rope based on color segmentation and Faster RCNN. In: 2021 International Conference on Control, Automation and Information Sciences (ICCAIS). IEEE, pp. 656–661 (2021)
Wang, Q., Wu, B., Zhu, P., Li, P., Hu, Q.: ECA-Net: efficient channel attention for deep convolutional neural networks. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)
Zhang, H., Wang, Y., Dayoub, F., Sunderhauf, N.: VarifocalNet: An IoU-aware dense object detector. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 8514–8523 (2021)
Wu, S., Li, X., Wang, X.: IoU-aware single-stage object detector for accurate localization. Image Vis. Comput. 97, 103911 (2020)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7132–7141 (2018)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2980–2988 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Deng, W., Wu, D., Jie, J., Wang, W. (2023). Defect Detection of Exposure Lead Frame Based on Improved YOLOX. In: **ong, N., Li, M., Li, K., **ao, Z., Liao, L., Wang, L. (eds) Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery. ICNC-FSKD 2022. Lecture Notes on Data Engineering and Communications Technologies, vol 153. Springer, Cham. https://doi.org/10.1007/978-3-031-20738-9_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-20738-9_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20737-2
Online ISBN: 978-3-031-20738-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)