Potato Crop abiotic stressors: interveinal Chlorosis and Leaf Curling

This dataset focuses on enabling abiotic stress detection in potato crops, necessitating annotated images of healthy leaves and leaves exhibiting symptoms of interveinal chlorosis and leaf curling. The dataset was created as part of the E-SPFdigit project (Grant Agreement No. 101157922), funded by the European Union's Horizon Europe research and innovation programme. A commercial smartphone was utilized for the RGB imaging data collection. Expert phytopathologists conducted the image capture in two locations: Volos, Magnesia, Greece for healthy potato plants in open-field conditions, and La Palma, Cartagena, Murcia, Spain for symptomatic potato plants. The dataset is comprised of 149 annotated images with four labels: Unknown, Interveinal Chlorosis, Leaf Curling and Healthy. In total there are 4,244 leaf annotations. Approximately 30% of these instances were classified as "unknown" due to visual ambiguity. The annotations are in an instance segmentation format. The dataset per class counts can be seen in the following table: Class Id Class Name Annotation Instances 0 Unknown 1239 1 Interveinal chlorosis 802 2 Leaf curling 820 3 Healthy 1383