High-resolution Microscopic Image Dataset of Freshwater Plankton in Japanese Lakes and Reservoirs (FREPJ): I. Zooplankton

“Zooplankton images” is a dataset recorded in “High-resolution Microscopic Image Dataset of Freshwater Plankton in Japanese Lakes and Reservoirs (FREPJ): I. Zooplankton” by “Yurie Ohtake, Aoi Osone, Wataru Makino, Koichi Ito, Takafumi Aoki, Kanta Miura, Yoshinobu Hayakawa, RyotaroYoshida, Satoshi Ichise, Akihiro Tuji and Jotaro Urabe”. It contains a total of 88,653 images of 214 freshwater zooplankton taxa collected from 87 lakes and reservoirs located in different areas of the Japanese archipelago. 
In the dataset, the images are stored in separate 40x and 100x folders, named “images_40” and “images_100” respectively. In these two folders, each folder name corresponds to a taxonomic label (phylum, class, order, family, genus, and species) and contains the images labeled with them. 
To obtain these images, a single large photograph for was first taken by scanning each zooplankton sample with a high-resolution camera installed in an intelligent microscope. Then, each plankton individual was cropped and extracted from the photograph as a single image, classified and labeled with multiple taxonomic ranks (phylum, class, order, family, genus, and species), and stored in the dataset. 
Metadata of this dataset is shown as “meta_data.docx”. Table S1 shows the information of sampling sites and date. Table S2 shows links between labels attached to each plankton image and classification information. Table S3 and S4 show the sampling location and sampling date for each individual plankton image in 40x and 100x folders. The present dataset will be useful not only as an atlas of freshwater zooplankton in Japan, but also for the construction, training, and evaluation of an automatic plankton identification and enumeration system based on machine learning.

《浮游动物图像》数据集由Yurie Ohtake、Aoi Osone、Wataru Makino、Koichi Ito、Takafumi Aoki、Kanta Miura、Yoshinobu Hayakawa、Ryotaro Yoshida、Satoshi Ichise、Akihiro Tuji及Jotaro Urabe共同录制于《日本湖泊与水库淡水浮游生物高分辨率显微镜图像数据集（FREPJ）：I. 浮游动物》一书中。该数据集总计收录了来自日本群岛不同区域的87个湖泊和水库中采集的214种淡水浮游动物共计88,653张图像。在该数据集中，图像被存储于名为“images_40”和“images_100”的独立文件夹中，分别对应40倍和100倍的放大倍数。这两个文件夹中的每个文件夹名称均对应一个分类标签（门、纲、目、科、属和种），并包含带有相应标签的图像。为了获取这些图像，首先使用安装在智能显微镜中的高分辨率相机对每个浮游动物样本进行扫描，拍摄单一的大照片。随后，从照片中裁剪并提取每个浮游生物个体作为单一图像，对其进行分类并标注多个分类等级（门、纲、目、科、属和种），并存储于数据集中。该数据集的元数据以“meta_data.docx”的形式呈现。表S1展示了采样地点和日期的信息。表S2展示了附加在每个浮游动物图像上的标签与分类信息之间的联系。表S3和S4展示了40倍和100倍文件夹中每个个体浮游动物图像的采样地点和采样日期。本数据集不仅可用作日本淡水浮游动物的图谱，亦可用于基于机器学习的自动浮游生物识别和计数系统的构建、训练与评估。