GRASP-125: A Dataset for Greek Vascular Plant Recognition in Natural Environment

Plant identification from images has become a rapidly developing research field in computer vision and is particularly challenging due to the morphological complexity of plants. The availability large databases plant images, advancements image processing, pattern recognition machine learning, have resulted number remarkably accurate reliable image-based techniques, overcoming time expertise required for conventional identification, which feasible only expert botanists. In this paper, we introduce GReek vAScular Plants (GRASP) dataset, set composed 125 classes different species, automatic vascular plants Greece. context, describe methodology data acquisition dataset organization, along with statistical features dataset. Furthermore, present results application popular deep learning architectures classification Using transfer report 91% top-1 98% top-5 accuracy.