Cretan Pollen Dataset v1 (CPD-1)

Pollen analysis and the classification of several pollen species is an important task in melissopalynology. The development of classification models depends on available datasets of pollen grains from various plant species from around the globe. In this paper, Cretan Pollen Dataset v1 (CPD-1) is presented, which is a novel dataset of grains from 20 pollen species from plants gathered in Crete, Greece. The pollen grains were prepared and stained with fuchsin, in order to be captured by a camera attached to a microscope under x400 magnification. In addition, a pollen grain segmentation method is presented, which segments and crops each unique pollen grain and achieved an overall detection accuracy of 92%. The final dataset comprises 4034 segmented pollen grains of 20 different pollen species as well as the raw data and ground truth, as annotated by an expert. The developed dataset is publicly accessible, which we hope will accelerate research in melissopalynology. Files included in this dataset: Cropped Pollen Grains: This folder contains all the segmented pollen grains with the background present. Isolated Pollen Grains: This folder contains all the segmented pollen grains with the background removed. Raw Data/Images: This folder contains all the original raw images, as captured by the camera attached to the microscope. Raw Data/Annotations: This folder contains a '.csv' file for every pollen type, which contains the annotations for the pollen grains' bounding boxes. A bounding box is represented by its upper left corner (x,y) as well as its width and height (w,h). In addition, each annotation points to a specific image file of that pollen type.