Microplastics_SEM

Here are the datasets for the paper (Automatic quantification and classification of microplastics in scanning electron micrographs via deep learning) published the Science of the Total Environment. The complete training dataset of semantic segmentation and shape classification is in dataset1.zip. The dataset of instance segmentation is present in multiple forms in dataset2.zip. The experiment setting for each micrograph was recorded together with the original SEM micrographs and all ground-truth labels in the file dataset3.zip. Main results were saved in result.zip.

Paper link: https://doi.org/10.1016/j.scitotenv.2022.153903
Code link: https://github.com/benjamin3344/Microplastics_Unet

本论文所涉数据集收录于《环境总科学》期刊发表的论文《通过深度学习自动量化与分类扫描电子显微镜下的微塑料》（Automatic quantification and classification of microplastics in scanning electron micrographs via deep learning）。语义分割与形状分类的完整训练数据集封装于dataset1.zip文件中。实例分割数据集以多种格式存储于dataset2.zip文件中。每个显微图像的实验设置、原始扫描电子显微镜图像以及所有真实标签均记录于dataset3.zip文件中。主要结果已保存于result.zip。

搜集汇总

背景与挑战

背景概述

该数据集包含用于深度学习的微塑料扫描电子显微镜图像，涵盖语义分割、形状分类和实例分割的训练数据，以及实验设置和原始图像。数据分为四个压缩文件，总大小为1.77 GB，适用于微塑料的自动量化和分类研究。