Development of Tomato Leaf Disease Prediction System to the Farmers by using Artificial Intelligent Network

Tomato leaf diseases have a big impact on yield and quality. The early-stage analysis and categorization of tomato leaf diseases based on past knowledge may help to limit pathogen transmission throughout the field while also increasing crop yield. Using a Deep Convolutional Neural Network, this paper proposes developing a prediction system that classifies tomato leaf diseases. The images present in the Taiwan and Plant-Village dataset are preprocessed using the image processing approach, and features are extracted and classified using ResNet and fine-tuned ResNet-50 model. The chemical, organic control measures are recommended to the farmers based on the classification measures. The interpretation was made over the ResNet and fine-tuned ResNet-50 model. The resultant number indicates that fine-tuned ResNet has a higher accuracy of 97.6 than the other standard models. The proposed system produces improved accuracy with a lower error rate of 0.090 in the classification of tomato leaf diseases, according to this research.