A novel groundnut leaf dataset for detection and classification of groundnut leaf diseases

Abstract

Groundnut (Arachis hypogaea) is a widely cultivated legume crop that plays a vital role in global agriculture and food se- curity. It is a major source of vegetable oil and protein for human consumption, as well as a cash crop for farmers in many regions. Despite the importance of this crop to house- hold food security and income, diseases, particularly Leaf spot (early and late), Alternaria leaf spot, Rust, and Rosette, have had a significant impact on its production. Deep learn- ing (DL) techniques, especially convolutional neural networks (CNNs), have demonstrated significant ability for early di- agnosis of the plant leaf diseases. However, the availabil- ity of groundnut-specific datasets for training and evalua- tion of DL models is limited, hindering the development and benchmarking of groundnut-related deep learning applica- tions. Therefore, this study provides a dataset of groundnut leaf images, both diseased and healthy, captured in real culti- vation fields at Ramchandrapur, Purba Medinipur, West Ben- gal, using a smartphone camera. The dataset contains a to- tal of 1720 original images, that can be utilized to train DL models to detect groundnut leaf diseases at an early stage.