[1]吴瑞林,葛泉波,刘华平.基于YOLOX的类增量印刷电路板缺陷检测方法[J].智能系统学报,2024,19(4):1061-1070.[doi:10.11992/tis.202309044]
WU Ruilin,GE Quanbo,LIU Huaping.Class-incremental printed circuit board defect detection method based on YOLOX[J].CAAI Transactions on Intelligent Systems,2024,19(4):1061-1070.[doi:10.11992/tis.202309044]
点击复制
WU Ruilin,GE Quanbo,LIU Huaping.Class-incremental printed circuit board defect detection method based on YOLOX[J].CAAI Transactions on Intelligent Systems,2024,19(4):1061-1070.[doi:10.11992/tis.202309044]
基于YOLOX的类增量印刷电路板缺陷检测方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
19
期数:
2024年第4期
页码:
1061-1070
栏目:
吴文俊人工智能科学技术奖论坛
出版日期:
2024-07-05
- Title:
- Class-incremental printed circuit board defect detection method based on YOLOX
- Keywords:
- deep learning; printed circuit board; class-incremental; incremental learning; defect detection; object detection; dynamic detection; knowledge distillation; catastrophic forgetting
- 分类号:
- TP391
- 摘要:
- 为了应对更加实际的增量式印刷电路板缺陷检测场景，本文将知识蒸馏与YOLOX相结合，提出了一种基于YOLOX的类增量印刷电路板缺陷检测方法。在只使用新训练数据的情况下，模型能够检测出所有学过的缺陷类型。通过对模型的输出特征和中间特征使用知识蒸馏来促进旧缺陷类别知识的传递，使得学生模型能够有效保留教师模型在旧缺陷类别上的检测性能。实验结果表明，本文方法能够显著缓解增量学习过程中的灾难性遗忘问题，在两阶段增量场景下，模型对所有缺陷的平均检测精度为88.5%，参数量为25.3×106，检测速度为39.8 f/s，便于工业设备部署的同时，可以满足增量式检测场景下印刷电路板(printed circuit board, PCB)质检的检测精度和检测速度要求。
- Abstract:
- To cope with more practical incremental printed circuit board detection scenarios, by combining the knowledge distillation with the YOLOX, this paper proposes a class-incremental Printed Circuit Board defect detection method based on YOLOX. The model can detect all learned defect types when only new training data is used. The transfer of knowledge about old defect categories is facilitated by using knowledge distillation for the model’s output features and intermediate features, enabling the student model to effectively retain the detection performance of the teacher model on old defect categories. The experimental results show that the method in this paper can significantly alleviate the catastrophic forgetting problem during the incremental learning process. Under the two-stage incremental scenario, the model has a mean average precision of 88.5% for all defects, a parameter size of 25.3 M, and an inspection speed of 39.8 f/s, which facilitates the deployment of industrial equipment and at the same time, it can satisfy the detection accuracy of printed circuit board (PCB) quality inspection and the inspection speed requirement in incremental detection scenarios.
- 参考文献/References:
-
[1] CHEN Yajun, DING Yuanyuan, ZHAO Fan, et al. Surface defect detection methods for industrial products: a review[J]. Applied sciences, 2021, 11(16): 7657.
[2] 钱万明, 朱红萍, 朱泓知, 等. 基于自适应加权特征融合的PCB裸板缺陷检测研究[J]. 电子测量与仪器学报, 2022, 36(10): 92–99
QIAN Wanming, ZHU Hongping, ZHU Hongzhi, et al. Research on defect detection of PCB bare board based on adaptive weighted feature fusion[J]. Journal of electronic measurement and instrumentation, 2022, 36(10): 92–99
[3] 季堂煜, 赵倩, 余文涛, 等. 基于增强小目标特征提取的PCB板缺陷检测模型[J]. 仪表技术与传感器, 2023(4): 87–92
JI Tangyu, ZHAO Qian, YU Wentao, et al. PCB board defect detection model based on enhanced small-target feature extraction[J]. Instrumentation technology and sensors, 2023(4): 87–92
[4] TANG Junlong, LIU Shenbo, ZHAO Dongxue, et al. PCB-YOLO: an improved detection algorithm of PCB surface defects based on YOLOv5[J]. Sustainability, 2023, 15(7): 5963.
[5] CHEN Wei, HUANG Zhongtian, MU Qian, et al. PCB defect detection method based on transformer-yolo[J]. IEEE access, 2022, 10: 129480–129489.
[6] QIN Ling, ISA N A M. Printed circuit board defect detection methods based on image processing, machine learning and deep learning: a survey[J]. IEEE access, 2023, 11: 15921–15944.
[7] LI Zhizhong, HOIEM D. Learning without forgetting[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 40(12): 2935–2947.
[8] HINTON G, VINYAL O, DEAN J. Distilling the knowledge in a neural network[EB/OL]. (2015-03-09) [2023-09-27]. https://arxiv.org/abs/1503.02531.
[9] REBUFFI S A, KOLESNIKOV A, SPERL G, et al. Icarl: incremental classifier and representation learning[C]//Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 2001-2010.
[10] DOUILLARD A, CORD M, OLLION C, et al. Podnet: pooled outputs distillation for small-tasks incremental learning[C]//European Conference on Computer Vision. Glasgow: Springer International Publishing, 2020: 86-102.
[11] SHMELKOV K, SCHMID C, ALAHARI K. Incremental learning of object detectors without catastrophic forgetting[C]//Proceedings of the IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 3400-3409.
[12] ZHOU Wang, CHANG Shiyu, SOSA N, et al. Lifelong object detection[EB/OL]. (2020-09-02) [2023-09-27]. https://arxiv.org/abs/2009.01129.
[13] GE Zheng, LIU Songtao, WANG Feng, et al. Yolox: exceeding yolo series in 2021[EB/OL]. (2021-07-06) [2023-09-27]. https://arxiv.org/abs/2107.08430.
[14] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 1440-1448.
[15] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2016, 39(6): 1137–1149.
[16] TIAN Zhi, SHEN Chunhua, CHEN Hao, et al. Fcos: fully convolutional one-stage object detection[C]//Proceedings of the IEEE International Conference on Computer Vision. Seoul: IEEE, 2019: 9627-9636.
[17] CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers[C]//European Conference on Computer Vision. Cham: Springer International Publishing, 2020: 213-229.
[18] KOTHALA L P, JONNALA P, GUNTUR S R. Localization of mixed intracranial hemorrhages by using a ghost convolution-based YOLO network[J]. Biomedical signal processing and control, 2023, 80: 104378.
[19] 韩璐,毕晓君. 基于增强特征融合YOLOV5的视网膜病变检测[J]. 应用科技, 2022, 49(1): 66–72
HAN Lu, BI Xiaojun. Detection of retinopathy based on enhanced feature fusion YOLOV5[J]. Applied science and technology, 2022, 49(1): 66–72
[20] BAO Wenxia, DU Xiang, WANG Nian, et al. A defect detection method based on BC-YOLO for transmission line components in UAV remote sensing images[J]. Remote sensing, 2022, 14(20): 5176.
[21] 李朝辉,安金堂,贾红雨,等. 结合旋转框和注意力机制的轻量遥感图像检测模型[J]. 中国图象图形学报, 2023, 28(9): 2706–2718
LI Zhaohui, AN Jintang, JIA Hongyu, et al. Lightweight object detection model in remote sensing image by combining rotation box and attention mechanism[J]. Journal of image and graphics, 2023, 28(9): 2706–2718
[22] 孙智文,秦志亮,彭若松,等. 基于改进YOLOv4深度学习的有雾海面船只识别[J]. 应用科技, 2023, 50(5): 37–45
SUN Zhiwen, QIN Zhiliang, PENG Ruosong, et al. Ship identification of foggy sea surface based on improved YOLOv4 deep learning algorithm[J]. Applied science and technology, 2023, 50(5): 37–45
[23] 吴睿,毕晓君. 基于改进YOLOv5算法的珊瑚礁底栖生物识别方法[J]. 哈尔滨工程大学学报, 2022, 43(4): 580–586
WU Rui, BI Xiaojun. A coral reef benthic recognition method based on the improved YOLOv5 algorithm[J]. Journal of Harbin Engineering University, 2022, 43(4): 580–586
[24] 余越,柏兴,狄岚. 基于YOLO网络和小波降噪的视频车辆跟踪测速优化[J]. 应用科技, 2023, 50(1): 14–20
YU Yue, BAI Xing, DI Lan. Video vehicle tracking and speed measurement optimization based on YOLO network and wavelet noise reduction[J]. Applied science and technology, 2023, 50(1): 14–20
[25] 卞佰成, 陈田, 吴入军, 等. 基于改进YOLOv3的印刷电路板缺陷检测算法[J]. 浙江大学学报(工学版), 2023, 27(4): 735–743
BIAN Baicheng, CHEN Tian, WU Rujun, et al. PCB defect detection algorithm based on improved YOLOv3[J]. Journal of Zhejiang University (engineering science edition), 2023, 27(4): 735–743
[26] ZHENG Liaomo, WANG Xiaojie, WANG Qi, et al. A fabric defect detection method based on improved yolov5[C]//2021 7th International Conference on Computer and Communications. Chengdu: IEEE, 2021: 620-624.
[27] 张秋雁,朱傥,肖书舟,等. 基于改进YOLOv4算法的高压输电线路异物检测[J]. 应用科技, 2023, 50(4): 59–65
ZHANG Qiuyan, ZHU Tang, XIAO Shuzhou, et al. Foreign object detection of high voltage transmission line based on improved YOLOv4 algorithm[J]. Applied science and technology, 2023, 50(4): 59–65
[28] ZHANG Meng, YIN Liju. Solar cell surface defect detection based on improved YOLOv5[J]. IEEE access, 2022, 10: 80804–80815.
[29] 公徐路, 张淑娟. 基于改进YOLOv5s的苹果叶片小目标病害轻量化检测方法[J]. 农业工程学报, 2023, 29(19): 175–184
GONG Xulu, ZHANG Shujuan. Lightweight detection method of small target disease in apple leaves based on improved YOLOv5s[J]. Transactions of the chinese society of agricultural engineering, 2023, 29(19): 175–184
[30] LI Dawei, TASCI S, GHOSH S, et al. RILOD: near real-time incremental learning for object detection at the edge[C]//Proceedings of the 4th ACM/IEEE Symposium on Edge Computing. Washington: ACM, 2019: 113-126.
[31] RUSU A A, RABINOWIT N C, DESJARDIN G, et al. Progressive neural networks[EB/OL]. (2016-06-15) [2023-09-27]. https://arxiv.org/abs/1606.04671.
[32] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 2980-2988.
- 相似文献/References:
-
[1]张媛媛,霍静,杨婉琪,等.深度信念网络的二代身份证异构人脸核实算法[J].智能系统学报,2015,10(2):193.[doi:10.3969/j.issn.1673-4785.201405060]
ZHANG Yuanyuan,HUO Jing,YANG Wanqi,et al.A deep belief network-based heterogeneous face verification method for the second-generation identity card[J].CAAI Transactions on Intelligent Systems,2015,10():193.[doi:10.3969/j.issn.1673-4785.201405060]
[2]丁科,谭营.GPU通用计算及其在计算智能领域的应用[J].智能系统学报,2015,10(1):1.[doi:10.3969/j.issn.1673-4785.201403072]
DING Ke,TAN Ying.A review on general purpose computing on GPUs and its applications in computational intelligence[J].CAAI Transactions on Intelligent Systems,2015,10():1.[doi:10.3969/j.issn.1673-4785.201403072]
[3]马晓,张番栋,封举富.基于深度学习特征的稀疏表示的人脸识别方法[J].智能系统学报,2016,11(3):279.[doi:10.11992/tis.201603026]
MA Xiao,ZHANG Fandong,FENG Jufu.Sparse representation via deep learning features based face recognition method[J].CAAI Transactions on Intelligent Systems,2016,11():279.[doi:10.11992/tis.201603026]
[4]刘帅师,程曦,郭文燕,等.深度学习方法研究新进展[J].智能系统学报,2016,11(5):567.[doi:10.11992/tis.201511028]
LIU Shuaishi,CHENG Xi,GUO Wenyan,et al.Progress report on new research in deep learning[J].CAAI Transactions on Intelligent Systems,2016,11():567.[doi:10.11992/tis.201511028]
[5]马世龙,乌尼日其其格,李小平.大数据与深度学习综述[J].智能系统学报,2016,11(6):728.[doi:10.11992/tis.201611021]
MA Shilong,WUNIRI Qiqige,LI Xiaoping.Deep learning with big data: state of the art and development[J].CAAI Transactions on Intelligent Systems,2016,11():728.[doi:10.11992/tis.201611021]
[6]王亚杰,邱虹坤,吴燕燕,等.计算机博弈的研究与发展[J].智能系统学报,2016,11(6):788.[doi:10.11992/tis.201609006]
WANG Yajie,QIU Hongkun,WU Yanyan,et al.Research and development of computer games[J].CAAI Transactions on Intelligent Systems,2016,11():788.[doi:10.11992/tis.201609006]
[7]黄心汉.A3I:21世纪科技之光[J].智能系统学报,2016,11(6):835.[doi:10.11992/tis.201605022]
HUANG Xinhan.A3I: the star of science and technology for the 21st century[J].CAAI Transactions on Intelligent Systems,2016,11():835.[doi:10.11992/tis.201605022]
[8]宋婉茹,赵晴晴,陈昌红,等.行人重识别研究综述[J].智能系统学报,2017,12(6):770.[doi:10.11992/tis.201706084]
SONG Wanru,ZHAO Qingqing,CHEN Changhong,et al.Survey on pedestrian re-identification research[J].CAAI Transactions on Intelligent Systems,2017,12():770.[doi:10.11992/tis.201706084]
[9]杨梦铎,栾咏红,刘文军,等.基于自编码器的特征迁移算法[J].智能系统学报,2017,12(6):894.[doi:10.11992/tis.201706037]
YANG Mengduo,LUAN Yonghong,LIU Wenjun,et al.Feature transfer algorithm based on an auto-encoder[J].CAAI Transactions on Intelligent Systems,2017,12():894.[doi:10.11992/tis.201706037]
[10]王科俊,赵彦东,邢向磊.深度学习在无人驾驶汽车领域应用的研究进展[J].智能系统学报,2018,13(1):55.[doi:10.11992/tis.201609029]
WANG Kejun,ZHAO Yandong,XING Xianglei.Deep learning in driverless vehicles[J].CAAI Transactions on Intelligent Systems,2018,13():55.[doi:10.11992/tis.201609029]
备注/Memo
收稿日期:2023-09-27。
基金项目:江苏高校“青蓝工程”项目(R2023Q07).
作者简介:吴瑞林，硕士研究生，主要研究方向为计算机视觉和缺陷检测。E-mail：ruilin_wu0516@126.com;葛泉波，教授，博士生导师，主要研究方向为多源信息融合、自主无人系统和协同目标识别。中国自动化学会青年工作委员会副主任委员、智能自动化专业委员。主持国家自然科学基金项目（共4项，其中1项重点），发表学术论文100余篇。E-mail：geqb@ nuist.edu.cn;刘华平，教授，博士生导师，主要研究方向为机器人感知、学习与控制、多模态信息融合。吴文俊人工智能科学技术奖获得者、中国人工智能学会理事。主持国家杰出青年科学基金1项、国家自然科学基金1项。发表学术论文100余篇。E-mail：hpliu@ tsinghua.edu.cn
通讯作者:刘华平. E-mail：hpliu@tsinghua.edu.cn
更新日期/Last Update:
1900-01-01