Application Research of Deep Learning in Crop Leaf Disease Detection

DOI: https://doi.org/10.62517/jlsa.202507406

Author(s)

Ran Tao, Qianqian Li*, Yuhang Chen

Affiliation(s)

School of Artificial Intelligence and Software, Kewen College, Jiangsu Normal University, Xuzhou, Jiangsu, China

Abstract

Crop leaf diseases have become a critical bottleneck in improving agricultural productivity and quality. Traditional manual and laboratory detection methods suffer from inefficiency, environmental and operator-dependent accuracy, and limitations in large-scale field applications. Integrating leaf disease detection with object recognition technology has emerged as a rapidly developing research direction for smart agriculture. The YOLO series of deep learning algorithms demonstrates significant advantages in target recognition. This study utilizes the YOLOv8 algorithm to develop a crop leaf disease identification model. Based on this model, we designed and implemented an intuitive system featuring login/registration, image recognition, and model switching functions. The system adopts a modular and hierarchical architecture, utilizes the PyQt framework for user-friendly interfaces, and employs the SQLite database for data storage. This innovation enhances the efficiency and accuracy of agricultural pest detection, providing robust support for modern farming practices.

Keywords

Deep Learning; Disease Recognition; Yolov8; Crop Leaf; Recognition System

References

[1] Zhou Yang, Yang Puyun, Zhao Zhonghua, et al. Characteristics of Occurrence and Control of Major Crop Diseases and Pests in China in 2016 and Key Points of Control Work in 2017. China Plant Protection Guide, 2017, 37(05):60-64. [2] Wang Zhehao. Research on Tomato Leaf Disease Recognition and Classification Based on Convolutional Neural Network. Wuhan Polytechnic University, 2023. [3] Tan Zhifeng, He Zhilei, Zhang Lei, et al. Review on the Application of Deep Learning Technology in Crop Pest and Disease Identification. Hebei Agriculture, 2024, (01):30-32. [4] Zhou Jianglong, Wang Tianyi, Li Lun, et al. A lightweight crop leaf disease recognition model Based on Deep learning. Jiangsu Agricultural Sciences, 2024, 52 (16): 230-238. [5] Xu Xuefeng. Analysis of the Current Situation and Control Techniques of Crop Pests and Diseases in the New Era. Hebei Agriculture, 2024, (01):71-72. [6] Research on Corn Leaf Pest and Disease Identification System Based on Improved YOLOv5s Hu Mengjiao Hebei Normal University of Science and Technology 2023. [7] Xu Hongmei. Analyzing the Application of SQlite in Python. Neijiang Science and Technology, 2023, 44(04):60-61. [8] Dong Qin, Yang Guoyu. Crop Pest and Disease Identification Based on Optimized CBAM and Improved YOLOv5. Applications of Computer Systems, 2023, 32(07):261-268. [9] Tao Zhi, Kong Jianlei, Jin Xuebo, et al. Design of an APP System for Crop Pest and Disease Image Recognition Based on Deep Learning . Computer Applications and Software, 2022, 39(03):341-345. [10] Zhu Deming, Cheng Xiangping, Qiu Yijian, et al. Research Progress of Crop Image Recognition Technology Based on Deep Learning . Jiangxi Science, 2025, 43 (01): 154-161.