project-oceania/isiisnet

ISIISNet数据集包含2016年7月在西北地中海使用原位鱼卵成像系统（ISIIS）捕获的浮游生物图像。这些图像使用定制的软件apeep进行处理，并通过深度分割器提取感兴趣的区域，这些区域被目标为浮游生物。最终，408,166个对象根据通用的分类指南被分类为32个分类单元。为了训练机器学习分类器，每个类别的图像被分为训练集、验证集和测试集，比例分别为70%、15%和15%。

The ISIISNet dataset contains plankton images captured in July 2016 using the In Situ Ichthyoplankton Imaging System (ISIIS) in the North Western Mediterranean Sea. These images were processed with custom software apeep and regions of interest were extracted, targeted to be planktonic organisms by a deep segmenter. The resulting 408,166 objects were sorted into 32 taxa following a common taxonomic guide. For the purpose of training machine learning classifiers, the images in each class were split into training, validation, and test sets with proportions of 70%, 15%, and 15% respectively.