Open Access Article
Contemporary Natural Sciences DOI: .
*通讯作者： 无
发布时间: 2026-08-19 总浏览量: 24
To address the low efficiency and high subjectivity of manual diagnosis, this paper analyzes the task framework, data foundations, and principal computer vision methods used for plant disease recognition. The findings indicate that deep learning has substantially improved classification accuracy for images acquired under controlled conditions. However, occlusion, co-occurring diseases, class imbalance, and domain shift in natural environments continue to constrain practical application. Future research should strengthen cross-regional dataset development; integrate object detection, image segmentation, self-supervised learning, and multimodal information; and improve system reliability through model calibration, uncertainty estimation, and external field testing.
[1] Mohanty S P, Hughes D P, Salathé M. Using deep learning for image-based plant disease detection [J]. Frontiers in Plant Science, 2016, 7: 1419.
[2] Ferentinos K P. Deep learning models for plant disease detection and diagnosis [J]. Computers and Electronics in Agriculture, 2018, 145: 311–318.
[3] Ramcharan A, Baranowski K, McCloskey P, et al. Deep learning for image-based cassava disease detection [J]. Frontiers in Plant Science, 2017, 8: 1852.
[4] Fuentes A, Yoon S, Kim S C, et al. A robust deeplearning-based detector for real-time tomato plant diseases and pests recognition [J]. Sensors, 2017, 17(9): 2022.
[5] Singh D, Jain N, Jain P, et al. PlantDoc: A dataset for visual plant disease detection [C]// Proceedings of the 7th ACM IKDD CoDS and 25th COMAD. New York: ACM, 2020: 249–253.
[6] Barbedo J G A. Factors influencing the use of deep learning for plant disease recognition [J]. Biosystems Engineering, 2018, 172: 84–91.
投稿
审稿