Paddy Doctor: A Visual Image Dataset for Automated Paddy Disease Classification and Benchmarking

This dataset consists of annotated paddy leaf images. The paddy leaf images were collected from real paddy fields using high-resolution smartphone cameras. The collected images were carefully cleaned and annotated with the help of an agricultural officer (AO). The final dataset contains 16,225 leaf images across 13 classes (12 diseases and healthy leaves).This dataset can be used to develop and benchmark automated paddy disease classification algorithms such as machine learning and deep learning models.