Intelligent Disease Detection in Tomato Leaves Using Dense Neural Networks

Grain Production is the most significant field.Many Nations have taken steps to restrict the grain exports as COVID-19 expanded all over the world.one of the major concern affecting economies today is how to increase grain output.Crop diseases are a challenging issue for farmers,though,it’s crucial to understand their severity as soon as possible in order to assist staff in taking additional steps to prevent further plant infection. A Restructured residual dense network was proposed for tomato leaf disease identification;this hybrid deep learning model combines deep residual networks and dense networks,which improves the flow of information and gradients while reducing the number of training process parameters to increase computation accuracy.On the Tomato test dataset,experimental findings demonstrate that this model can reach top-1 average identification accuracy of 95%,the RDN model may outperform the majority of state-of-the-art model by considerable margin using less computing power to attain superior results. Keywords: Residual Dense Network, Flow of gradients, Deep Learning, State-of-the-art-model.