Supporting data for "SeedGerm-VIG: an open and comprehensive pipeline to quantify seed vigour in wheat and other cereal crops using deep learning powered dynamic phenotypic analysis"

As one of the most important cereal crops, wheat (<i>Triticum aestivum</i> L.) production and grain quality are essential to many nations in the world. Early developmental phases such as seed germination and seedling establishment are key to wheats growth and development as they impact directly on crops early performance and yield potential. Hence, it is critical to develop a dataset for seed germination. <br>This study presents a dataset of "SeedVig-phase" consisting of 776 images at IMB, 720 at PRO, 784 during RE and 773 during SE for phase detection, and a ''SeedVig-traits" dataset containing 1,932 seeds, 2,106 seeds with roots and seedlings, and 2,040 seedlings for mask segmentation. <br>The "SeedVig-phase" dataset is used to train YOlOv8x-Germ model while the "SeedVig-traits" dataset is used to train Unet models.