Microscopic Pollen Species Image Database
收藏资源简介：
Description This repository contains microscopic pollen species images, binary ground truth segmentation masks, and classification data developed for automated pollen detection, overlapping pollen separation, and species classification research. Repository Contents Imaging modality: Optical microscopy Application: Pollen species classification Overlapping object segmentation Number of pollen species: 12 Total pollen grains: 618 Total microscopic images: 390 Ground truth: Binary segmentation masks Pollen Species Included Class Common Name Scientific Name Pollen Samples Images 1 Huisache Acacia farnesiana 49 45 2 Alfalfa Medicago sativa 47 29 3 Nettle-leaved goosefoot Chenopodium murale 60 31 4 Chicken foot grass Cynodon dactylon 37 34 5 Grass bitter Helianthus ciliaris 43 34 6 White mulberry Morus alba 57 24 7 Pecan Carya illinoensis 32 31 8 Olive Olea europaea 28 28 9 Honey mesquite Prosopis glandulosa 86 50 10 Willow Salix spp. 64 30 11 Pepper tree Schinus molle 78 23 12 Johnson grass Sorghum halepense 34 31 Total Dataset Total pollen grains: 618 Total images: 390 The images provided in this dataset were generated in: TELLO-MIJARES, Santiago; FLORES, Francisco.A Novel Method for the Separation of Overlapping Pollen Species for Automated Detection and Classification.Computational and Mathematical Methods in Medicine, 2016, Vol. 2016, Article ID 5689346.
