@inproceedings{arnold-tilton-2020-enriching,
title = "Enriching Historic Photography with Structured Data using Image Region Segmentation",
author = "Arnold, Taylor and
Tilton, Lauren",
editor = "Abgaz, Yalemisew and
Dorn, Amelie and
Diaz, Jose Luis Preza and
Koch, Gerda",
booktitle = "Proceedings of the 1st International Workshop on Artificial Intelligence for Historical Image Enrichment and Access",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/2020.ai4hi-1.1",
pages = "1--10",
abstract = "Cultural institutions such as galleries, libraries, archives and museums continue to make commitments to large scale digitization of collections. An ongoing challenge is how to increase discovery and access through structured data and the semantic web. In this paper we describe a method for using computer vision algorithms that automatically detect regions of {``}stuff{''} {---} such as the sky, water, and roads {---} to produce rich and accurate structured data triples for describing the content of historic photography. We apply our method to a collection of 1610 documentary photographs produced in the 1930s and 1940 by the FSA-OWI division of the U.S. federal government. Manual verification of the extracted annotations yields an accuracy rate of 97.5{\%}, compared to 70.7{\%} for relations extracted from object detection and 31.5{\%} for automatically generated captions. Our method also produces a rich set of features, providing more unique labels (1170) than either the captions (1040) or object detection (178) methods. We conclude by describing directions for a linguistically-focused ontology of region categories that can better enrich historical image data. Open source code and the extracted metadata from our corpus are made available as external resources.",
language = "English",
ISBN = "979-10-95546-63-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arnold-tilton-2020-enriching">
<titleInfo>
<title>Enriching Historic Photography with Structured Data using Image Region Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Taylor</namePart>
<namePart type="family">Arnold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lauren</namePart>
<namePart type="family">Tilton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st International Workshop on Artificial Intelligence for Historical Image Enrichment and Access</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yalemisew</namePart>
<namePart type="family">Abgaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amelie</namePart>
<namePart type="family">Dorn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="given">Luis</namePart>
<namePart type="given">Preza</namePart>
<namePart type="family">Diaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerda</namePart>
<namePart type="family">Koch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-63-4</identifier>
</relatedItem>
<abstract>Cultural institutions such as galleries, libraries, archives and museums continue to make commitments to large scale digitization of collections. An ongoing challenge is how to increase discovery and access through structured data and the semantic web. In this paper we describe a method for using computer vision algorithms that automatically detect regions of “stuff” — such as the sky, water, and roads — to produce rich and accurate structured data triples for describing the content of historic photography. We apply our method to a collection of 1610 documentary photographs produced in the 1930s and 1940 by the FSA-OWI division of the U.S. federal government. Manual verification of the extracted annotations yields an accuracy rate of 97.5%, compared to 70.7% for relations extracted from object detection and 31.5% for automatically generated captions. Our method also produces a rich set of features, providing more unique labels (1170) than either the captions (1040) or object detection (178) methods. We conclude by describing directions for a linguistically-focused ontology of region categories that can better enrich historical image data. Open source code and the extracted metadata from our corpus are made available as external resources.</abstract>
<identifier type="citekey">arnold-tilton-2020-enriching</identifier>
<location>
<url>https://aclanthology.org/2020.ai4hi-1.1</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enriching Historic Photography with Structured Data using Image Region Segmentation
%A Arnold, Taylor
%A Tilton, Lauren
%Y Abgaz, Yalemisew
%Y Dorn, Amelie
%Y Diaz, Jose Luis Preza
%Y Koch, Gerda
%S Proceedings of the 1st International Workshop on Artificial Intelligence for Historical Image Enrichment and Access
%D 2020
%8 May
%I European Language Resources Association (ELRA)
%C Marseille, France
%@ 979-10-95546-63-4
%G English
%F arnold-tilton-2020-enriching
%X Cultural institutions such as galleries, libraries, archives and museums continue to make commitments to large scale digitization of collections. An ongoing challenge is how to increase discovery and access through structured data and the semantic web. In this paper we describe a method for using computer vision algorithms that automatically detect regions of “stuff” — such as the sky, water, and roads — to produce rich and accurate structured data triples for describing the content of historic photography. We apply our method to a collection of 1610 documentary photographs produced in the 1930s and 1940 by the FSA-OWI division of the U.S. federal government. Manual verification of the extracted annotations yields an accuracy rate of 97.5%, compared to 70.7% for relations extracted from object detection and 31.5% for automatically generated captions. Our method also produces a rich set of features, providing more unique labels (1170) than either the captions (1040) or object detection (178) methods. We conclude by describing directions for a linguistically-focused ontology of region categories that can better enrich historical image data. Open source code and the extracted metadata from our corpus are made available as external resources.
%U https://aclanthology.org/2020.ai4hi-1.1
%P 1-10
Markdown (Informal)
[Enriching Historic Photography with Structured Data using Image Region Segmentation](https://aclanthology.org/2020.ai4hi-1.1) (Arnold & Tilton, AI4HI 2020)
ACL