Build your Art and History Profile

The purpose of the CHIP demonstrator is constructing of a user profile in order to define his location within Art and History dimension of the Rijksmuseum Amsterdam collection. It uses semantically annotated data of the Rijksmuseum to elicit specific user's interests in artists, periods, genres and themes and uses these values to recommend relevant artefacts and related concepts from the museum collection. Later on we are planning to use the constructed profile to enable dynamical generation of personalized museum tours for different users.

Browse and search the Sound and Vision GTAA thesaurus

The Netherlands Institute for Sound and Vision carefully maintains its terminology in the GTAA (Common Thesaurus Audiovisual Archives). The GTAA contains approximately 160.000 terms, organized in six separate groups and accompanied by many relationships and term information. Use this application to browse and search for terms in the GTAA.

Radio Oranje

The CHoral project aims to advance the state-of-the-art in Spoken Document Retrieval and will develop technology for the disclosure of oral history collections. The focus of attention will be on spoken word collections with stories and testimonies on historical events. The Radio Oranje demo shows online access, search and browsing for a historical spoken word collection. During World War II queen Wilhelmina read speeches addressed to the Dutch nation via Radio Oranje. This radio station was located in London, England. The speeches were recorded and preserved, and transcriptions were made. The recordings and corresponding transcriptions were aligned to form a time-stamped index that makes it possible to search the speeches at word level. The Radio Oranje demo is a collaboration between NIOD, Nederlands Instituut voor Beeld en Geluid, CHoral and MultimediaN.

Highlight possible abnormalities in database text

The goal of the MITCH project is to research and develop techniques to discover new meaning in large collections of partially structured data that are available at Naturalis, the Dutch National Museum of Natural History. This demo shows a small subset of some error-detection and correction routines that have highlighted possible abnormalities in the text, and a method for human experts to review and amend those errors if necessary.

CatchUp

MUSEUM (Multiple-collection Searching Using Metadata) sets the goal to allow single-interface access to the multi-collection database of the Gemeentemuseum in The Hague. The pilot incorporates all the museum objects, books and documents, the museum journal (data about exhibitions, acquisitions, loans, etc) and the museum correspondence and letters, in total over 1.2 million documents. These data are converted to plain text and searchable in a Google style simple form. Some of the data are available to museum employees only but most of it is open to the general public.

Browse the glass collection

Different ways to browse through all the glasses of the collection. The collection contains historical glass from archaeological excavations. Uses PHP server-side scripting. and a MySQL database.

Find your glass in the glass collection

Upload an image of your glass and find it in the glasscollection. Uses Matlab.

Sparse-knowledge search methods for handwritten collections.

Background of the pilot -- The goal is to create a test on Information-Retrieval (IR) approaches for handwritten document retrieval where the bag-of-words concept from regular IR is replaced by a "bag-of-glyphs" in handwriting. A minimum number of assumptions on language and content is present. In fact we only assume a script with horizontal lines of text.

Structured Access to Multiple Collections

A number of collections have been integrated into one portal. By determining equivalencies between concepts, it is possible to access the integrated collections using the structured vocabularies/thesauri of the collections. Different ways on how to access the collections are provided. You can also get an impression of the quality of automatic mapping tools by selecting different mappings.

Search for similar melodies

The purpose of the WITCHCRAFT project is to develop a content-based retrieval system for a large number of folk song melodies. The demonstration gives access to the collection "Onder de groene linde" of the Meertens institute. Users can either use metadata or music to search for melodies in the database.