Secondary Electron Hyperspectral Images Dataset For Machine Learning and Computer Vision Application

Read full text
Authors: Ali Alsari, Jingqiong Zhang, Nicholas T. H. Farr, Cornelia Rodenburg, Lyudmila Mihaylova
Cited by: 0

Abstract

This data repository can be used as benchmark data for material characterization, particularly for investigating nanostructures and chemical properties in materials using SEHI (Secondary Electron Hyperspectral Imaging), as well as research in Scanning Electron Microscopy and Secondary Electron (SE) spectroscopy, and advanced image processing and data analysis ( image registration, super resolution, ..) techniques.This work is supported by the UK EPSRC EP/V012126/1, the grant ‘‘SEE MORE, MAKE MORE: Secondary Electron Energy Measurement Optimisation for Reliable Manufacturing of Key Materials’’. Contact: SM3 (SEE MORE MAKE MORE) project PI, Professor Cornelia Rodenburg, c.rodenburg@shefield.ac.uk.The University of Sheffield printed this dataset. This dataset contains different films with different magnifications collected from different regions of interest, and the associated bottom bar for experimental conditions. Please read the text file for experimental conditions.Overview:This dataset contains secondary electron hyperspectral imaging (SEHI) data acquired as part of a research project focused on developing automated, multi-scale, spatio-spectral approaches for materials characterization. The data support the study presented in the associated publication and are intended to enable reproducibility, further analysis, and method development in electron microscopy and hyperspectral image analysis. Dataset Context:Secondary electron hyperspectral imaging extends conventional SEM imaging by capturing spectral information from secondary electrons as a function of energy. This dataset was collected to investigate how spectral and spatial information can be combined across multiple length scales to improve image registration, feature identification, and automated materials analysis.Data Acquisition:All data were acquired using a Helios scanning electron microscope operating in immersion mode. Acquisition parameters (e.g., accelerating voltage, working distance, magnification, horizontal field width, and scale bar) are provided alongside each dataset and/or in associated metadata files. Dataset Structure:The dataset is organised into folders corresponding to individual acquisitions or imaging conditions. Each folder contains:- SEHI image files- Associated metadata files (e.g., acquisition parameters)The data contribute to research on:- Multi-scale SEHI imaging- Spectral–spatial data fusion- Automated and data-driven materials characterization- Registration of hyperspectral electron microscopy datasets-Super solution of hyperspectral electron microscopy datasets- Spectral and spatial analysis of secondary electron signals.Users are encouraged to cite the associated publication when using this dataset in their work.

Fields of Study & Subjects

Electron and X-Ray Spectroscopy Techniques Advanced Electron Microscopy Techniques and Applications Machine Learning in Materials Science

Publication details

Journal / source
ORDA - The University of Sheffield Research Data Catalogue and Repository
Publication date
1 January 2026
Document type
Dataset