Keywords
YOLOv8
Deep learning
Lightweight
Image detection
Submitted : 2025-09-17
Accepted : 2025-10-02
Published : 2025-10-17
Abstract
Addressing challenges in accurately detecting persimmon fruit quality in orchards—such as reliance on manual grading, low efficiency, severe foliage obstruction, and subtle differences between quality grades—this paper proposes a lightweight persimmon detection model based on an improved YOLOv8s architecture. First, the Conv layer in the backbone network is replaced with an ADown module to reduce model complexity. Second, MSFAN is introduced in the Neck layer to fully extract texture features from persimmon images, highlighting differences between quality grades. Finally, the Wise-IoU loss function mitigates the impact of low-quality sample data on grading accuracy. The improved model accurately identifies and separates persimmons of varying quality, effectively addressing quality grading detection in complex backgrounds. This provides a viable technical approach for achieving persimmon quality grading detection.
References
Gao R, Huang Y, Zhao W, et al., 2023, Current Status and SWOT Analysis of Luotian Sweet Persimmon Industry Development in Luotian County. Southern China Fruit, 52(03): 212–218.
Guo X, Chang Y, Huang J, et al., 2022, Rural Revitalization: A Promising Path for Persimmon Industry!—Development Strategies for Guangxi’s Persimmon Industry in the Context of Rural Revitalization. Southern Horticulture, 33(3): 78–84.
Huo P, 2023, Development Countermeasures for Guangxi Zhuang Autonomous Region’s Fruit Industry Based on SWOT Analysis. Rural Science and Technology, 14 (11): 42–45.
Li F, 2022, An Exploration of Intelligent Technology Applications in Modern Agricultural Machinery. Rural Practical Technology, (3): 110–111.
Gao M, 2022, Research on the Application of New Agricultural Machinery Technologies in Rural Production. Farmer’s Wealth Companion, (23): 87–89.
Pan M, 2021, Application of Machine Vision Technology in Field Agricultural Machinery. Automation Technology and Application, 40(08): 163–166.
He D, Yang Q, Xue S, et al., 1998, Research on Computer Vision Grading Technology for Fruit Surface Color. Transactions of the Chinese Society for Agricultural Engineering, (03): 207–210.
Tao Y, Heinemann PH, Varghese Z, et al., 2013, Machine Vision for Color Inspection of Potatoes and Apples. Transactions of the ASAE, 38(5): 1555–1561.
Sofu MM, Er O, Kayacan MC, et al., 2016, Design of an Automatic Apple Sorting System Using Machine Vision. Computers and Electronics in Agriculture, 2016: 395–405.
Huang C, Fei J, 2017, An Online Grading Method for Apples Based on Image Feature Fusion. Transactions of the Chinese Society for Agricultural Engineering, 33(01): 285–291.
Huang F, 2016, Research on Quality Detection and Variety Identification of Nectarines Based on Hyperspectral Imaging Technology, dissertation, Shanxi Agricultural University.
Ma G, 2022, Research on Pear Quality Detection and Grading System Based on Machine Vision, dissertation, Hebei Normal University of Science and Technology.
Huang Y, Li N, Liu Z, et al., 2023, Classification Method for Grape Disease-Affected Leaves Using an Improved Lightweight Convolutional Network. Journal of Harbin University of Science and Technology, 28(03): 1–9.
Liu Z, Ding Y, 2020, Research on Recognition Methods for Occluded Fruits in Natural Environments. Research on Computer Applications, 37(S2): 333–335, 339.
Zhang Z, Zhou J, Jiang Z, et al., 2024, Apple Recognition Method in Natural Orchard Environments Based on an Improved YOLOv7 Lightweight Model. Transactions of the Chinese Society for Agricultural Machinery, 55(3): 231–242.
Qiu P, Su Z, Jia Y, 2023, Research on Surface Damage Detection of Fragrant Pears Using Machine Vision. Information Systems Engineering, (12): 133–136.
Sun X, 2023, Research on Apple Appearance Quality Grading Using Residual Neural Networks, dissertation, Shandong Technology and Business University.
Wang CY, Yeh IH, Mark Liao HY, 2024, YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information, European Conference on Computer Vision, Springer Nature Switzerland, Cham, 1–21.