The Archives Hub and IIIF: supporting the true potential of images on the Web

October 26, 2021 / Jane Stevenson

IIIF is a model for presenting and annotating digital content on the Web, including images and audio/visual files. There is a very active global community that develops IIIF and promotes the principles of open, shareable content. One of the strengths of IIIF is the community, which is a diverse mix of people, including developers and information professionals.

IIIF map showing where there are known IIIF projects and implementations

Images are fundamental carriers of information. They provide a huge amount of value for researchers, helping us understand history and culture. We interact with huge amounts of images, and yet we do not always get as much value out of them as we might. Content may be digitised, but it is often within silos, where the end user has to go to a specific website to discover content and to view a specific image, it is not always easy or possible to discover, gather together, compare, analyse and manipulate images.

IIIF is a particularly useful solution for cultural heritage, where analysis of images is so important. A current ‘Towards a National Collection’ project has been looking at practical applications of IIIF.

The IIIF Solution

Exactly what IIIF enables depends upon a number of factors, but in general it enables:

Deep zoom: view and zoom in closely to see all the detail of an image

Sequencing: navigate through a book or sequence of archival materials

Comparisons: bring images together and put them side-by-side. This can enable researchers to bring together images from different collections, maybe material with the same provenance that has been separated over time.

Search within text: work with transcriptions and translations

Connections: connect to resources such as Wikidata

Use of different IIIF viewers: different viewers have their own features and facilities.

How It Works

The IIIF community tends to talk in terms of APIs. These can be thought of as agreed and structured ways to connect systems. If you have this kind of agreement then you can implement different systems, or parts of systems, to work with the same content, because you are sticking to an agreed structure. The basic principle is to store an image once (on a IIIF server) and be able to use it many times in many contexts.

IIIF is like a a layer above the data stores that host content. The images are accessed through that IIIF layer – or through the IIIF APIs. This enables different agents to create viewers and tools for the data held in all the stores.

Different repositories have their own data stores, but they can share content through the IIIF APIs.

There are a few different APIs that make up the IIIF standard.

Image API

This API delivers the content (or pixels). The image is delivered as a URL, and the URL is structured in an agreed way.

Presentation API

This delivers information on the presentation of the material, such as the sequence of a book, for example, or a bundle of letters, and metadata about the object.

Search API

Allows searching within the text of an object.

Authentication API

Allows materials to be restricted by audience. So, this is useful for sensitive images or images under copyright that may have restrictions.

IIIF viewer

As IIIF images are served in a standard way, any IIIF viewer can access them. Examples of IIIF viewers:

The Universal Viewer: https://universalviewer.io/
Mirador: https://mirador-dev.netlify.app/tests/integration/mirador/
Archival IIIF: https://archival-iiif.github.io/
Storiiies digital storytelling: https://storiiies.cogapp.com/#storiiies

There are a whole host of viewers available, with various functionality. Most will offer the basics of zooming and cropping. There does seem to be a question around why so many viewers are needed. It might be considered a better approach for the community to work on a limited group of viewers, but this may be a politically driven desire to own and brand a viewer. In the end, a IIIF viewer can display any IIIF content, and each viewer will have its own features and functionality.

To find out more about how researchers can benefit from IIIF, you may like to watch this presentation on YouTube (59m): Using IIIF for research

Some Examples

In many projects, the aim is to digitise key materials, such as artworks of national importance and rare books and manuscripts, in order to provide a rich experience for end users. For instance, the Raphael Cartoons at the V&A are now available to explore different layers and detail, even enabling the infra-red view and surface view, to allow researchers to study the paintings in great depth. Images can easily be compared within your own workspace, by pulling in other IIIF images.

The V&A Raphael Cartoons can be viewed in ultra high resolution colour, exploring all of the layers

What is the Archives Hub planning to do with IIIF?

Hosting content: We are starting a 15 month project to explore options for hosting and delivering content. Integral to this project will be providing a IIIF Image API. As referenced above, this will mean that the digital content can be viewed in any IIIF viewer, because we will provide the necessary URLs to do so. One of the barriers for many archives is that images need to be on a IIIF server in order to utilise the Image API. It may be that Jisc can provide this service.

Creation of IIIF manifests: We’ll talk more about this in future blog posts, but the manifest is a part of the Presentation API. It contains a sequence (e.g. ordering of a book), as well as metadata such as a title, description, attribution, rights information, table of contents, and any other information about the objects that may be useful for presentation. We will be looking at how to create manifests efficiently and at scale, and the implications for representing hierarchical collections.

Providing an interface to manage content: This would be useful for any image store, so it does not relate specifically to IIIF. But it may have implications around the metadata provided and what we might put into a IIIF manifest.

Integrating a IIIF viewer into the Archives Hub: We will be providing a IIIF viewer so that the images that we host, and other IIIF images, can be viewed within the Archives Hub.

Assessing image quality: A key aim of this project is to assess the real-world situation of a typical archive repository in the UK, and how they can best engage with IIIF. Image resolution is one potential issue. Whilst any image can be served through the IIIF API, a lower resolution image will not give the end user the same sort of rich experience with zooming and analysing that a high resolution image provides. We will be considering the implications of the likely mix of different resolutions that many repositories will hold.

Looking at rights and IIIF: Rights are an important issue with archives, and we will be considering how to work with images at scale and ensure rights are respected.

Projects often have a finite goal of providing some kind of demonstrator showing what is possible, and they often pre-select material to work with. We are taking a different approach. We are working with a limited number of institutions, but we have not pre-selected ‘good’ material. We are simply going to try things out and see what works and what doesn’t, what the barriers are and how to overcome them. The process of ingest of the descriptive data and images will be part of the project. We are looking to consider both scalability and sustainability for the UK archive sector, including all different kinds of repositories with different resourcing and expertise, and with a whole variety of content and granularity of metadata.

Acknowledgement: This blog post cites the introductory video on IIIF which can be viewed within YouTube.

Employing Machine Learning and Artificial Intelligence in Cultural Institutions

July 9, 2021 / Adrian Stevenson

As mentioned in my last post, we’re looking at the possibilities Artificial Intelligence and Machine Learning can offer the Archives Hub and the archives community in general. I also now have a wider role in Jisc as a ‘Technical Innovations Manager’, so my brief is to consider the wider technical and strategic possibilities of AI/ML for the Digital Resources directorate and Jisc as a whole. We continue to work behind the scenes, but we also keep a watch on cultural heritage and wider sector activities. As part of this I participated in the Aeolian Project’s ‘Online Workshop 1: Employing Machine Learning and Artificial Intelligence in Cultural Institutions’ yesterday.

‘Visual AI and Printed Chapbook Illustrations at the National Library of Scotland’ – Dr Giles Bergel (University of Oxford / National Library of Scotland)

Giles’ team have been using machine learning (ML) on data from data.nls.uk. He outlined their three part approach. First they find illustrations in manuscripts using Google’s EfficientDet object detection convolutional neural network seeded by manually pre-annotated images. They found the object detector worked extremely well after relatively few learning passes. There were a few false positives such as image ink showing through, marginalia and dog ears that would confuse the model.

Image showing false postive ml recognition — False positive ML recognition – ink showthrough

Next they matched and grouped the illustrations using their “state of art” image search engine. Giles believes this shows that AI simplifies the task of finding things that are related in images. The final step was to apply classification alogorithms with the VGG Image Classification Engine which uses Google as a source of labelled images. The lessons learned were:

AI requires well-curated data
Tools for annotating data are no less important than classifiers
Generic image models generalize well to printed books
‘Classical’ computer vision still works
AI software development benefits from end-to-end use-cases including data preparation, refinement, consulting with domain experts, public engagement etc.

‘Machine Learning and Cultural Heritage: What Is It Good Enough For?’ – John Stack (UK Science Museum)

John described how AI is being used as part of the Science Museum’s linked data work to collect data into a central knowledge graph. He noted that the Science Museum are doing a great deal of digitisation but currently they only have what John describes as ‘thin’ object data.

They are looking at using AI for name disambiguation as a first step before adding links to wikidata and using entity recognition to enhance their own catalogue. It stuck me that they, and we at the Hub, have been ‘doing AI’ for a while now with such technologies as entity recognition and OCR before the term AI was used. They are aiming to link through to wikidata such that they can pull in the data and add it to their knowledge graph. This allows them to enhance their local data and apply ML to perform such things as clustering to draw out new insights.

John identified the main benefits of ML currently as suggesting possibilities and identifying trends and gaps. It’s also useful for visualisation and identifying related content as well as enhancing catalogues with new terminology. However there were ‘but’s. ML content needs framing and context. He noted that false positives are not always apparent and usually require specialist knowledge. It’s important to approach things critically and understand what can’t be done. John mentioned that they don’t have any ML driven features in production as yet.

Diagram showing the components of the Heritage Connector software

This was followed by a Q&A where several issues came up. We need to consider how AI may drive new ways/modalities of browsing that we haven’t imagined yet. A major issue is the work needed to feed AI enhancements into user interfaces. Most work so far has been on backend data. AI tools need to integrate into day-to-day workflows for their benefits to be realised. More sector specific case-studies, training materials, tools and models are needed that are appropriate to cultural heritage. See the Heritage Connector blog for more information.

‘AI and the Photoarchive‘ – John McQuaid (Frick Collection), Dr Vardan Papyan (University of Toronto), and X.Y. Han (Cornell University)

The Frick Collection have been using the PyTorch deep neural network to identify labels for their photo archive collection. They then compared the ML results as a validation exercise with internally crowdsourced data from their staff and curators captured by the Zooinverse software for the same photos.

Frick Collection workflow — Frick Collection ML workflow

They found that 67% of the ML labels matched with the crowdsource validations which they considered a good result. They concluded that at present ML is most useful for ‘curatorial amplification’, but much human effort is still needed. This auto-generation of metadata was their main use case so far.

‘Keep True: Three Strategies to Guide AI Engagement‘ – Thomas Padilla (Center for Research Libraries)

Thomas believes GLAMs have an opportunity to distinguish themselves in the AI space. He covered a number of themes, the first being the ’Non-scalability imperative’. Scale is everywhere with AI. There’s a great deal of marketing language about scale, but we need to look at all the non-scalable processes that scale depends on. There’s a problematic dependency where scalability is made possible by non-scalable processes, resources and people. Heterogeneity and diversity can become a problem to be solved by ML. There’s little consideration that AI should be just and fair.

The second theme was ‘Neoliberal traps’ in AI. Who says ethical AI is ethical AI? GLAMs are trying to do the right thing with AI, but this is in the context of neoliberal moral regulation which is unfair and ineffective. He mentioned some of the good examples from the sector including from CILIP, Museums AI Network and his own ‘Responsible Operations‘ paper.

He credited Melissa Terras for asking the question “How are you going to advocate for this with legislation?”. The US doesn’t have any regulations at the moment to get the private sector to get better. I mentioned the UK AI Council who are looking at this in the UK context, and the recent CogX event where the need for AI regulation was discussed in many of the sessions.

The final theme was ‘Maintenance as Innovation’. Information maintenance is a Practice of Care. There is an asserted dichotomy between maintenance and innovation that’s false. Maintenance is sustained innovation and we must value the importance of maintenance to innovation. He appealed to the origin of the word ‘innovation’ which derives from the latin ‘innovare’ which means “to alter, renew, restore, return to a thing, introduce changes in the way something is done or made”. It’s not about creating from new. At the Hub we wholeheartedly endorse this view. We feel there’s far too much focus on the latest technology meme and we’ve had tensions within our own organisation along these lines. There may appear to be some irony here given the topic of this post, but we have been doing AI for a while as noted above. He referred us to https://themaintainers.org/ for more on this.

Roundtable discussion with the AEOLIAN Project Team

Dr Lise Jaillant, Dr Annalina Caputo, Glen Worthey (University of Illinois), Prof. Claire Warwick (Durham University), Prof. J. Stephen Downie (University of Illinois), Dr Paul Gooding (Glasgow University), and Ryan Dubnicek (University of Illinois).

Stephen Downie talked about the need for standardisation of ML extracted features so we can re-use these across GLAMs in a consistent way. The ‘Datasheets for Datasets’ paper was mentioned that proposes “a short document to accompany public datasets, commercial APIs, and pretrained models”. This reminded me of Yves Bernaert’s talk about the related need for standardisation of carbon consumption measures. Both are critical issues and possible areas for Jisc to be involved in providing leadership. Another point that Stephen made is that researchers are finding they can’t afford the bill for ML processing. Finding hardware and resources is a big problem. As noted by ML guru Andrew Ng, we have a considerable data issue with AI and ML work . It may be that we need to work more on the data rather than wasting time, electricity and money re-creating expensive ML models. A related piece of work, ‘Lessons from Archives‘ was also mentioned in this regard. There is a case for sharing model developments across the sector for efficiency and sustainability here.

Artificial Intelligence – Getting the Next Ten Years Right

June 23, 2021 / Adrian Stevenson / 2 Comments

I attended the ‘CogX Global Leadership Summit and Festival of AI’ last week, my first ‘in-person’ event in quite a while. The CogX Festival “gathers the brightest minds in business, government and technology to celebrate innovation, discuss global topics and share the latest trends shaping the defining decade ahead”. Although the event wasn’t orientated towards archives or cultural heritage specifically, we are doing work behind the scenes on AI and machine learning with the Archives Hub that we’ll say more about in due course. Most of what’s described below is relevant to all sectors as AI is a very generalised technology in its application.

My attention was drawn to the event by my niece Laura Stevenson who works at Faculty and was presenting on ‘How the NHS is using AI to predict demand for services‘. Laura has led on Faculty’s AI driven ‘Early Warning System’ that forecasts covid patient admissions and bed usage for the NHS. The system can use data from one trust to help forecast care for a trust in another area, and can help with best and worst scenario planning with 95% confidence. It also incorporates expert knowledge into the modelling to forecast upticks more accurately than doubling rates can. Laura noted that embedding such a system into operational workflows is a considerable extra challenge to developing the technology.

Screenshot of Explainability Data — Example of AI explainability data from the Early Warning System (image *©Faculty.ai* )

The system includes an explainability feature showing various inputs and the degree to which they affect forecasting. To help users trust the tool, the interface has a model performance tab so users can see information on how accurate the tool has been with previous forecasts. The tool is continuing to help NHS operational managers make planning decisions with confidence and is expected to have lasting impact on NHS decision making.

‘Responsible leadership: The risks and the rewards of advancing the state of the art in AI’ – Lila Ibrahim

Lila works at Deep Mind who are looking to use AI to unlock whole new areas of science. Lila highlighted the role of the AI Council who are providing guidance to UK Government in regard to UK AI research. She talked about Alphafold that has been addressing the 50 year old challenge of protein folding. This is a critical issue as being able to predict protein folding unlocks many possibilities including disease control and using enzymes to break down industrial waste. DeepMind have already created an AI system that can help predict how a protein folding occurs and have a peer reviewed article coming out soon. They are trying to get closer to the great challenge of general intelligence.

‘Sustainable Technologies, Green IT & Cloud‘ – Yves Bernaert, Senior Managing Director, Accenture

Yves focussed on company and corporate responsibility, starting his session with some striking statistics:

100 companies produce 70% of global carbon emissions.
40% of water consumption is by companies.
40% of deforestation is by companies.
There is 80 times more industrial waste than consumer waste.
20% of the acidification of the ocean is produced by 20 companies only.

Yves therefore believes that companies have a great responsibility, and technology can help to reduce climate impact. 2% of global electricity comes from data centres currently and is growing exponentially, soon to be 8%. A single email produces on average 4g of carbon. Yves stressed that all companies have to accept that now is the time to come up with solutions and companies must urgently get on with solving this problem. IT energy consumption needs to be seen as something to be fixed. If we use IT more efficiently, emissions can be reduced by 20-30%. The solution starts with measurement which must be built into the IT design process.

We can also design software to be far more efficient. Yves gave the example of AI model accuracy. More accuracy requires more energy. If 96% accuracy is to be improved by just 2%, the cost will be 7 times more energy usage. To train a single neural network requires the equivalent of the full lifecycle energy consumption of five cars. These are massive considerations. Interpreted program code has much higher energy use than compiled code such as C++.

A positive note is that 80% of the global IT workload is expected to move to the cloud in the next 3 years. This will reduce carbon emissions by 84%. Savings can be made with cloud efficiency measures such as scaling systems down and outwards so as not to unneccessarily provision for occasional workload spikes. Cloud migration can save 60 million tons carbon per year which is the equivalent of 20 million full lifecycle car emissions. We have to make this happen!

On where are the big wins, Yves said this is also in the IT area. Companies need to embed sustainability into their goals and strategy. We should go straight for the biggest spend. Make measurements and make changes that will have the most effect. Allow departments and people to know their carbon footprint.

* Update 28th June 2021 * – It was remiss of me not to mention that I’m working on a number of initiatives relating to green sustainable computing at Jisc. We’re looking at assessing the carbon footprint of the Archives Hub using the Cloud Carbon Footprint tool to help us make optimisations. I’m also leading on efforts within my directorate, Digital Resources, to optimise our overall cloud infrastructure using some of the measures mentioned above in conjuction with the Jisc Cloud Solutions team and our General Infrastructure team. Our Cloud CTO Andy Powell says more on this in his ‘AI, cloud and the environment‘ blog post.

‘Future of Research’ – Prof. Dame Ottoline Leyser, CEO, UK Research and Innovation (UKRI)

Ottoline believes that pushing the boundaries of how we support research needs to happen. Research is now more holistic. We draw in what we need to create value. The lone genius is a big problem for research culture and it has to go. Research is insecure and needs connectivity.

Ottoline believes AI will change everything about how research is done. It’s initially replacing mundane tasks but will some more complex tasks such as spotting correlations. Eventually AI will be used as a tool to help understanding in a fundamental way. In terms of the existential risk of AI, we need to embed research as collective endeavour and share effort to mitigate and distribute this risk. It requires culture change, joining up education and entrepreneurship.

We need to fund research in places that are not the usual places. Ottoline likes a football analogy where people are excited and engaged at all levels of the endeavour, whether in the local park or at the stadium. She suggests research at the moment is more like elitist Polo not football.

Ottoline mentioned that UKRI funding does allow for white spaces research. Anyone can apply. However, we need to create wider white spaces to allow research in areas not covered by the usual research categories. It will involve braided and micro careers, not just research careers. Funding is needed to support radical transitions. Ottonline agrees that the slow pace of publication and peer review is a big problem that undermines research. We need to broaden ways we evaluate research. Peer Review is helpful but mustn’t slow things down.

‘Ethics and Bias in AI‘ – Rob Glaser, CEO & Founder of RealNetworks

Rob suggests we are in an era with AI where there are no clear rules of the road yet. The task for AI is to make it safe to ‘drive’ with regulations. We can’t stop facial recognition any more than we can stop gravity. We need datasets for governance so we can check accuracy against these for validation. Transparency is also required so we can validate algorithms. A big AI concern is the tribalism on social media.

‘AI and Healthcare‘ – Rt. Hon. Matt Hancock

Matt Hancock believes we are at a key moment with healthcare and AI technology where it’s now of vital importance. Data saves lives! The next thing is how to take things forward in NHS. A clinical trials interoperability programme is starting that will agreed standards to get more out of data use, and the Government will be updating it’s Data strategy soon. He suggests we need to remove silos and commercial incentives (sic). On the use of GP data he suggests we all agree on the use of data, but the question is how it’s used. The NHS technical architecture needs to improve for better use and building data into the way the NHS works. GPs don’t own patient data, it is the citizen.

He said a data lake is being built across the NHS. Citizen interaction with health data is now greater than ever before and NHS data presents a great opportunity for research, and an enormous opportunity for the use of data to advance health care. He suggested we need to radically simplify the NHS information governance rules. On areas where not enough progress has been made, he mentioned the lack of separation of data layers is currently a problem. So many applications silo their data. There has also been a culture of Individual data with personal curation. The UK is going for a TRE first approach: ‘Trusted Research Environment service for England‘. Data is the preserve of the patient who will allow accredited researchers to use the data through the TRE. The clear preference of citizens is sharing data if they trust the sharing mechanism. Every person goes through a consent process for all data sharing. Acceptance requires motivating people with the lifesaving element of research. If there’s trust, the public will be on side. Researchers in this domain with have to abide by new rules to allow us to build on this data. He mentioned that Ben Goldacre will look at the line where open commons ends and NHS data ownership begins in the forthcoming Goldacre Review.