鉴定(生物学)
残差神经网络
农业
人工智能
深度学习
学习迁移
精确性和召回率
农学
机器学习
计算机科学
农业工程
生物技术
生物
工程类
植物
生态学
作者
Rahul Singh,Neha Sharma,Rupesh Gupta
标识
DOI:10.1109/icces57224.2023.10192642
摘要
Corn leaf disease significantly impacts the food industry and the yield of corn crops, as corn is an essential and fundamental source of nutrition for humans, especially vegetarians and vegans. As a result, corn quality must be optimal; nevertheless, to achieve this, corn must be protected against several diseases. Consequently, early detection and diagnosis of plant diseases must be a top priority. This article uses plant images to focus on the ResNet 18 transfer learning model for corn plant disease detection. Recent research has demonstrated that ResNet 18 can accurately detect and diagnose corn leaf diseases. This trained model can be applied to the analysis of real-time images for accurate identification and classification of corn leaf diseases. These results are incredibly encouraging, as they indicate that the model can accurately identify all four types of corn leaf diseases with high precision, recall, and F1-Scores. The model's accuracy was increased by evaluating each parameter to 96%. Our findings suggest that the ResNet 18 model is a promising method for accurately and efficiently classifying corn leaf disease. This may have significant implications for the management and prevention of agricultural conditions.
科研通智能强力驱动
Strongly Powered by AbleSci AI