[1]LIU Youwu,ZHANG Hui,KONG Senlin,et al.Foreign object detection in pharmaceutical visible-light images using feature difference enhancement and residual distillation network[J].CAAI Transactions on Intelligent Systems,2025,20(1):118-127.[doi:10.11992/tis.202311023]
Copy

Foreign object detection in pharmaceutical visible-light images using feature difference enhancement and residual distillation network

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 20 Number of periods: 2025 1 Page number: 118-127 Column: 学术论文—智能系统 Public date: 2025-01-05
Title:
Foreign object detection in pharmaceutical visible-light images using feature difference enhancement and residual distillation network
Author(s):
LIU Youwu1;  ZHANG Hui2;  KONG Senlin1;  TAO Yan1;  LI Chong3
1. School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410114, China;
2. School of Robotics, Hunan University, Changsha 410012, China;
3. Truking Technology Limited, Changsha 410600, China
Keywords:
pharmaceutical; foreign objects; lightweight; deep learning; distillation; feature disparity; upsampling; lamp inspection
CLC:
TP391
DOI:
10.11992/tis.202311023
Abstract:
Foreign objects in pharmaceuticals are typically small, which causes difficulty for lightweight algorithms to detect them accurately, while high-performance algorithms often struggle with real-time capability. To balance real-time performance and accuracy, a deep learning distillation algorithm is proposed for the precise and rapid detection of foreign objects in pharmaceutical liquid images. The teacher network incorporates a semantic feature-based upsampling method to enhance the feature disparity between teacher and student networks. In addition, random noise is added to the training images of the student network to improve robustness in high-noise detection scenarios. To validate the effectiveness of the algorithm, a pharmaceutical liquid foreign-object dataset is collected using lamp inspection equipment, and comparative experiments are conducted. After distillation, the average precision improves by 4.1%, and the model achieves 65 frames per second, which surpasses current state-of-the-art methods. Extended experiments on the Tianchi liquor dataset show a 3.9% improvement in detection accuracy, which demonstrates the applicability of the model in similar scenarios.
References:
[1] 国家药典委员会. 中华人民共和国药典[S]. 2020年版第三部. 北京: 中国医药科技出版社, 2020: 481.
Chinese Pharmacopoeia Commission. Pharmacopoeia of People’s Republic of China[S]. Part III, 2020 Edition. Beijing: China medical science press, 2020: 481.
[2] PEREZ M, MAIGUY-FOINARD A, BARTHéLéMY C, et al. Particulate matter in injectable drugs: evaluation of risks to patients[J]. Pharmaceutical technology in hospital pharmacy, 2016, 1(2): 91-103.
[3] 徐帆, 杨伶俐, 毛盼盼, 等. 大输液包装材质与注射用药物相容性研究进展与思考[J]. 中国药业, 2014, 23(20): 91-94.
XU Fan, YANG Lingli, MAO Panpan, et al. Research advance and investigation on compatibility of large volume parenteral solution package material with injectable drugs[J]. China pharmaceuticals, 2014, 23(20): 91-94.
[4] 冯晗, 姜勇. 使用改进Yolov5的变电站绝缘子串检测方法[J]. 智能系统学报, 2023, 18(2): 325-332.
FENG Han, JIANG Yong. A substation insulator string detection method based on an improved Yolov5[J]. CAAI transactions on intelligent systems, 2023, 18(2): 325-332.
[5] 刘嘉轩, 胡非易, 张辉, 等. 上下文空间与实例信息的皮肤镜图像自监督分类[J]. 智能系统学报, 2023, 18(4): 783-792.
LIU Jiaxuan, HU Feiyi, ZHANG Hui, et al. Dermoscopic images classification based on context and instance-level feature of self-supervised learning[J]. CAAI transactions on intelligent systems, 2023, 18(4): 783-792.
[6] 郑广智, 彭添强, 肖计春, 等. 基于语义信息增强的化纤丝线网络度检测方法[J]. 自动化学报, 2024, 50(10): 1963-1976.
ZHENG Guangzhi, PENG Tianqiang, XIAO Jichun, et al. A detection method for the interlacing degree of filament yarn based on semantic information enhancement[J]. Acta automatica sinica, 2024, 50(10): 1963-1976.
[7] 康守强, 邢颖怡, 王玉静, 等. 基于无监督深度模型迁移的滚动轴承寿命预测方法[J]. 自动化学报, 2023, 49(12): 2627-2638.
KANG Shouqiang, XING Yingyi, WANG Yujing, et al. Rolling bearing life prediction based on unsupervised deep model transfer[J]. Acta automatica sinica, 2023, 49(12): 2627-2638.
[8] 闫涵, 卢伟, 吴玉虎. 基于轻量化卷积神经网络的金属断口图像识别[J]. 控制与决策, 2024, 39(9): 2858-2866.
YAN Han, LU Wei, WU Yuhu. Metal fracture recognition based on lightweight convolutional neural network[J]. Control and decision, 2024, 39(9): 2858-2866.
[9] WANG Sirui, ZHUO Qing, XIA Ji’an. Detection of glass chips in liquid injection based on computer vision[C]//2015 International Conference on Computational Intelligence and Communication Networks. Jabalpur: IEEE, 2015: 329-331.
[10] DAI Jinzhi. Retracted: drug residue detection system for infusion based on machine vision[C]//2016 International Conference on Smart City and Systems Engineering. Hu’nan: IEEE, 2016: 571-574.
[11] ZHANG Hui, LI Xuanlun, ZHONG Hang, et al. Automated machine vision system for liquid particle inspection of pharmaceutical injection[J]. IEEE transactions on instrumentation and measurement, 2018, 67(6): 1278-1297.
[12] ZHANG Hui, ZHAO Miao, LIU Li, et al. Deep multimodel cascade method based on CNN and random forest for pharmaceutical particle detection[J]. IEEE transactions on instrumentation and measurement, 2020, 69(9): 7028-7042.
[13] YI Junfei, ZHANG Hui, MAO Jianxu, et al. Pharmaceutical foreign particle detection: an efficient method based on adaptive convolution and multiscale attention[J]. IEEE transactions on emerging topics in computational intelligence, 2022, 6(6): 1302-1313.
[14] EVERINGHAM M, VAN GOOL L, WILLIAMS C K I, et al. The pascal visual object classes (VOC) challenge[J]. International journal of computer vision, 2010, 88(2): 303-338.
[15] WANG Jiabao, CHEN Yuming, ZHENG Zhaohui, et al. CrossKD: cross-head knowledge distillation for object detection[EB/OL]. (2023-06-20)[2023-11-17]. https://arxiv.org/abs/2306.11369.
[16] HU Jie, SHEN Li, SUN Gang. Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7132-7141.
[17] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[M]//Lecture Notes in Computer Science. Cham: Springer International Publishing, 2018: 3-19.
[18] PARK J, WOO S, LEE J Y, et al. BAM: bottleneck attention module[EB/OL]. (2018-07-17)[2023-11-17]. https://arxiv.org/abs/1807.06514.
[19] YANG Lingxiao, ZHANG Ruyuan , LI Lida, et al. Simam: a simple, parameter-free attention module for convolutional neural networks[C]//Proceedings of the 38th International Conference on Machine Learning. Online: PMLR, 2021: 11863-11874.
[20] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
[21] LIN T Y, DOLLáR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 936-944.
[22] LI Xiang, WANG Wenhai, WU Lijun, et al. Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection[C]//Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc. , 2020, 33: 21002-21012.
[23] WANG Jiaqi, CHEN Kai, XU Rui, et al. CARAFE: content-aware reassembly of features[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 3007-3016.
[24] REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union: a metric and a loss for bounding box regression[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 658-666.
[25] ZHENG Zhaohui, YE Rongguang, WANG Ping, et al. Localization distillation for dense object detection[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 9397-9406.
[26] SUN Siqi, CHENG Yu, GAN Zhe, et al. Patient knowledge distillation for BERT model compression[EB/OL]. (2019-08-25)[2023-11-17]. https://arxiv.org/abs/1908.09355.
[27] ZHANG Haoyang, WANG Ying, DAYOUB F, et al. VarifocalNet: an IoU-aware dense object detector[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 8510-8519.
[28] ZHANG Shifeng, CHI Cheng, YAO Yongqiang, et al. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 9756-9765.
[29] FENG Chengjian, ZHONG Yujie, GAO Yu, et al. TOOD: task-aligned one-stage object detection[C]//2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 3490-3499.
[30] CHEN Qiang, WANG Yingming, YANG Tong, et al. You only look one-level feature[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 13034-13043.
[31] CHEN Fangyi, ZHANG Han, HU Kai, et al. Enhanced training of query-based object detection via selective query recollection[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023: 23756-23765.
Similar References:

Memo

-

Last Update: 2025-01-05

Copyright © CAAI Transactions on Intelligent Systems