A hybrid approach to machine learning annotation of large galaxy image databases
Modern astronomy relies on massive databases collected by robotic telescopes and digital sky surveys, acquiring data in a much faster pace than what manual analysis can support. Among other data, these sky surveys collect information about millions and sometimes billions of extra-galactic objects. S...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2018-10 |
---|---|
Hauptverfasser: | , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Kuminski, Evan Shamir, Lior |
description | Modern astronomy relies on massive databases collected by robotic telescopes and digital sky surveys, acquiring data in a much faster pace than what manual analysis can support. Among other data, these sky surveys collect information about millions and sometimes billions of extra-galactic objects. Since the very large number of objects makes manual observation impractical, automatic methods that can analyze and annotate extra-galactic objects are required to fully utilize the discovery power of these databases. Machine learning methods for annotation of celestial objects can be separated broadly into methods that use the photometric information collected by digital sky surveys, and methods that analyze the image of the object. Here we describe a hybrid method that combines photometry and image data to annotate galaxies by their morphology, and a method that uses that information to identify objects that are visually similar to a query object (query-by-example). The results are compared to using just photometric information from SDSS, and to using just the morphological descriptors extracted directly from the images. The comparison shows that for automatic classification the image data provide marginal addition to the information provided by the photometry data. For query-by-example, however, the analysis of the image data provides more information that improves the automatic detection substantially. The source code and binaries of the method can be downloaded through the Astrophysics Source Code Library. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2126699154</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2126699154</sourcerecordid><originalsourceid>FETCH-proquest_journals_21266991543</originalsourceid><addsrcrecordid>eNqNjMEKgkAURYcgSMp_eNBa0Bm1XEYULVu0l1eOOjK-sZkR8u-bRR_Q6nA5l7NiERciS4455xsWOzekacrLAy8KEbH7CfrlaVUDOE3W4KsHb2AMVCRBS7SkqAMkMh69MgSmBY22k9Chxs8CasQwGvT4RCfdjq1b1E7GP27Z_np5nG9JqL9n6Xw9mNlSUDXPeFlWVVbk4r_XF1OGPvQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2126699154</pqid></control><display><type>article</type><title>A hybrid approach to machine learning annotation of large galaxy image databases</title><source>Free E- Journals</source><creator>Kuminski, Evan ; Shamir, Lior</creator><creatorcontrib>Kuminski, Evan ; Shamir, Lior</creatorcontrib><description>Modern astronomy relies on massive databases collected by robotic telescopes and digital sky surveys, acquiring data in a much faster pace than what manual analysis can support. Among other data, these sky surveys collect information about millions and sometimes billions of extra-galactic objects. Since the very large number of objects makes manual observation impractical, automatic methods that can analyze and annotate extra-galactic objects are required to fully utilize the discovery power of these databases. Machine learning methods for annotation of celestial objects can be separated broadly into methods that use the photometric information collected by digital sky surveys, and methods that analyze the image of the object. Here we describe a hybrid method that combines photometry and image data to annotate galaxies by their morphology, and a method that uses that information to identify objects that are visually similar to a query object (query-by-example). The results are compared to using just photometric information from SDSS, and to using just the morphological descriptors extracted directly from the images. The comparison shows that for automatic classification the image data provide marginal addition to the information provided by the photometry data. For query-by-example, however, the analysis of the image data provides more information that improves the automatic detection substantially. The source code and binaries of the method can be downloaded through the Astrophysics Source Code Library.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Annotations ; Artificial intelligence ; Astronomy ; Astrophysics ; Binary stars ; Data acquisition ; Digital imaging ; Galaxies ; Image classification ; Image detection ; Machine learning ; Methods ; Morphology ; Photometry ; Queries ; Sky surveys (astronomy) ; Source code ; Space telescopes ; Telescopes</subject><ispartof>arXiv.org, 2018-10</ispartof><rights>2018. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Kuminski, Evan</creatorcontrib><creatorcontrib>Shamir, Lior</creatorcontrib><title>A hybrid approach to machine learning annotation of large galaxy image databases</title><title>arXiv.org</title><description>Modern astronomy relies on massive databases collected by robotic telescopes and digital sky surveys, acquiring data in a much faster pace than what manual analysis can support. Among other data, these sky surveys collect information about millions and sometimes billions of extra-galactic objects. Since the very large number of objects makes manual observation impractical, automatic methods that can analyze and annotate extra-galactic objects are required to fully utilize the discovery power of these databases. Machine learning methods for annotation of celestial objects can be separated broadly into methods that use the photometric information collected by digital sky surveys, and methods that analyze the image of the object. Here we describe a hybrid method that combines photometry and image data to annotate galaxies by their morphology, and a method that uses that information to identify objects that are visually similar to a query object (query-by-example). The results are compared to using just photometric information from SDSS, and to using just the morphological descriptors extracted directly from the images. The comparison shows that for automatic classification the image data provide marginal addition to the information provided by the photometry data. For query-by-example, however, the analysis of the image data provides more information that improves the automatic detection substantially. The source code and binaries of the method can be downloaded through the Astrophysics Source Code Library.</description><subject>Annotations</subject><subject>Artificial intelligence</subject><subject>Astronomy</subject><subject>Astrophysics</subject><subject>Binary stars</subject><subject>Data acquisition</subject><subject>Digital imaging</subject><subject>Galaxies</subject><subject>Image classification</subject><subject>Image detection</subject><subject>Machine learning</subject><subject>Methods</subject><subject>Morphology</subject><subject>Photometry</subject><subject>Queries</subject><subject>Sky surveys (astronomy)</subject><subject>Source code</subject><subject>Space telescopes</subject><subject>Telescopes</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjMEKgkAURYcgSMp_eNBa0Bm1XEYULVu0l1eOOjK-sZkR8u-bRR_Q6nA5l7NiERciS4455xsWOzekacrLAy8KEbH7CfrlaVUDOE3W4KsHb2AMVCRBS7SkqAMkMh69MgSmBY22k9Chxs8CasQwGvT4RCfdjq1b1E7GP27Z_np5nG9JqL9n6Xw9mNlSUDXPeFlWVVbk4r_XF1OGPvQ</recordid><startdate>20181026</startdate><enddate>20181026</enddate><creator>Kuminski, Evan</creator><creator>Shamir, Lior</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20181026</creationdate><title>A hybrid approach to machine learning annotation of large galaxy image databases</title><author>Kuminski, Evan ; Shamir, Lior</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_21266991543</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Annotations</topic><topic>Artificial intelligence</topic><topic>Astronomy</topic><topic>Astrophysics</topic><topic>Binary stars</topic><topic>Data acquisition</topic><topic>Digital imaging</topic><topic>Galaxies</topic><topic>Image classification</topic><topic>Image detection</topic><topic>Machine learning</topic><topic>Methods</topic><topic>Morphology</topic><topic>Photometry</topic><topic>Queries</topic><topic>Sky surveys (astronomy)</topic><topic>Source code</topic><topic>Space telescopes</topic><topic>Telescopes</topic><toplevel>online_resources</toplevel><creatorcontrib>Kuminski, Evan</creatorcontrib><creatorcontrib>Shamir, Lior</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kuminski, Evan</au><au>Shamir, Lior</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>A hybrid approach to machine learning annotation of large galaxy image databases</atitle><jtitle>arXiv.org</jtitle><date>2018-10-26</date><risdate>2018</risdate><eissn>2331-8422</eissn><abstract>Modern astronomy relies on massive databases collected by robotic telescopes and digital sky surveys, acquiring data in a much faster pace than what manual analysis can support. Among other data, these sky surveys collect information about millions and sometimes billions of extra-galactic objects. Since the very large number of objects makes manual observation impractical, automatic methods that can analyze and annotate extra-galactic objects are required to fully utilize the discovery power of these databases. Machine learning methods for annotation of celestial objects can be separated broadly into methods that use the photometric information collected by digital sky surveys, and methods that analyze the image of the object. Here we describe a hybrid method that combines photometry and image data to annotate galaxies by their morphology, and a method that uses that information to identify objects that are visually similar to a query object (query-by-example). The results are compared to using just photometric information from SDSS, and to using just the morphological descriptors extracted directly from the images. The comparison shows that for automatic classification the image data provide marginal addition to the information provided by the photometry data. For query-by-example, however, the analysis of the image data provides more information that improves the automatic detection substantially. The source code and binaries of the method can be downloaded through the Astrophysics Source Code Library.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2018-10 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2126699154 |
source | Free E- Journals |
subjects | Annotations Artificial intelligence Astronomy Astrophysics Binary stars Data acquisition Digital imaging Galaxies Image classification Image detection Machine learning Methods Morphology Photometry Queries Sky surveys (astronomy) Source code Space telescopes Telescopes |
title | A hybrid approach to machine learning annotation of large galaxy image databases |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T12%3A02%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=A%20hybrid%20approach%20to%20machine%20learning%20annotation%20of%20large%20galaxy%20image%20databases&rft.jtitle=arXiv.org&rft.au=Kuminski,%20Evan&rft.date=2018-10-26&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2126699154%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2126699154&rft_id=info:pmid/&rfr_iscdi=true |