HP-YOLO11n: A lightweight model for surface defect detection of liquor bottle caps based on improved YOLO11n

Jiting Han; Yingqian Zhang; Dazhi Yang; Haojun Liang; Feiyu Chen

doi:10.54097/qn6ex465

Authors

Jiting Han
Yingqian Zhang
Dazhi Yang
Haojun Liang
Feiyu Chen

DOI:

https://doi.org/10.54097/qn6ex465

Keywords:

Defect detection, YOLO11n, HGNetv2, P2, Bottle cap

Abstract

In production, defect detection is crucial for ensuring product quality and consumer satisfaction. To address the issues of surface defect detection in liquor bottle caps and the large number of algorithm parameters, this study improves YOLO11n and proposes a more lightweight and higher-precision HP-YOLO11n algorithm. Firstly, We employ the improved HGNetv2 backbone network as our model backbone, which makes the model more lightweight while ensuring the accuracy of model detection. Secondly, added a P2 detection layer to YOLO11n, incorporating high-resolution feature maps and rich detailed information to enhance the model's overall recognition performance. Finally, we remove the P5 layer used for detecting large targets, which reduces the number of parameters and computational load while maintaining accuracy. The experimental results show that the HP-YOLO11n algorithm achieves a mean average precision mAP@0.5 of 87.06%, which is 1.52 percentage points higher than the original YOLOv11n algorithm, while reducing the number of parameters by 44.57%, making it more accurate and lightweight.

Downloads

Download data is not yet available.

References

[1] Hu W, Chen Y, Wu Z, et al. Study on the High Quality Development of Liquor Industry[J]. World Scientific Research Journal, 2023, 9(6): 109-121.

[2] Shen Y. A Study of the Operation Strategies of Kweichow Moutai Co., Ltd[J]. Academic Journal of Business & Management, 2023, 5(11): 54-58.

[3] Wang X, Lan X, Liu L. ESW-YOLO: A lightweight YOLO model for defect detection in bottled liquor[J]. 2024.

[4] China Liquor Industry Association. (2024). Anal ysis of output trend of Chinese liquor industry in 2023-2024 [R]. Beijing: CADA

[5] Liang, S.Qin, L, Zhang, M, Chu, Y, Teng, L, He, L.Win big with small:the influence of organic food packaging size on purchase intention. Foods 11(16), 2494 (2022)

[6] Chen B, Li C, Yuan P, et al. Research on defect detection of bottle cap interior based on low-angle and large divergence angle vision system[J]. Plos one, 2024, 19(5): e0303744.

[7] Abbey J D, Kleber R, Souza G C, et al. The role of perceived quality risk in pricing remanufactured products[J]. Production and Operations Management, 2017, 26(1): 100-115.

[8] Sharma V K, Mir R N. A comprehensive and systematic look up into deep learning based object detection techniques: A review[J]. Computer Science Review, 2020, 38: 100301.

[9] HU Z, WANG C. A small object detection algorithm of remote sensing image based onim proved Faster R-CNN[J]. Computer Engineering & Science, 2024, 46(06): 1063.

[10] ZHANG R, NING Q, LEI Y, et al. Garbage detection based on Mask R-CNN[J]. Computer Engineering & Science, 2022, 44(11): 2003.

[11] Nazir A, Wani M A. You only look once-object detection models: a review[C]//2023 10th International conference on computing for sustainable global development (INDIACom). IEEE, 2023: 1088-1095.

[12] Li Y, Ren F. Light-weight retinanet for object detec tion[J]. arXiv preprint arXiv:1905.10011, 2019.

[13] Toxqui-Quitl, C, Cardenas-Franco, J., Padilla -Vivanco, A., ValdiviezoNavarro, J: Bottle inspector based on machine vision. In: Image Processing: Machine Vision Applications VI, vol. 8661, pp. 299– 308 (2013). SPIE

[14] Zhou, X, Wang, Y, Zhu, Q, Mao, J, Xiao, C, Lu, X, Zhang, H: A surface defect detection framework for glass bottle bottom using visual attention model and wavelet transform. IEEE Transactions on Industrial Informatics 16(4), 2189–2201 (2019)

[15] Sheng,Z, Wang, G. Fast method of detecting packaging bottle defects based on eca-efficientdet. Journal of Sensors 2022(1), 9518910 (2022)

[16] Vijayakumar A, Vairavasundaram S. Yolo-based object detection models: A review and its applications[J]. Multimedia Tools and Applications, 2024, 83(35): 83535-83574.Khanam R, Hussain M. Yolov11: An overview of the key architectural enhancements[J]. arXiv preprint arXiv:2410.17725, 2024.

[17] Swathi Y, Challa M. YOLOv8: advancements and innovations in object detection[C]//International Conference on Smart Computing and Communi -cation. Singapore: Springer Nature Singapore, 2024: 1-13.

[18] Khanam R, Hussain M. Yolov11: An overview of the key architectural enhancements[J]. arXiv preprint arXiv:2410.17725, 2024.

[19] Zhao Y, Lv W, Xu S, et al. Detrs beat yolos on real-time object detection[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024: 16965-16974.

[20] Zhang P, Lo E, Lu B. High performance depthwise and pointwise convolutions on mobile devices [C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34(04): 6795-6802.

[21] Wang Z, Su Y, Kang F, et al. Pc-yolo11s: a lightweight and effective feature extraction method for small target image detection[J]. Sensors, 2025, 25(2): 348.