CNN and Autoencoders based Hybrid Deep Learning Model for Crop Disease Detection

Indian agriculture is quite diverse and plays a vital role in the country's economic growth. The tools and techniques used in agriculture are no more primitive. With the gradual evolution of the population, this sector is under severe pressure to produce at high efficiency. One of the significant factors in improving crop harvest is the timely detection of crop diseases. The farmers use scouting to monitor their crops, which requires extensive labor and is time-consuming. Image processing-based disease identification makes the process faster and more accurate. Recently, deep learning techniques have been deployed for automatic plant disease identification. Researchers have used Convolutional Neural Networks (CNN) to predict the type of diseases in different crops accurately. Considering the advantages of autoencoders and CNN, we have proposed and developed a hybrid deep learning model based on CNN and Autoencoders to detect multiple plant diseases. The proposed architecture is fine-tuned to detect diseases of numerous crops. The proposed model provides higher accuracy when compared with similar systems. We have tested our model using the Plant village dataset containing almost 15 different types of crops.