Challenging our understanding of Digitisation
At the forthcoming Developer Happiness Days one of the sessions planned to take place will be exploring a DIY digitisation workflow:
Taking you from the act of scanning images and objects, learning how to process and edit them with software like ocrupus, blender and OpenCV, storing and manipulating them online and finally, through to printing their digital forms out, mashed together with comments, citations, automatic qr codes and even other digital objects!
While this session is not intended to showcase the same results one would expect to find on large scale institutional and heritage digitisation projects, the session might just force a consideration of digitisation practices and trigger off some interesting questions and dialogue.
So, if this confrontation with digitisation sounds interesting then there is an opportunity for attendance at this session by project members from JISC digitisation and eContent projects.
Spaces will be limited, so please contact me directly if you wish to register your interest: b.showers@jisc.ac.uk.
And to find out a little more about this session you can read Ben O’Steen’s blog and his ideas for the “The Secret Life of the Book” session at the event.
And further information about the Dev8d programme is available on the Developer Happiness website
#dev8d
OCR for the mass digitisation of textual materials
A workshop was held at the University of Bath on 24th September 2009, looking at some of the current issues in using Optical Character Recognition for digitisation, organised in the context of the EU Impact project.
Videos, slideshows, notes and questions from the day are now all available from the workshop webpages
Workshop: Optical Character Recognition (OCR) for the mass digitisation of textual materials: Improving Access to Text
24 September 2009 - UKOLN, University of Bath
http://www.ukoln.ac.uk/events/ocr-2009/
FREE one-day workshop for
* Collection holders in HE and Cultural Heritage organisations
* Users of digitised content for teaching, learning and research
This workshop is funded by the Joint Information Systems Committee (JISC) as
part of a series of workshops & seminars on Achievements & Challenges in
Digitisation & e-Content.
The workshop will provide an opportunity for participants to learn about the
current state-of-the-art in the digitisation of historical texts, to look at
improvements in digitisation techniques currently being explored in research
projects such as the EU-funded IMPACT project, and to explore how Optical
Character Recognition (OCR) is used in practical digitisation contexts and
workflows.
There will also be an opportunity for participants to investigate
the opportunities and challenges of the scholarly use of what is an
ever-increasing range of digitised content, supporting new interdisciplinary
ways of exploring cultural and social history, philology, and the history of
ideas.
European Conference on OCR and Mass Digitisation
From the IMPACT project, a European Union project which is aiming to create a centre of excellent for the digitisation of textual cultural heritage
Introduction
On 6 and 7 April 2009 the IMPACT project will organise a conference on OCR in mass digitisation projects. This conference will focus on exchanging views with other researchers and suppliers in the OCR field, as well as presenting some preliminary results from the first year of the IMPACT project.
Tentative programme
Monday 6 April 2009: New advances in OCR technology, such as collaborative correction and adaptive OCR techniques, a possible way forward for future large-scale digitisation programmes.
Tuesday 7 April 2009: Current and future challenges facing OCR technology, such as image enhancement and linguistic issues that come up when digitising historical text material.
Both days will feature key speakers from outside of the project, in addition to experts from the IMPACT consortium (to be announced in the near future).
Each day’s programme will last from 10.00 – 18.00, with a conference dinner on the first day.
Practical information
The venue will be the Koninklijke Bibliotheek (KB – National Library of the Netherlands) in The Hague. There is a maximum of 150 participants. Registration is now possible at an early bird fee of € 95. After 1 January 2009, the regular fee will be € 110. This fee includes coffee breaks, lunches and a conference dinner on Monday 6 April.
The challenges of “useful” OCR
The National Archive’s digitisation project, British Governance in the 20th century – Cabinet Papers, 1914-1975, has been grappling with issues of “useful” OCR. It might be stating the obvious, but accurate OCR is as useful as the search results it produces.
If OCRd text consistently misspells particularly relevant key words for retrieving certain documents, than the search results against these key words will not always bring up appropriate documents, and will lack in accuracy.
For the National Archives, it was not enough to establish a range of acceptable OCR performance levels purely from a quantitative point of view, eg OCR performance accuracy should not be below 88%. This is because if the remaining 12% of text that is not accurate includes particularly relevant key words for retrieving a certain document that users are likely to search by, the discovery of that document is impeded or made less likely. Eg, if the word “submarine” is particularly relevant to the subject of a document, and it’s consistently misspelt by the OCR software, the likelihood of discovering that document is less than if another, less relevant, word, had been misspelled. So, even matching an established minimum percentage of performance (eg 88%), does not necessarily mean that search results will be accurate or useful.
The National Archives are also adopting a more qualitative approach to run alongside the quantitative one described above. They are concentrating on identifying the most relevant and frequently misspelt “key” words across all of the OCRd documents. They are then planning to run a global “search and replace” to reinstate the correctly spelt words.
Although this will have marginal effect on the overall accuracy ratings, this will increase the usefulness of OCR to the end user.