Tools for presenting and searching through our collections.

Desired outcome

Theatre institute has several collections, i.e. audio and video recordings, press clipping and photographs, sketches. Many of those have been scanned or have been produced in a digital form.

Initial Problem Description

We are facing two challenges. How to develop a web portal that would be accessible on demand, because these materials are subject to copyriht. Second is the fact that we need a search engine that could read through texts in pdf or other format and recognise faces/actors on photographs. Such a search engine would enable us and our clients (mainly researchers) to search the vast database, make new insights and analyses.

Context

The idea is to have all our collections in digital form and to enable researchers to search through them easily. This would enable research in Slovene theatre history and show the connections to other European and global contexts. However, the obstacles are the copyright that prevents us to upload this material on the web and make it accesssible to everybody without limitations. The second one is that it is a large number of artefacts and we do not have them in a database with keywords. We do not have enough people to do it and a number of new artefacts is too large. We need a computer to do it for us.

Connection to cross-cutting areas

Our problem is linked to digitalisation. It is a problem that a number of museums and archives face today. Furthermore, we are facing a challenge of how to connect different collections in different museums in order to enable the larger research of the field in Europe and on global scale. Some of such initiatives already exist, but they are mainly limited to the databases where one needs to put the keywords in, thus enabling the search.

Input

So far we do not have an existing scenario. We have a basic idea of our needs and an idea that it might be solvable with the use of the AI. We are aware of the exception in the copyright law that enables non-profit use of copyright material for research and pedagogical use. The scenario is to search for an appropriate AI to use with our case. Later on we would develop a web portal, an entry point to our collections that could be accessed on demand.

Expectations

We would like students to develop the initial idea or even a search engine that we could test on our collections. We can then further develop the idea and make it accessible on the web. The next step would be checking for the possibilities to connect different collections from similar museums in other countries. This would make a larger net of institutions and collections that would enable large-scale research.

Desired Team Profile

We would imagine the team to have a mixture of expertise. On one hand ethnology, arts and humanities, skills in catalogisation and archives. On the other hand an expertise in computer science, programming, computer systems etc. Such an interdisciplinary approach could develop a solution that would take into account the pros and cons of the current situation and search for innovative solutions.

Additional Information

This is the problem that the majority of public institutions in the field of cultural heritage face. Digitization has come as a great opportunity to the sector. A large number of artefacts has been collected in databases like Europeana. Now it is clear that such large databases are not really alive due to the large number of artefacts and a lack of search engines or narratives that would guide the customers through the collection.

Related Keywords

• Digitalization
• Computer related
• Scanning Related
• OCR (optical character recognition)