Where Are the Pictures? Linking Photographic Records across Collections Using Fuzzy Logic

Stephen C Brown, David Croft, Simon Coupland, Jethro Shell, Alexander von Lünen

Research output: Chapter in Book/Report/Conference proceedingConference proceeding

Abstract

This paper describes a novel approach to interrogating different online collections to identify potential matches between them, using fuzzy logic-based data-mining algorithms. Potentially, information about objects from one collection could be used to enrich records in another where there are overlaps. But although there is a considerable amount of bibliographic and other kinds of data on the Web that share similar information, a standardized way of structuring such data in a way that makes it easy to identify significant relationships does not yet exist. In the case of historical photographs, the challenge is further exacerbated by the enormous range of subjects depicted, and the fact that surviving records are not always complete, accurate, or consistent and the amount of text available per record is very small. Fuzzy-matching algorithms combined with semantic similarity techniques offer a way of finding potential matches between such items when standard ontology and corpus-based approaches are inadequate, in this case helping researchers for the first time match photographs held in different archives to historical exhibition catalogue records.
Original languageEnglish
Title of host publicationMuseums and the Web Asia 2013
Publication statusPublished - 2013
EventMuseums and the Web Asia 2013 - Sheraton Hong Kong Hotel and Towers, Hong Kong
Duration: 8 Dec 201312 Dec 2013
http://mwa2013.museumsandtheweb.com/

Conference

ConferenceMuseums and the Web Asia 2013
Abbreviated titleMWA2013
CountryHong Kong
Period8/12/1312/12/13
Internet address

Fingerprint

Fuzzy logic
Data mining
Ontology
Semantics

Keywords

  • Linked data
  • Semantic
  • Ontology
  • Metadata
  • Fuzzy logic
  • Co-reference

Cite this

Brown, S. C., Croft, D., Coupland, S., Shell, J., & von Lünen, A. (2013). Where Are the Pictures? Linking Photographic Records across Collections Using Fuzzy Logic. In Museums and the Web Asia 2013

Where Are the Pictures? Linking Photographic Records across Collections Using Fuzzy Logic. / Brown, Stephen C; Croft, David; Coupland, Simon; Shell, Jethro; von Lünen, Alexander.

Museums and the Web Asia 2013. 2013.

Research output: Chapter in Book/Report/Conference proceedingConference proceeding

Brown, SC, Croft, D, Coupland, S, Shell, J & von Lünen, A 2013, Where Are the Pictures? Linking Photographic Records across Collections Using Fuzzy Logic. in Museums and the Web Asia 2013. Museums and the Web Asia 2013, Hong Kong, 8/12/13.
Brown SC, Croft D, Coupland S, Shell J, von Lünen A. Where Are the Pictures? Linking Photographic Records across Collections Using Fuzzy Logic. In Museums and the Web Asia 2013. 2013
Brown, Stephen C ; Croft, David ; Coupland, Simon ; Shell, Jethro ; von Lünen, Alexander. / Where Are the Pictures? Linking Photographic Records across Collections Using Fuzzy Logic. Museums and the Web Asia 2013. 2013.
@inproceedings{90fc4b6b0cd84b3081e3e4158e99ce4e,
title = "Where Are the Pictures?: Linking Photographic Records across Collections Using Fuzzy Logic",
abstract = "This paper describes a novel approach to interrogating different online collections to identify potential matches between them, using fuzzy logic-based data-mining algorithms. Potentially, information about objects from one collection could be used to enrich records in another where there are overlaps. But although there is a considerable amount of bibliographic and other kinds of data on the Web that share similar information, a standardized way of structuring such data in a way that makes it easy to identify significant relationships does not yet exist. In the case of historical photographs, the challenge is further exacerbated by the enormous range of subjects depicted, and the fact that surviving records are not always complete, accurate, or consistent and the amount of text available per record is very small. Fuzzy-matching algorithms combined with semantic similarity techniques offer a way of finding potential matches between such items when standard ontology and corpus-based approaches are inadequate, in this case helping researchers for the first time match photographs held in different archives to historical exhibition catalogue records.",
keywords = "Linked data, Semantic, Ontology, Metadata, Fuzzy logic, Co-reference",
author = "Brown, {Stephen C} and David Croft and Simon Coupland and Jethro Shell and {von L{\"u}nen}, Alexander",
year = "2013",
language = "English",
booktitle = "Museums and the Web Asia 2013",

}

TY - GEN

T1 - Where Are the Pictures?

T2 - Linking Photographic Records across Collections Using Fuzzy Logic

AU - Brown, Stephen C

AU - Croft, David

AU - Coupland, Simon

AU - Shell, Jethro

AU - von Lünen, Alexander

PY - 2013

Y1 - 2013

N2 - This paper describes a novel approach to interrogating different online collections to identify potential matches between them, using fuzzy logic-based data-mining algorithms. Potentially, information about objects from one collection could be used to enrich records in another where there are overlaps. But although there is a considerable amount of bibliographic and other kinds of data on the Web that share similar information, a standardized way of structuring such data in a way that makes it easy to identify significant relationships does not yet exist. In the case of historical photographs, the challenge is further exacerbated by the enormous range of subjects depicted, and the fact that surviving records are not always complete, accurate, or consistent and the amount of text available per record is very small. Fuzzy-matching algorithms combined with semantic similarity techniques offer a way of finding potential matches between such items when standard ontology and corpus-based approaches are inadequate, in this case helping researchers for the first time match photographs held in different archives to historical exhibition catalogue records.

AB - This paper describes a novel approach to interrogating different online collections to identify potential matches between them, using fuzzy logic-based data-mining algorithms. Potentially, information about objects from one collection could be used to enrich records in another where there are overlaps. But although there is a considerable amount of bibliographic and other kinds of data on the Web that share similar information, a standardized way of structuring such data in a way that makes it easy to identify significant relationships does not yet exist. In the case of historical photographs, the challenge is further exacerbated by the enormous range of subjects depicted, and the fact that surviving records are not always complete, accurate, or consistent and the amount of text available per record is very small. Fuzzy-matching algorithms combined with semantic similarity techniques offer a way of finding potential matches between such items when standard ontology and corpus-based approaches are inadequate, in this case helping researchers for the first time match photographs held in different archives to historical exhibition catalogue records.

KW - Linked data

KW - Semantic

KW - Ontology

KW - Metadata

KW - Fuzzy logic

KW - Co-reference

M3 - Conference proceeding

BT - Museums and the Web Asia 2013

ER -