Overzicht Lopende Projecten
Onderstaand overzicht geeft kort weer welke projecten op dit moment binnen CATCH worden uitgevoerd. Meer informatie over een project, zoals een overzicht van de uitvoerders en lijst van publicaties, vindt u op de algemene projectendatabase van NWO.
AGORA
Creating the historic fabric for and providing web-enabled access to objects in dynamic historical sequences
The collections of the Rijksmuseum Amsterdam and the Netherlands Institute for Sound and Vision in Hilversum jointly form an inexhaustible source of data about and objects from Dutch history. Yet the associated information about historic events is linked to these collections in many different ways. This makes it difficult to access knowledge about specific historical developments via these audio-visual and visual sources.
Based on several pilots that are related to current canonical debates, Agora is facilitating and investigating the digitally-mediated access that the Rijksmuseum and the Netherlands Institute for Sound and Vision offer to sources from the past. This must ultimately lead to a web-based interactive space on the interpretation of historical sources for both heritage professionals and interested members of the public.
AGORA is a project of the Free University Amsterdam, the Netherlands Institute for Sound and Vision and the Rijksmuseum Amsterdam.
BRIDGE
Building Rich Links to Enable Television History Research
Television is no longer an independent entity. Broadcasting companies are now platforms and providers of multimedia information. The traditional TV archive is being extended to include other sources so that a meaningful web of information can be realised. The aim of the BRIDGE project is to generate automatic links and associations between sources related to a television archive.
BRIDGE is a project of the University of Amsterdam, Utrecht University and the Netherlands Institute for Sound and Vision.
CHIP
Cultural Heritage Information Personalization
CHIP investigates how the interaction with the Dutch cultural heritage information can be enriched. It aims to guide each visitor through the virtual cultural Netherlands in ways that are adapted to that visitor. Research will be focused on the presentation of digitised cultural artefacts together with information about these artefacts, navigation by means of structures that connect artefacts, collections and artists, and personalization on individual and group level.
CHIP is a project of the Rijksmuseum, the Technische Universiteit Eindhoven and the Telematica Instituut
www.nwo.nl/catch/chip
CHOICE
Charting the Information Landscape Employing Context Information
CHOICE seeks to chart the uncharted information landscape, focusing on semi-automatic semantic annotation and employing context information. Semantic annotation involves the annotation of archived objects, such as video, images and books with semantic categories from some standardized metadata repository, such as domain thesauri and ontologies. The use of semantic annotation allows one to widen the search facilities in a collection.
CHOICE is a project of the Netherlands Institute for Sound and Vision, the Telematica Institute, Max Planck Institute and the Vrije Universiteit Amsterdam
www.nwo.nl/catch/choice
CHORAL
Acces to oral History
CHoral aims at the development of spoken document retrieval technology for the disclosure of oral history collections. With speech recognition transcriptions can be generated for spoken documents (audio and video). The transcripts have timestamps associated with the words and will be used to build an index that allows searching the audio files at fragment level. This project aims to contribute to the advent of methodological framework for handling and use of multimedia oral history content for historical research.
Choral is a project of the University of T wente, the Municipal Archives Rotterdam, the Erasmus University Rotterdam and Radio Rijnmond.
www.nwo.nl/catch/choral
CHoral contributed to the short movie 'CATCH: the future' that was first displayed at the CATCH symposium on 13 November 2009
HITIME
Historical Timeline Mining and Extraction
There is a wealth of information in different forms about the labour movement during the period 1850-1940, which includes biographies, letters and other personal material. HITIME aims to provide a software tool kit for historical research. This will enable a large-scale analysis of the links between people, professions, locations, events and schools of thought in order to create a clear picture of the labour movement’s social network. The tool kit shall also be made suitable for generic historical text mining.
HITIME is a project of the Tilburg University and the International Institute of Social History.
LINKS
Linking system for historical family reconstruction
Since 1811, the birth, marriage and death certificates of every person in the Netherlands have been kept. Countless volunteers are digitising the information about these people in GENLIAS. By linking these data together, a wealth of knowledge can be derived in areas such as historical demography (child mortality), historical sociology (social mobility) and epidemiology and genetics. In that linking process due consideration is given to matters such as incorrect spelling and regional deviations in the names.
The LINKS project aims to reconstruct all families in the Netherlands from the 19th and early 20th century, using techniques such as fuzzy matching and self learning.
LINKS is a project of the IISG-KNAW, Utrecht University, Virtual Knowledge Studio, LIACS, P.J. Meertens Institute, Netherlands Interdisciplinary Demographic Institute, Historic Centre of Overijssel and Tresoar.
MITCH
Mining for Information in Texts from the Cultural Heritage
Text mining, a research domain of natural language engineering, has advanced to a level at which automatic language technology and information extraction modules can be applied to vast amounts of text and (semi-)structured data with textual elements. Textual data can be analysed on spelling, syntax, document structure and topical-semantic information. This project investigates how text mining can be employed to support the automisation of knowledge enrichment and understanding of digitised cultural-heritage texts and textual object data bases. The case studies are provided by Naturalis, the Dutch National Museum for Natural History, and focus on the vast numbers of unanalyzed and unlinked object databases and log books describing collected animal specime ns, and taxonomies that organize these specimens according to the progressing international conventions.
MITCH is a project of the National Museum of Natural History and Tilburg University.
www.nwo.nl/catch/mitch
MITCH contributed to the short movie 'CATCH: the future' that was first displayed at the CATCH symposium on 13 November 2009
MUnCH
MultimediaN and CATCH
MuNCH focuses on knowledge enrichment by means of automated analyses of digital images and video. With the advent of digital communication, we live in the exciting times of broad and narrow casting through the Internet, of passive and active viewers, of direct or delayed broadcast, and of digital pictures being delivered in the museum or at home. At the same time, the picture and television archives turn digital. In these demanding times, the archives are likely to be swamped with information requests unless they swiftly adapt to partially automatic annotation and digital retrieval. The aim of this project is to provide faster and more complete access to pictures in cultural archives through digital analysis.
MuNCH is a project of the University of Amsterdam, the Vrije Universiteit Amsterdam, the Netherlands Institute for Sound and Vision and the association Digitaal Erfgoed Nederland.
www.nwo.nl/catch/munch
MuSEUM
Multiple-collection Searching Using Metadata
MuSeUM addresses the prototypical problem of a cultural heritage institute with the ambition to disclose all of its content in a single, unified system. Institutes use various systems, each dealing with a small part of the collection, constructed for different purposes, in different times, by different people, working in different traditions, based on different design principles, with different access methods, etcetera. This project will investigate theoretically transparent ways of combining modern information retrieval methods based on statistical language modeling with varying amounts of metadata and non-content features.
MuSEUM is a project of the University of Amsterdam, the Gemeentemuseum Den Haag, the Rijksbureau voor Kunsthistorische Documentatie and the Municipal Archives Rotterdam.
www.nwo.nl/catch/museum
RICH
Reading Images in the Cultural Heritage
The research question addressed in the RICH project reads: How can artificial intelligence support the automatic visual analysis of archaeological objects? The approach followed in the RICH project is empirical. Machine-learning algorithms are trained on large collections of images. After training, the ability to recognize or classify previously unseen images is assessed yielding a measure of generalisation performance.
RICH is a project of the Rijksdienst voor Archeologie, Cultuurlandschap en Monumenten (RACM) and the Universiteit Maastricht.
www.nwo.nl/catch/rich
RICH contributed to the short movie 'CATCH: the future' that was first displayed at the CATCH symposium on 13 November 2009
SCRATCH
Script Analysis Tools for the Cultural Heritage
Large collections of handwritten material do not lend them selves easily to simple access on the basis of keyword search. Recent developments in machine learning and the availability of computing power allow for data-mining and information-retrieval methods to be applied to machine-facilitated analysis and annotation of large script archives. This project tackles problems both at the level of pattern recognition of handwriting and at the level of the linguistic structure of handwritten texts.
SCRATCH is a project of the Nationaal Archief and the University of Groningen.
www.nwo.nl/catch/scratch
SCRATCH contributed to the short movie 'CATCH: the future' that was first displayed at the CATCH symposium on 13 November 2009
STITCH
Semantic Interoperability to Access Cultural Heritage
The prime research objective of this project is to develop theory, methods and tools for allowing metadata interoperability through semantic links between the vocabularies. This research challenge is similar to what is called the ontology mapping problem in ontology research.
STITCH is a project of the National Library of the Netherlands, the Vrije Universiteit Amsterdam and the Max Planck Institute.
www.nwo.nl/catch/stitch
WITCHCRAFT
What is topical in Cultural Heritage: content-based Retrieval Among Folksong tunes
The WITCHCRAFT project sets as its objective to develop a fully-functional content-based retrieval system for large amounts of melodies stored as audio and notation, building on the best practices of Music Information Retrieval research. The project can have an impact on MIR research by providing insight into the modeling of high-level musical features, by setting a standard to compare future systems against, and by creating tools, data and evaluation methods that can be used in other MIR research projects.
WITCHCRAFT is a project of the Utrecht University, the Meertens Instituut and the Theater Instituut Nederland.
www.nwo.nl/catch/witchcraft