[1] ZHU Yudong, CHEN Yuxue. Visual inspection method of detecting flaws on optical glasses surface[J]. Journal of Applied Optics, 41, 553-558(2020).

[2] CAO Yu, XU Chuanpeng. Application of an improved threshold segmentation algorithm in lens defect detection[J]. Laser & Optoelectronics Progress, 58, 219-224(2021).

[3] SUN Li, LIU Chen, YAO Hongbing. Automatic detection of water-mask for resin glassby machine vision[J]. Journal of Jiangsu University (Natural Science Edition), 39, 425-430(2018).

[4] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 39, 1137-1149(2016).

[5] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C], 779-788(2016).

[6] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C], 6517-6525(2017).

[7] BOCHKOVSKIY A, WANG C Y, YUAN H, et al. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. https://arxiv.org/pdf/2004.10934.pdf

[8] ZHU Hongzhao. The research on resin lens defect recogni- tion method based on degenerate YOLO network[D](2019).

[9] WANG Yulong. Research on scratch detction of optical lens surface based on U-Net network[D](2021).

[10] HOU W, TAO X, XU D. Combining prior knowledge with CNN for weak scratch inspection of optical components[J]. IEEE Transactions on Instrumentation and Measurement, 70, 1-11(2020).

[11] LIU Xiaolei, LIU Fenghui, CUI Chenjia. Optical glass curved lens based on YOLOv5s network defect detection methods[J]. Laser Journal, 45, 94-99(2024).

[12] LIU Xiaolei, LIU Fenghui. Defect detection of curved optical lenses based on improved YOLOv5s[J]. Journal of Applied Optics, 45, 781-789(2024).

[13] National Technical Committee of Standardization of Optics and Photonics[S]. GB/T 1185-2006 optical parts surface defects(2007).

[14] FAN Wu YANG Y Y, JIANG J B, et al. Classification between digs and dust particles on optical surfaces with acquisition and analysis of polarization characteri-stics.[J]. Applied Optics, 58, 1073-1083(2019).

[15] LIU S T, DI H, WANG Y H. Receptive field block net for accurate and fast object detection.[C], 404-419(2018).

[16] ZHANG Bo. YOLOv6 v3.0: a full-scale reloading[EB/OL]. https://arxiv.org/pdf/2301.05586v1

[17] PANVAN KUMAR A V. MobileOne: an improved one millisecond mobile backbone[EB/OL]. https://arxiv.org/pdf/2206.04040

[18] YANG L, ZHANG R Y, LI L, et al. SimAM: a simple, parameter-free attention module for convolutional neural networks[C], 11863-11874(2021).

[19] XU C. A normalized Gaussian wasserstein distance for tiny object detection[EB/OL]. http://arxiv.org/abs/2110.13389v2

[20] GEVORGYAN Z. SIoU loss: more powerful learning for bounding box regression[EB/OL]. https://arxiv.org/abs/2205.12740

[21] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[J]. European Conference on Computer Vision (ECCV), 9905, 21-37(2016).

[22] NILCOLAS C, FRANCISCO M, Gabriel S, et al. End-to-end object detection with transformers[C], 213-229(2020).

[23] ZHOU X Y. Objects as points[EB/OL]. https://arxiv.org/abs/1904.07850

[24] TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection[C], 10778-10787(2020).

[25] VARGHESE R, SAMBATH M. YOLOv8: a novel object detection algorithm with enhanced performance and robustness[C], 1-6(2024).