The biggest threat to the safety of food is plant diseases. They have the ability to dramatically lower the quantity and quality of agricultural products. Recognizing plant diseases is the biggest issue in the agricultural industries. Convolutional Neural Networks (CNN) are effective in solving image classification problems in computer vision. Numerous deep learning architectures have been used to diagnose plant diseases. This study presents a transfer learning-based model for identifying diseases in plant leaves. In this paper, a CNN classifier based on transfer learning model called DenseNet201 are proposed. An analysis of four deep learning models (VGG16, Inception V3, ResNet152V2, and DenseNet201) done to see which one can detect plant diseases with the greatest degree of accuracy. Web based application developed for plant disease diagnosing from defected leaf image and the proposed model which identify the disease and give the recommended treatment. The used images dataset contains 28310 leaves photos of 3 crops, tomato, potato and pepper divided into 15 different classes, 9 disorders and one healthy class for tomato, 2 disorders and one healthy class for potato and 1 disorder and one healthy for pepper. In our experimental, the results shows that the proposed model achieves the highest training accuracy of 99.44% and validation accuracy of 98.70%.
Plant diseases are a foremost risk to the safety of food. They have the potential to significantly reduce agricultural products quality and quantity. In agriculture sectors, it is the most prominent challenge to recognize plant diseases. In computer vision, the Convolutional Neural Network (CNN) produces good results when solving image classification tasks. For plant disease diagnosis, many deep learning architectures have been applied. This paper introduces a transfer learning based model for detecting tomato leaf diseases. This study proposes a model of DenseNet201 as a transfer learning-based model and CNN classifier. A comparison study between four deep learning models (VGG16, Inception V3, ResNet152V2 and DenseNet201) done in order to determine the best accuracy in using transfer learning in plant disease detection. The used images dataset contains 22930 photos of tomato leaves in 10 different classes, 9 disorders and one healthy class. In our experimental, the results shows that the proposed model achieves the highest training accuracy of 99.84% and validation accuracy of 99.30%.
Seven pot experiments were conducted to study the direct and the accumulative effect of urea containing (0.4, 1.0, 1.5, 2.0, 3.0 and 4.0 %) biuret on the growth of rice, wheat, and maize plants and their N content and N uptake in two fine textured alluvial soils and one sandy clay loam (highly calcareous) soil. It was found that both rice and wheat grain yields were not significantly reduced in all soils where urea containing high percentage of biuret was used namely 3 % and 4 %. Ammonium sulphate fertilizer was superior to urea in plant production only in the sandy clay loam. Moreover, the N recovery was higher in the alluvial soils in comparison to the sandy clay loam. The accumulative addition of biuret to the soils did not further reduce either the growth rate or the N uptake of the plants.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.