Abstract
[Objective] To improve the accuracy of liquor packaging defect detection. [Methods] A detection model based on an improved YOLOv 8n is proposed.The ADown module is introduced into the model to effectively reduce parameter count and computational load while maintaining the original feature extraction capability.Large separable kernel attention (LSKA ) is integrated into the spatial pyramid pooling fusion (SPPF ) structure to further enhance the model's ability to capture and extract multi -scale features.In addition, the original CIOU loss function is replaced with the Inner -WIoU loss function, which combines Inner -IoU and Wise -IoU, thereby improving detection accuracy and accelerating model convergence. [Results] On a self -built liquor packaging dataset, the improved YOLOv 8n model achieves an average precision of 86.4%, representing a 5.2% improvement over the original model.Moreover, the parameter count is reduced by 4.9%, and computation is reduced by 6.6%. [Conclusion] The model can meet the real -time detection requirements of liquor packaging.
Publication Date
12-11-2025
First Page
215
Last Page
224
DOI
10.13652/j.spjx.1003.5788.2024.81107
Recommended Citation
Gangjian, HE; Shuiling, ZENG; Fangcong, LIN; Shuo, XIANG; and Jiaxiong, ZHANG
(2025)
"Defect detection of liquor packaging based on improved YOLOv 8n,"
Food and Machinery: Vol. 41:
Iss.
11, Article 28.
DOI: 10.13652/j.spjx.1003.5788.2024.81107
Available at:
https://www.ifoodmm.cn/journal/vol41/iss11/28
References
[1] LIU W,ANGUELOV D,ERHAN D,et al.SSD:single shot multibox detector [C]// Computer Visio-ECCV 2016:14th European Conference.Amsterdam:Springer International Publishing,2016:21-37.
[2] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:unified,real-time object detection [C]// 2016 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE Press,2016:779-788.
[3] WANG C Y,BOCHKOVSKIY A,LIAO H Y M.YOLOv 7:trainable bag-of-freebies sets new state-of-the-art for real-time object detectors [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Vancouver:IEEE,2023:7 464-7 475.
[4] REDMON J,FARHADI A.YOLO 9000:better,faster,stronger[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Hawaii:IEEE,2017:7 263-7 271.
[5] GIRSHICK R.Fast R-CNN [C]// Proceedings of the IEEE International Conference on Computer Vision.Santiago:IEEE Press,2015:1 440-1 448.
[6] 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 and Machine Intelligence,2017,39(6):106680.
[7] 夏军勇,王康宇,周宏娣.基于改进 Faster R-CNN 的食品包装缺陷检测 [J].食品与机械,2023,39(11):131-136,151.XIA J Y,WANG K Y,ZHOU H D.Food packaging defect detection by improved network model of Faster R-CNN [J].Food & Machinery,2023,39(11):131-136,151.
[8] 李 志 诚,曾 志 强.基 于 改 进 YOLOv 3的 卷 纸 包 装 缺 陷 实 时 检测算法 [J].中国造纸学报,2022,37(2):87-93.LI Z C,ZENG Z Q.Real-time defect detection algorithm for roll paper packaging based on improved YOLOv 3[J].Transactions of China Pulp and Paper,2022,37(2):87-93.
[9] 李建明,杨挺,王惠栋.基于深度学习的工业自动化包装缺陷检测方法 [J].包装工程,2020,41(7):175-184.LI J M,YANG T,WANG H D.An industrial automation packaging defect detection method based on deep learning [J].Packaging Engineering,2020,41(7):175-184.
[10] 叶宇星,孙志锋,马风力,等.基于改进 YOLOv 5s的腌制蔬菜真空包装缺陷检测 [J].包装工程,2023,44(9):45-53.YE Y X,SUN Z F,MA F L,et al.Vacuum packaging defect detection of pickled vegetables based on improved YOLOv 5s[J].Packaging Engineering,2023,44(9):45-53.
[11] 曾 秀 云,陆 华 才,吕 禾 丰.基 于 改 进 Faster R-CNN 的 棉 布 包(4):179-186.ZENG X Y,LU H C,LYU H F.Research on cotton packaging defect detection method based on improved Faster R-CNN [J].Journal of Electronic Measurement and Instrumentation,2022,36(4):179-186.装 缺 陷 检 测 的 方 法 研 究 [J].电 子 测 量 与 仪 器 学 报,2022,36
[12] LIN G J,LIU K Y,XIA X K,et al.An efficient and intelligent detection method for fabric defects based on improved YOLOv 5[J].Sensors,2022,23(1):97.
[13] WANG C Y,YEH I H,MARK LIAO H Y.Yolov 9:learning what you want to learn using programmable gradient information [C]// European Conference on Computer Vision.Cham:Springer Nature Switzerland,2025:1-21.
[14] LAU K W,PO L M,REHMAN Y A U.Large separable kernel attention:rethinking the large kernel attention design in CNN[J].Expert Systems with Applications,2024,236:121352.
[15] ZHENG Z,WANG P,REN D,et al.Enhancing geometric factors in model learning and inference for object detection and instance segmentation [J].IEEE Transactions on Cybernetics,2021,52(8):8 574-8 586.
[16] 张 嘉 雄,曾 水 玲,李 昭 贤.基 于 改 进 YOLOv 7的 钢 板 表 面 缺陷 检 测 的 方 法 [J/OL ].控 制 工 程.(2024 -04-01) [2024 -09-15].https://doi.org/10.14107 /j.cnki.kzgc.20231034.ZHANG J X,ZENG S L,LI Z X.Method for surface defect detection in steel plates based on improved YOLOv 7 [J/OL ].Control Engineering of China.(2024 -04-01) [2024 -09-15].https://doi.org/10.14107 /j.cnki.kzgc.20231034.
[17] TONG Z,CHEN Y,XU Z,et al.Wise-IoU:bounding box regression loss with dynamic focusing mechanism [J/OL ].ArXiv.(2023 -01-24) [2024 -09-28].https://arxiv.org/abs/ 2301.10051.
[18] ZHANG H,XU C,ZHANG S.Inner-IoU:more effective intersection over union loss with auxiliary bounding box [J/OL].ArXiv.(2023 -11-06) [2024 -09-28].https://arxiv.org/abs/2311.02877.
[19] LV W Y,XU S L,ZHAO Y A,et al.DETRs beat YOLOs on real-time object detection [C]// proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR ).Seattle:IEEE,2024:16 965-16 974.
[20] WANG A,CHEN H,LIU L,et al.Yolov 10:real-time end-toend object detection [J].Advances in Neural Information Processing Systems,2024,37:107 984-108 011.
[21] FENG C J,ZHONG Y J,GAO Y,et al.TOOD:task-aligned one-stage object detection [C]// 2021 IEEE/CVF International Conference on Computer Vision.New York:IEEE Press,2022:3 490-3 499.
[22] ZHANG H,LI F,LIU S,et al.Dino:detr with improved denoising anchor boxes for end-to-end object detection [J/OL ].ArXiv.(2022 -03-07) [2024 -09-28].https://arxiv.org/abs/ 2203.03605.
[23] ZHANG S F,CHI C,YAO Y Q,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.New York:IEEE Press,2020:9 756-9 765.
[24] LIN T Y,GOYAL P,GIRSHICK R,et al.Focal loss for dense object detection [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(2):318-327.
