Detection and Identification of Tomato Disease Based on Deep Learning and Machine Learning algorithms

Plant diseases negatively affect crop production; the quality and the quantity of crop production are being interrupted. Identifying diseases manually is a hard task and time consuming, also the majority of farmers don't have the necessary knowledge to do this operation. So, we need agriculture engineer which are rare. To address these issues, we need an accurate and automated detection system for crop disease. A new technique based on deep learning to detect crop disease is required. In this paper, we propose a new technique called ALS-NN (Autoencoder Latent Space - Neural network) which combines two models Autoencoder and Neural Network. The Autoencoder compress data into Latent Space representation, and the Neural Network is used for classification based on compressed data. The dataset used in this paper is PlantVillage with 4 types of Tomato diseases. Our system achieved 91% accuracy.