Small microplankton (MicroS) FlowCam Plankton Images version_0.1

Work in progress (last modified 2022-04-06). Manually sorted and annotated plankton images obtained using a FlowCam 8400 Yokogawa Fluid Imaging Technologies (camera and microscope system) equipped with a 10x objective lens and a 100µm deep field-of-view flowcell (magnification = 100). The size of one pixel is 0.7330 µm. The images have been sorted into a taxonomical folder structure according to phylogeny (e.g. Family – Order – Genus - Species). This version (last modified: 2022-04-06) is incomplete in the phylogenetic organization of the folders. Plankton sizes range from 5-100 µm ABD (Area Based Diameter). The plankton samples were ~50 ml carefully filtered through 80 µm mesh to remove large organisms that will clog the flowsystem. Both live and lugol fixed samples were imaged for this dataset, with an overweight of live samples. Samples originated from the tidal zone in Flødevigen. This version of the dataset needs further improvement (number of images in each class) in order to train a machine learning model and apply it for the classification of real plankton samples. As a preliminary data-set it was intended to investigate machine-learning algorithms. There may be misplaced images and misannotations.

本数据集尚在完善中（最后更新于2022年4月6日）。本数据集包含经人工分拣与标注的浮游生物图像，采集自横河流体成像技术公司（Yokogawa Fluid Imaging Technologies）生产的FlowCam 8400型相机显微镜系统，该系统搭载10倍物镜与100微米景深流动池，放大倍数为100倍。单像素尺寸为0.7330微米。所有图像已依据系统发育关系，按照科-目-属-种的分类学文件夹层级结构进行归类。本版本（最后更新于2022年4月6日）的文件夹系统发育组织尚未完善。浮游生物尺寸范围为5至100微米ABD（面积等效直径，Area Based Diameter）。实验所用浮游生物样本约50毫升，经80微米滤网精细过滤以去除可能堵塞流动系统的大型生物。本数据集涵盖活体与鲁哥氏（Lugol）固定两种样本的成像结果，其中活体样本占比更高。样本采集自弗勒德维根（Flødevigen）潮间带区域。为训练机器学习模型并将其应用于实际浮游生物样本分类，本版本数据集仍需进一步优化（如补充各分类类别的图像数量）。作为预实验数据集，本数据集最初用于探究机器学习算法的应用效果。数据集内可能存在图像归类错误与标注偏差。