COMPUTER VISION BY YOLOs FOR DETECTION OF MAJOR DISEASES IN VIETNAMESE CUSTARD APPLE USING FRUIT IMAGERY
DOI:
https://doi.org/10.62985/j.huit_ojs.vol26.no2E.403Từ khóa:
Artificial intelligence, computer vision, YOLO, object detection, custard apple diseasesTóm tắt
Amid Vietnam’s rapid digital transformation in agriculture, the integration of artificial intelligence (AI) technologies for identifying, monitoring, and predicting crop pests and diseases has emerged as an inevitable trend. Custard apple (Annona squamosa L.), a high-value fruit crop, suffers significant losses due to prevalent diseases, including Anthracnose, Black Canker, Diplodia rot, Leaf Spot, and Mealybug infestations. This paper proposes a robust computer vision framework that leverages state-of-the-art YOLO (You Only Look Once)-series object detection models to enable early and accurate detection of major diseases on custard apple leaves and fruits. The proposed system is designed for practical deployment through mobile and edge-device applications in the future, empowering farmers with timely, actionable diagnostics to minimize yield losses. Furthermore, we systematically evaluate and benchmark the performance of the latest YOLO variants (YOLOv8, YOLOv11, and YOLOv12) on a large-scale, real-world custard apple disease dataset collected under diverse field conditions in Vietnam. This work not only delivers a high-performance, deployable solution but also lays the groundwork for establishing a comprehensive digital database to advance AI-driven agricultural research in Vietnam.
Tài liệu tham khảo
[1] Hoàng Gia Minh, Nguyễn Văn Hiệu, Lê Quyết Tiến, "Artificial Intelligence In Agricultural Mechanization In Vietnam: Current Applications, Challenges And Future Directions," in Rural Industry Magazine, 2025, https://congnghiepnongthon.vn/hien-trang-ung-dung--thach-thuc-va-dinh-huong-phat-trien-tri-tue-nhan-tao--ai--trong-co-gioi-hoa-nong-nghiep-tai-viet-nam-363.htm.
[2] Andreas Kamilaris, Francesc X. Prenafeta-Boldú, "Deep learning in agriculture: A survey," in Computers and Electronics in Agriculture, vol. 147, pp. 70-90, 2018, https://doi.org/10.1016/j.compag.2018.02.016.
[3] Ultralytics, YOLOv8 and YOLOv12 Documentation, 2024.
[4] Roboflow, “Roboflow Documentation: Image Annotation and Augmentation,” 2024.
[5] Ministry of Agriculture and Rural Development, “Strategy for digital transformation of Vietnam's agriculture to 2030, vision 2050,” Hanoi, 2021.
[6] Goodfellow, I., Bengio, Y., and Courville, A., Deep Learning, MIT Press, 2016.
[7] Liakos, K. G., et al., “Machine learning in agriculture: A review,” Sensors, vol 18 no 8, pp. 2674, 2018.
[8] Bùi Văn Hậu, Nguyễn Thiên Tân, Phạm Anh Tuấn, Hoàng Trọng Minh, "The Effective Application Of Crop Disease Recognition Systems In Smart Agriculture," JST-HAUI, vol. 60, no. 6, pp. 51-56, June 2024, doi: http://doi.org/10.57001/huih5804.2024.206.
[9] Jocher, G., et al., “YOLOv12 Technical Overview,” Ultralytics Documentation, 2024.
[10] Liu, W. et al., “SSD: Single Shot MultiBox Detector,” in Leibe, B., Matas, J., Sebe, N., Welling, M. (eds) Computer Vision – ECCV 2016. Lecture Notes in Computer Science, vol 9905. Springer, Cham. https://doi.org/10.1007/978-3-319-46448-0_2.
[11] SharkYun, “Computer Vision — Object Detection, One-Stage vs Two-Stage detectors,” Medium, Oct. 2024. [Online]. Available: https://sharkyun.medium.com/computer-vision-object-detection-one-stage-vs-two-stage-b05dbff88195.
[12] Ross B. Girshick, “Fast R-CNN,” 2015, https://doi.org/10.48550/arXiv.1504.08083.
[13] S. Ren, K. He, R. Girshick and J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 39, no. 06, pp. 1137-1149, June 2017, doi: 10.1109/TPAMI.2016.2577031.
[14] Mohanty SP, Hughes DP, Salathé M., “Using Deep Learning for Image-Based Plant Disease Detection,” Front Plant Sci. 2016 Sep 22;7:1419. doi: 10.3389/fpls.2016.01419. PMID: 27713752; PMCID: PMC5032846.
[15] Eman Abdullah Aldakheel, Mohammed Zakariah and Amira H. Alabdalall, “Detection and identification of plant leaf diseases using YOLOv4,” Front. Plant Sci., 22 April 2024, Sec. Plant Pathogen Interactions, Volume 15 - 2024 | https://doi.org/10.3389/fpls.2024.1355941.
[16] Li H., Shi L., Fang S., Yin F., “Real-Time Detection of Apple Leaf Diseases in Natural Scenes Based on YOLOv5,” Agriculture. 2023; 13(4):878. https://doi.org/10.3390/agriculture13040878.
[17] Liu J, Wang X, Zhu Q, Miao W., “Tomato brown rot disease detection using improved YOLOv5 with attention mechanism”, Front Plant Sci., vol. 14, 2023 Nov 20, 1289464. doi: https://doi.org/10.3389/fpls.2023.1289464
[18] Rahima Khanam and Muhammad Hussain, “A Review of YOLOv12: Attention-Based Enhancements vs. Previous Versions,” Apr. 2025. [Online]. Available: https://arxiv.org/html/2504.11995v1.
[19] Trinh Cong Dong, Mac Tuan Anh, Giap Dang Khanh, Nguyen Thanh Huong, Nguyen Trong Cac and Bui Dang Thanh, “Using deep learning in rice disease detection using YOLOv5,” Journal of Scientific Research - Sao Do University, vol. 2 no. 81, 2023, pp. 19-23. https://www.vjol.info.vn/index.php/saodo/article/view/114776/96047.
[20] Roboflow., “Roboflow Data Augmentation Documentation,” 2024. [Online]. Available: https://docs.roboflow.com/datasets/dataset-versions/image-augmentation.
