Getting affected by a disease is very common in plants due to various factors such as fertilizers, cultural practices followed, environmental conditions, etc. These diseases hurt agricultural yield and eventually the economy based on it.
Any technique or method to overcome this problem and getting a warning before the plants are infected would aid farmers to efficiently cultivate crops or plants, both qualitatively and quantitatively. Thus, disease detection in plants plays a very important role in agriculture.
Every year, more than 20% of the maize crop, is lost, due to diseases. If the diseases are detected promptly, an appropriate remedy can be applied plus crop loss can be prevented. For disease detection, regular inspection of the cornfields by experts and pathologists is needed, but this is seldom possible, due to the shortage of experts. To fulfil this gap, image classification using deep learning has proven to be very helpful.
We use a publicly available and quite famous, The PlantVillage Dataset. The dataset can be viewed from https://www.kaggle.com/emmarex/plantdisease
Due to the limited computational power, it is difficult to train the classification model locally on a majority of normal machines. Therefore, we use Google Colab notebook as it connects us to a free TPU instance quickly and effortlessly.