Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Report . 2022
License: CC BY
Data sources: Datacite
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Report . 2022
License: CC BY
Data sources: ZENODO
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Report . 2022
License: CC BY
Data sources: Datacite
versions View all 2 versions
addClaim

Krant & foto's verbonden. Een verkenning om kunstmatige intelligentie in te zetten om erfgoedcollecties te verbinden

Authors: De Gruijter, Michel; Balmashnova, Evgeniya; Bertrams, Rob; Brons, Martine; Franken, Jeroen; Groothuis, Mark; De Groot, Roosmarijn; +6 Authors

Krant & foto's verbonden. Een verkenning om kunstmatige intelligentie in te zetten om erfgoedcollecties te verbinden

Abstract

Press photographers often take several photos of an event. Usually only one of these appears in the newspaper. Nowadays, both the newspaper and the original photo series of the press photographer can often be found in digitised form. But searching for these sources and making connections between them is still manual work. Researchers are now exploring the possibilities of Artificial Intelligence (AI) to connect these collections and better unlock the wealth of press photo archives. This makes it easier to find out the full story of a single press photo. With the help of AI, the collections can be connected and we can use image recognition to link thousands of newspaper photos with the whole series of photos in press photo archives. The aim is that users start with the photo in the newspaper and with one mouse click end up with all associated photos in the press photo archive, in order to discover and tell stories in new ways. From March 2022, users can submit a search query on www.krant-en-fotos.nl, where the technology is included in a search engine. For the time being, these are photos from the 1970s from three Dutch newspapers Nieuwsblad van het Noorden, IJmuider Courant and Haarlems Dagblad. The Noord-Hollands Archief, Groninger Archives, the technology companies Sioux Technologies and Picturae, and KB, the national library, have joined forces to connect the newspapers and the photos with AI. The project is funded by the Ministry of Education, Culture and Science (OCW). The project has been included as an inspiring use case in the elaboration of the position paper of the Culture and Media workgroup of the Dutch AI Coalition (NLAIC). It shows what the power of AI can mean for the production process within the culture and media sector. The results will also be shared within the NLAIC network. [Dutch] Persfotografen maken van een gebeurtenis vaak meerdere foto���s. Daarvan verschijnt er meestal maar ����n in de krant. Tegenwoordig zijn zowel de krant als de originele fotoserie van de persfotograaf veelal in gedigitaliseerde vorm terug te vinden. Maar het zoeken naar deze bronnen en het leggen van verbindingen daartussen is vooralsnog handwerk. Onderzoekers verkennen nu de mogelijkheden van Artificial Intelligence (AI) om deze collecties met elkaar te verbinden en de rijkdom van persfotoarchieven beter te ontsluiten. Hierdoor wordt het makkelijker om het volledige verhaal van een enkele persfoto te achterhalen. Met behulp van AI kunnen de collecties worden verbonden en kunnen we beeldherkenning inzetten om duizenden krantenfoto���s te koppelen met de hele reeks foto���s in persfotoarchieven. Met als doel dat gebruikers kunnen doorklikken van de foto uit de krant naar alle bijbehorende foto���s in het persfotoarchief, om zo op nieuwe manieren verhalen te ontdekken en te vertellen. Gebruikers kunnen vanaf maart 2022 een zoekvraag opgeven op www.krant-en-fotos.nl, waar de technologie in een zoekmachine is opgenomen. Het gaat vooralsnog om foto���s uit de jaren 1970 uit Nieuwsblad van het Noorden, IJmuider Courant en Haarlems Dagblad. Voor het verbinden met AI van de kranten en de foto���s hebben het Noord-Hollands Archief, Groninger Archieven, de technologiebedrijven Sioux Technologies en Picturae, en KB, de nationale bibliotheek de handen ineengeslagen. Het project wordt gefinancierd door het ministerie van Onderwijs, Cultuur en Wetenschap (OCW). Het project is als een inspirerende use case opgenomen in de uitwerking van het position paper van de werkgroep Cultuur en Media van de Nederlandse AI Coalitie (NLAIC). Het laat zien wat de kracht van AI kan betekenen voor het productieproces binnen de cultuur- en mediasector. De resultaten zullen gedeeld worden binnen het netwerk van de NLAIC.

This project was funded by the Ministry of Education, Culture and Science of the Netherlands

Related Organizations
Keywords

image recognition, press photos, digital scholarship, best practices, convolutional neural network, cultural heritage, artificial intelligence, newspapers

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 84
    download downloads 77
  • 84
    views
    77
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
download
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
views
OpenAIRE UsageCountsViews provided by UsageCounts
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
0
Average
Average
Average
84
77
Green