The Hubble Image Similarity Project

We have created a large database of similarity information between subregions of Hubble Space Telescope images. These data can be used to assess the accuracy of image-search algorithms based on computer vision methods. The images were compared by humans in a citizen science project, where they were...

Full description

Saved in:
Bibliographic Details
Main Authors: Richard L. White, J. E. G. Peek
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:The Astronomical Journal
Subjects:
Online Access:https://doi.org/10.3847/1538-3881/adcb43
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849322086817857536
author Richard L. White
J. E. G. Peek
author_facet Richard L. White
J. E. G. Peek
author_sort Richard L. White
collection DOAJ
description We have created a large database of similarity information between subregions of Hubble Space Telescope images. These data can be used to assess the accuracy of image-search algorithms based on computer vision methods. The images were compared by humans in a citizen science project, where they were asked to select similar images from a comparison sample. We utilized the Amazon Mechanical Turk system to pay our reviewers a fair wage for their work. Nearly 850,000 comparison measurements have been analyzed to construct a similarity distance matrix between all the pairs of images. We describe the algorithm used to extract a robust distance matrix from the (sometimes noisy) user reviews. The results are very impressive: The data capture similarity between images based on morphology, texture, and other details that are sometimes difficult even to describe in words (e.g., dusty absorption bands with sharp edges). The collective visual wisdom of our citizen scientists matches the accuracy of the trained eye, with even subtle differences among images faithfully reflected in the distances.
format Article
id doaj-art-cdfc6f4b8fbe4d5c8fad6b00af9a1f4e
institution Kabale University
issn 1538-3881
language English
publishDate 2025-01-01
publisher IOP Publishing
record_format Article
series The Astronomical Journal
spelling doaj-art-cdfc6f4b8fbe4d5c8fad6b00af9a1f4e2025-08-20T03:49:32ZengIOP PublishingThe Astronomical Journal1538-38812025-01-01169630610.3847/1538-3881/adcb43The Hubble Image Similarity ProjectRichard L. White0https://orcid.org/0000-0002-9194-2807J. E. G. Peek1https://orcid.org/0000-0003-4797-7030Space Telescope Science Institute , 3700 San Martin Drive, Baltimore, MD 21218, USA ; rlw@stsci.eduSpace Telescope Science Institute , 3700 San Martin Drive, Baltimore, MD 21218, USA ; rlw@stsci.edu; Department of Physics & Astronomy, Johns Hopkins University , 3400 N. Charles Street, Baltimore, MD 21218, USAWe have created a large database of similarity information between subregions of Hubble Space Telescope images. These data can be used to assess the accuracy of image-search algorithms based on computer vision methods. The images were compared by humans in a citizen science project, where they were asked to select similar images from a comparison sample. We utilized the Amazon Mechanical Turk system to pay our reviewers a fair wage for their work. Nearly 850,000 comparison measurements have been analyzed to construct a similarity distance matrix between all the pairs of images. We describe the algorithm used to extract a robust distance matrix from the (sometimes noisy) user reviews. The results are very impressive: The data capture similarity between images based on morphology, texture, and other details that are sometimes difficult even to describe in words (e.g., dusty absorption bands with sharp edges). The collective visual wisdom of our citizen scientists matches the accuracy of the trained eye, with even subtle differences among images faithfully reflected in the distances.https://doi.org/10.3847/1538-3881/adcb43Astronomy image processingAstronomy data analysisAstronomy databasesGalaxiesNebulaeStar clusters
spellingShingle Richard L. White
J. E. G. Peek
The Hubble Image Similarity Project
The Astronomical Journal
Astronomy image processing
Astronomy data analysis
Astronomy databases
Galaxies
Nebulae
Star clusters
title The Hubble Image Similarity Project
title_full The Hubble Image Similarity Project
title_fullStr The Hubble Image Similarity Project
title_full_unstemmed The Hubble Image Similarity Project
title_short The Hubble Image Similarity Project
title_sort hubble image similarity project
topic Astronomy image processing
Astronomy data analysis
Astronomy databases
Galaxies
Nebulae
Star clusters
url https://doi.org/10.3847/1538-3881/adcb43
work_keys_str_mv AT richardlwhite thehubbleimagesimilarityproject
AT jegpeek thehubbleimagesimilarityproject
AT richardlwhite hubbleimagesimilarityproject
AT jegpeek hubbleimagesimilarityproject