Last week I came back from my very first ICDAR conference, inspired and energised for things to come! The International Conference on Document Analysis and Recognition (ICDAR) is the main international event for scientists and practitioners involved in document analysis and recognition. Its 17th edition was held in San José, California, 21-26 August 2023.
ICDAR 2023 featured a three-day conference, including several competitions to challenge the field, as well as post-conference workshops and tutorials. All conference papers were made available as conference proceedings with Springer. 155 submissions were selected for inclusion into the scientific programme of ICDAR 2023, out of which 55 were delivered as oral presentations, and 100 as posters. The conference also teamed up with the International Journal of Document Analysis and Recognition (IJDAR) for a special journal track. 13 papers were accepted and published in a special issue entitled “Advanced Topics of Document Analysis and Recognition,” and were included as oral presentations in the conference programme. Do have a look at the programme booklet for more information!
ICDAR 2023 Logo
Each conference day included a thought-provoking keynote talk. The first one, by Marti Hearst, Professor and Interim Dean of the UC Berkeley School of Information, was entitled “A First Look at LLMs Applied to Scientific Documents.” I learned about three platforms using Natural Language Processing (NLP) methods on PDF documents: ScholarPhi, Paper Plain, and SCIM. These projects help people read academic scientific publications, for example by enabling definitions for mathematical notations, or generating glossary for nonce words (e.g. acronyms, symbols, jargon terms); make medical research more accessible by enabling simplified summaries and Q&A; and classifying key passages in papers to enable quick and intelligent paper skimming.
The second keynote talk, “Enabling the Document Experiences of the Future,” was by Vlad Morariu, Senior Research Scientist at Adobe Research. Vlad addressed the need for human-document interaction, and took us through some future document experiences: PDF re-flows for mobile devices, documents read themselves, and conversational functionalities such as asking questions and receiving answers. Enabling this type of ultra-responsive documents is reliant on methods such as structural element detection, page layout understanding, and semantic connections.
The third and final keynote talk was by Seiichi Uchida, Distinguished Professor and Senior Vice President, Kyushu University, Japan. In his talk, “What Are Letters?,” Seiichi took us through the four main functions of letters and text: message (transmission of verbalised info), label (disambiguation of objects and environments), design (give a nonverbal info, such as impression), and code (readability under various noises and deformations). He provoked us to contemplate how our lives were affected by texts around us, and how could we analyse the correlation between our behaviour and the texts that we read.
Prof Seiichi Uchida giving his keynote talk on “What Are Letters?”
When it came to papers submitted for review by the conference committee, the most prominent topic represented in those submissions was handwriting recognition, with a growing number of papers specifically tackling historical documents. Other submission topics included Graphics Recognition, Natural Language Processing for Documents (D-NLP), Applications (including for medical, legal, and business documents), and other types of Document Analysis and Recognition topics (DAR).
Screenshot of a slide showing the main submission topics for ICDAR 2023
Some of the papers that I attended tackled Named Entity Recognition (NER) evaluation methods and genealogical information extraction; papers dealing with Document Understanding, e.g. identifying the internal structure of documents, and understanding the relations between different entities; papers on Text and Document Recognition, such as looking into a model for multilingual OCR; and papers looking into Graphics, especially the recognition of table structure and content, as well as extracting data from structure diagrammes, for example in financial documents, or flowchart recognition. Papers on Handwritten Text Recognition (HTR) dealt with methods for Writer Retrieval, i.e. identifying documents likely written by specific authors, the creation of generic models, text line detection, and more.
The conference included two poster sessions, featuring an incredibly rich array of poster presentations, as well as doctoral consortia. One of my favourite posters was presented by Mirjam Cuper, Data Scientist at the National Library of the Netherlands (KB), entitled “Unraveling confidence: examining confidence scores as proxy for OCR quality.” Together with colleagues Corine van Dongen and Tineke Koster, she looked into confidence scores provided by OCR engines, which indicate the level of certainty in which a word or character were accurately recognised. However, other factors are at play when measuring OCR quality – you can watch a ‘teaser’ video for this poster.
Conference participants at one of the poster sessions
As mentioned, the conference was followed by three days of tutorials and workshops. I enjoyed the tutorial on Computational Analysis of Historical Documents, co-led by Dr Isabelle Marthot-Santaniello (University of Bale, Switzerland) and Dr Hussein Adnan Mohammed (University of Hamburg, Germany). Presentations focused on the unique challenges, difficulties, and opportunities inherent to working with different types of historical documents. The distinct difficulties posed by historical handwritten manuscripts and ancient artifacts necessitate an interdisciplinary strategy and the utilisation of state-of-the-art technologies – and this fusion leads to the emergence of exciting and novel advancements in this area. The presentations were interwoven with great questions and a rich discussion, indicative of the audience’s enthusiasm. This tutorial was appropriately followed by a workshop dedicated to Computational Palaeography (IWCP).
I especially looked forward to the next day’s workshop, which was the 7th edition of Historical Document Imaging and Processing (HIP’23). It was all about making documents accessible in digital libraries, looking at methods addressing OCR/HTR of historical documents, information extraction, writer identification, script transliteration, virtual reconstruction, and so much more. This day-long workshop featured papers in four sessions: HTR and Multi-Modal Methods, Classics, Segmentation & Layout Analysis, and Language Technologies & Classification. One of my favourite presentations was by Prof Apostolos Antonacopoulos, talking about his work with Christian Clausner and Stefan Pletschacher on “NAME – A Rich XML Format for Named Entity and Relation Tagging.” Their NAME XML tackles the need to represent named entities in rich and complex scenarios. Tags could be overlapping and nested, character-precise, multi-part, and possibly with non-consecutive words or tokens. This flexible and extensible format addresses the relationships between entities, makes them interoperable, usable alongside other information (images and other formats), and possible to validate.
Prof Apostolos Antonacopoulos talking about “NAME – A Rich XML Format for Named Entity and Relation Tagging”
I’ve greatly enjoyed the conference and its wonderful community, meeting old colleagues and making new friends. Until next time!
Digitised archives and library collections are rich resources for creative practitioners, including video game makers, who can bring history to life in new ways with immersive storytelling. A wonderful example of this is Astrologaster by Nyamyam, an interactive comedy set in Elizabethan London, based on the manuscripts of medical astrologer Simon Forman, which is currently showcased in the British Library’s Digital Storytelling exhibition.
On Friday 15th September we are delighted to host an event to celebrate the making and the music of Astrologaster. Featuring game designer Jennifer Schneidereit in conversation with historian Lauren Kassell discussing how they created the game. Followed by a vocal quartet who will sing madrigal songs from the soundtrack composed by Andrea Boccadoro. Each character in the game has their own Renaissance style theme song with witty lyrics written by Katharine Neil. This set has never before been performed live, so we can’t wait to hear these songs at the Library and we would love for you to join us, click here to book. We've had the title song, which you can play below, as an earworm for the last few months!
Simon Forman was a self-taught doctor and astrologer who claimed to have cured himself of the plague in 1592. Despite being unlicensed and scorned by the Royal College of Physicians he established a practice in London where he analysed the stars to diagnose and solve his querents’ personal, professional and medical problems. Forman documented his life and work in detail, leaving a vast quantity of papers to his protégé Richard Napier, whose archive was subsequently acquired by Elias Ashmole for the Ashmolean Museum at the University of Oxford. In the nineteenth century this collection transferred to the Bodleian Library, where Forman’s manuscripts can still be consulted today.
Screen capture image of the Casebooks digital edition showing ‘CASE5148’.
Lauren Kassell, Michael Hawkins, Robert Ralley, John Young, Joanne Edge, Janet Yvonne Martin-Portugues, and Natalie Kaoukji (eds.), ‘CASE5148’, The casebooks of Simon Forman and Richard Napier, 1596–1634: a digital edition, https://casebooks.lib.cam.ac.uk/cases/CASE5148, accessed 1 September 2023.
Funded by the Wellcome Trust, the Casebooks Project led by Professor Lauren Kassell at the University of Cambridge, spent over a decade researching, digitising, documenting and transcribing these records. Producing The casebooks of Simon Forman and Richard Napier, 1596–1634: a digital edition published by Cambridge Digital Library in May 2019. Transforming the archive into a rich searchable online resource, with transcriptions and editorial insights about the astrologers’ records, alongside digitised images of the manuscripts.
In 2014 Nyamyam’s co-founder and creative director Jennifer Schneidereit saw Lauren present her research on Simon Forman’s casebooks, and became fascinated by this ambitious astrologer. Convinced that Forman and his patients’ stories would make an engaging game with astrology as a gameplay device, she reached out to Lauren to invite her to be a consultant on the project. Fortunately Lauren responded positively and arranged for the Casebooks Project to formally collaborate with Nyamyam to mine Forman’s patient records for information and inspiration to create the characters and narrative in the Astrologaster game.
Still image of a playthrough video demonstrating how to play Astrologaster made by Florence Smith Nicholls for the Digital Storytelling exhibition
At the British Library we are interested in collecting and curating interactive digital narratives as part of our ongoing emerging formats research. One method we are investigating is the acquisition and creation of contextual information, such as recording playthrough videos. In the Digital Storytelling exhibition you can watch three gameplay recordings, including one demonstrating how to play Astrologaster. These were made by Florence Smith Nicholls, a game AI PhD researcher based at Queen Mary University of London, using facilities at the City Interaction Lab within the Centre for Human-Computer Interaction Design at City, University of London. Beyond the exhibition, these recordings will hopefully benefit researchers in the future, providing valuable documentation on the original ‘look and feel’ of an interactive digital narrative, in addition to instructions on use whenever a format has become obsolete.
The Digital Storytelling exhibition is open until the 15th October 2023 at the British Library, displaying 11 narratives that demonstrate the evolving field of interactive writing. We hope you can join us for upcoming related events, including the Astrologaster performance on Friday 15th September, and an epic Steampunk Late on Friday 13th October. We are planning this Late with Clockwork Watch, Blockworks and Lancaster University's Litcraft initiative, so watch this blog for more information on this event soon.
The British Library has joined hands with the Wikimedia Foundation to support the Wikisource Loves Manuscripts (WiLMa) project, sharing 76 Javanese manuscripts, including what is probably the largest Javanese manuscript in the world, digitised as part of the Yogyakarta Digitisation Project. The manuscripts, which are now held in the British Library, were taken from the Kraton (Palace) of Yogyakarta following a British attack in June 1812. The British Library’s digitisation project was funded by Mr. S P Lohia and included conservation, photography, quality assurance and publication on the Library’s Digitised Manuscripts website, and the presentation of complete sets of digital images to the Governor of Yogyakarta Sri Sultan Hamengkubuwono X, the National Library of Indonesia, and the Library and Archives Board of Yogyakarta.
3D model ofMenak Amir Hamza (British Library Add MS 12309), probably the largest Javanese manuscript in the world
“Never before has a library of Javanese manuscripts of such importance been made available to the internet, especially for easy access to the almost 100 million Javanese people worldwide.”
User:Bennylin said about the British Library donation
As a global movement, Wikimedia is able to connect the Library with communities of origin, who can use the digitised manuscripts to revitalise their language online. As such, we have a history of collaboration with the Wikimedia community, hosting Wikimedians-in-Residence and working with the Wikisource community. In 2021, we collaborated with the West Bengal Wikimedians User Group to organise two Wikisource competitions (in Spring and Autumn). Forty rare Bengali books, digitised as a part of the Two Centuries of Indian Print project, were made available on Wikisource. The Bengali Wikisource community has corrected more than 5,000 pages of text, which were OCRed as part of the project.
“As part of our global engagement with Wikimedia communities, we were thrilled to engage in a partnership with the Bengali Wikisource community for the proofreading of rare and unique books digitised as part of the Two Centuries of Indian Print project. We extend our gratitude towards the community’s unwavering commitment and the enthusiasm of its members, which have greatly enhanced the accessibility of these historic gems for readers and researchers.”
Dr Adi Keinan-Schoonbaert, Digital Curator, British Library
The developing Javanese Wikisource community has already started using the newly digitised Javanese manuscripts in their project, and has plans ranging from transliteration and translation, to recording the content being sung, as originally intended. (Recording of Ki Sujarwo Joko Prehatin, singing (menembang) the texts of Javanese manuscripts, at the British Library, 12 March 2019; recording by Mariska Adamson).
Screenshot of a Javanese manuscript being used for training an HTR model using Transkribus
The Library’s collaboration with the Javanese community started earlier this year, when the Wikisource community included three manuscripts from the Library’s Henry D. Ginsburg Legacy Digitisation Projects in the list of focus texts for a Wikisource competition. Parts of these three long manuscripts were proofread by the community during the competition and now they are being used to create a Handwritten Text Recognition (HTR) model for the Javanese script using Transkribus, as part of our ongoing WiLMa initiative.
This is a guest post by Natalie Lucy, a PhD student at University College London, who recently undertook a British Library placement to work on a project Mapping Caribbean Diasporic Networks through the correspondence of Andrew Salkey.
Project Objectives
The project, supervised by curators Eleanor Casson and Stella Wisdom, focussed on the extensive correspondence contained within Andrew Salkey’s archive. One of the initial objectives was to digitally depict the movement of key Caribbean writers and artists, as it is evidenced within the correspondence, many of whom travelled between Britain and the Caribbean as well as the United States, Central and South America and Africa. Although Salkey corresponded with a diverse range of people, we therefore focused on the letters in his archive which were from Caribbean writers and academics and which illustrated patterns of movement of the Caribbean diaspora. Much of the correspondence stems from 1960s and 1970s, a time when Andrew Salkey was particularly active both in the Caribbean Artists Movement and, as a writer and broadcaster, at the BBC.
Photograph of Andrew Salkey
Andrew Salkey was unusual not only for the panoply of writers, artists and politicians with whom he was connected, but that he sustained those relationships, carefully preserving the correspondence which resulted from those networks. My personal interest in this project stemmed from the fact that my PhD seeks to consider the ways that the Caribbean trickster character, Anancy, has historically been reinvented to say something about heritage and identity. Significant to that question was the way that the Caribbean Artists Movement, a dynamic group of artists and writers formed in London in the mid-1960s, and of which Andrew Salkey was a founder, appropriated Anancy, reasserting him and the folktales to convey something of a literary ‘voice’ for the Caribbean. For this reason, I was also interested in the writing networks which were evidenced within the correspondence, together with their impact.
What is Gephi?
Prior to starting the project, Eleanor, who had catalogued the Andrew Salkey archive and Digital Curator, Stella, had identified Gephi as a possible software application through which to visualise this data. Gephi has been used in a variety of projects, including several at Harvard University, examples of the breadth and diversity of those initiatives can be found here. Several of these projects have social networks or historical trading routes as their focus, with obvious parallels to this project. Others notably use correspondence as their main data.
Gathering the Data
Andrew Salkey was known as something of a chronicler. He was interested in letters and travel and was also a serious collector of stamps. As such, he had not only retained the majority of the letters he received but categorised them. Eleanor had originally identified potential correspondents who might be useful to the project, selecting writers who travelled widely, whose correspondence had been separately stored by Salkey, partly because of its volume, and who might be of wider interest to the public. These included the acclaimed Caribbean writers, Samuel Selvon, George Lamming, Jan Carew and Edward Kamau Brathwaite and publishers and political activists, Jessica and Eric Huntley.
Our initial intention was to limit the data to simple facts which could easily be gleaned from the letters. Gephi required that we did so on a spreadsheet ,which had to conform to a particular format. In the first stages of the project, the data was confined to the dates and location of the correspondence, information which could suggest the patterns of movement within the diaspora. However, the letters were so rich in detail, that we ultimately recorded other information. This included any additional travel taken by any of the correspondents, and which was clearly evidenced in the letters, together with any passages from the correspondence which demonstrated either something of the nature and quality of the friendships or, alternatively, the mutual benefit of those relationships to the careers of so many of the writers.
Creating a visual network
Dr Duncan Hay was invited to collaborate with me on this project, as he has considerable expertise in this field, his research interests include web mapping for culture and heritage and data visualisation for literary criticism. After the initial data was collated, we discussed with Duncan what visualisations could be created. It became apparent early on that creating a visualisation of the social networks, as opposed to the patterns of movement, might be relatively straightforward via Gephi, an application which was particularly useful for this type of graph. I had prepared a spreadsheet but, Gephi requires the data to be presented in a strictly consistent way which meant that any anomalies had to be eradicated and the data effectively ‘cleaned up’ using Open Refine. Gephi also requires that information is presented by way of a system of ‘nodes’; ‘edges’ and ‘attributes’ with corresponding spreadsheet columns. In our project, the ‘nodes’ referred to Andrew Salkey and each of the correspondents and other individuals of interest who were specifically referred to within the correspondence. The edges referred to the way that those people were connected which, in this case, was through correspondence. However, what added to the potential of the project was that these nodes and edges could be further described by reference to ‘attributes.’ The possibility of assigning a range of ‘attributes’ to each of the correspondents allowed a wealth of additional information to be provided about the networks. As a consequence, and in order to make any visualisation as informative as possible, I also added brief biographical information for each of the writers and artists to be inputted as ‘attributes’ together with some explanation of the nature of the networks that were being illustrated.
The visual illustration below shows not only the quantity of letters from the sample of correspondents to Andrew Salkey (the pink lines), but also shows which other correspondents formed part of those networks and were referenced as friends or contacts within specific items of correspondence. For example, George Lamming references academic, Rex Nettleford and writer and activist, Claudia Jones, the founder of the Notting Hill Carnival, in his correspondence, connections which are depicted in grey.
Gephi: Andrew Salkey correspondence network
The aim was, however, for the visualisation to also be interactive. This required considerable further manipulation of the format and tools. In this illustration you can see the information that is revealed about the prominent Barbadian writer, George Lamming which, in an interactive format, can be accessed via the ‘i’ symbols beside many of the nodes coloured in green.
Whilst Gephi was a useful tool with which to illustrate the networks, it was less helpful as a way to demonstrate the patterns of movement, one of the primary objectives of the project. A challenge was, therefore, to create a map which could be both interactive and illustrative of the specific locations of the correspondents as well as their movement over time. With Duncan’s input and expertise, we opted for a hybrid approach, utilising two principal ways to illustrate the data: we used Gephi to create a visualisation of the ‘networks’ (above) and another software tool, Kepler.gl, to show the diasporic movement.
A static version of what ultimately will be a ‘moving’ map (illustrating correspondence with reference to person, date and location) is shown below. As well as demonstrating patterns of movement, it should also be possible to access information about specific letters as well as their shelf numbers through this map, hopefully making the archive more accessible.
Patterns of diasporic movement from Andrew Salkey's correspondence, illustrated in Kepler.gl
Whilst we are still exploring the potential of this project and how it might intersect with other areas of research and archives, it has already revealed something of the benefits of this type of data visualisation. For example, a project of this type could be used as an educational tool, providing something of a simple, but dynamic, introduction to the Caribbean Artists Movement. Being able to visualise the project has also allowed us to input information which confirms where specific letters of interest might be found within the archive. Ultimately, it is hoped that the project will offer ways to make a rich, yet arguably undervalued, archive more accessible to a wider audience with the potential to replicate something of an introductory model, or ‘pilot’ for further archives in the future.
Greetings! I’m Xiaoyan Yang, from Beijing, China, an MSc student at University College London. It was a great pleasure to have the opportunity to do a four-week placement at the British Library and Wikimedia UK under the supervision of Lucy Hinnie, Wikimedian in Residence, and Stella Wisdom, Digital Curator, Contemporary British Collections. I mainly focused on the Michael Marks Awards for Poetry Pamphlets Project and Lotus Sutra Project, and the collaboration between the Library and Wikimedia.
What interested you in applying for a placement at the Library?
This kind of placement, in world-famous cultural institutions such as the Library and Wikimedia is abrand-new experience for me. Because my undergraduate major is economic statistics, most ofmy internships in the past were in commercial and Internet technology companies. The driving force of my interest in digital humanities research, especially related data, knowledge graph, and visualization, is to better combine information technologies with cultural resources, in order to reach a wider audience, and promote the transmission of cultural and historical memoryin a more accessible way.
Libraries are institutions for the preservation and dissemination of knowledge for the public, and the British Library is one of the largest and best libraries in the worldwithout doubt. It has long been a leader and innovator in resource protection and digitization. The International Dunhuang Project(IDP) initiated by the British Library is now one of the most representative transnational collaborative projects of digital humanistic resources in the field. I applied for a placement opportunity hoping to learn more about the usage of digital resources in real projects andthe process of collaboration from the initial design to the following arrangement.I also wanted to have the chance to get involved in the practice of linked data, to accumulate experience, and find the direction of future improvements.
I would like to thank Dr Adi Keinan-Schoonbaert for her kind introduction to the British Library's Asian and African Digitization projects, especially the IDP, which has enabled me to learn more about the librarian-led practices in this area. At the same time, I was very happy to sit in on the weekly meetings of the Digital Scholarship Team during this placement, which allowed me to observe how collaboration between different departments are carried out and managed in a large cultural resource organizationlike the British Library.
What is the most surprising thing you have learned?
In short, it is so easy to contribute knowledge at Wikimedia. Inthis placement, one of my very first tasks was to upload information about winning and shortlisted poems of the Michael Marks Awards for Poetry Pamphlets for each year from 2009 to the latest, 2021, to Wikidata. The first step was to check whether this poem and its author and publisher already existed in Wikidata. If not, I created an item page for it. Before I started, I thought the process would be very complicated, but after I started following the manual, I found it was actually really easy. I just need to click "Create a new Item".
I always remember that the first item of people that I created was Sarah Jackson, one of the shortlist winners of this award in 2009. The unique QID was automatically generated as Q111940266. With such a simple operation, anyone can contribute to the vast knowledge world of Wiki. Many people who I have never met may read this item page in the future, a page created and perfected by me at this moment. This feeling is magical and full of achievement for me. Also, there are many useful guides, examples and batch loading tools such as Quickstatements that help the users to start editing with joy. Useful guides include the Wikidata help pages for Quickstatements and material from the University of Edinburgh.
An example of one of Xiaoyan’s queries - you can try it here!
How do you hope to use your skills going forward?
My current dissertation researchfocuses on the regional classic Chinese poetry in the Hexi Corridor. This particular geographical area is deeply bound up with the Silk Road in history and has inspired and attracted many poets to visit and write. My project aims to build a proper ontology and knowledge map, then combining with GIS visualization display and text analysis, to explore the historical, geographic, political and cultural changes in this area, from the perspective of time and space. Wikidata provides a standard way to undertake this work.
Thanks to Dr Martin Poulter’s wonderful training and Stuart Prior’s kind instructions, I quickly picked up some practical skills on Wiki queries construction. The layout design of the timeline and geographical visualization tools offered by Wiki query inspired me to improve my skills in this field more in the future. What’s more, although I haven’t had a chance to experience Wikibase yet, I am very interested in it now, thanks to Dr Lucy Hinnie and Dr Graham Jevon’s introduction, I will definitely try it in future.
Would you like to share some Wiki advice with us?
Wiki is very self-learning friendly: on the Help page various manuals and examplesare presented, all of which are very good learning resources.I will keep learning and exploring in the future.
I do want to share my feelings and a little experience with Wikidata. In the Michael Marks Awards for Poetry Pamphlets Project, all the properties used to describe poets, poems and publishers can be easily found in the existing Wikidata property list. However, in the second Lotus Sutra Project, I encountered more difficulties. For example, it is difficult to find suitable items and properties to represent paragraphs of scrolls’ text content and binding design on Wikidata,and this information is more suitable to be represented on WikiCommons at present.
However, as I learn more and more other Wikidata examples, I understand more and more about Wikidata and the purpose of these restrictions. Maintaining concise structured data and accurate correlation is one of the main purposes of Wikidata. It encourages reuse of existing propertiesas well as imposing more qualifications on long text descriptions. Therefore, this feature of Wikidata needs to be taken into account from the outset when designing metadata frameworksfor data uploading.
In the end, I would like to sincerely thank my direct supervisor Lucy for her kind guidance, help, encouragement and affirmation, as well as the British Library and Wikimedia platform. I have received so much warm help and gained so much valuable practical experience, and I am also very happy and honored that by using my knowledge and technology I can make a small contribution to linked data. I will always cherish the wonderful memories here and continue to explore the potential of digital humanities in the future.
Digitisation has become one of the key tasks for the curatorial roles within the British Library. This is supported by two main pillars: the accessibility of the collection items to everybody around the world and the preservation of unique and sometimes, very fragile, items. Digitisation involves many different teams and workflow stages including retrieval, conservation, curatorial management, copyright assessment, imaging, workflow management, quality control, and the final publication to online platforms.
The Heritage Made Digital (HMD) team works across the Library to assist with digitisation projects. An excellent example of the collaborative nature of the relationship between the HMD and International Dunhuang Project (IDP) teams is the quality control (QC) of the Lotus Sutra Project’s digital files. It is crucial that images meet the quality standards of the digital process. As a Digitisation Officer in HMD, I am in charge of QC for the Lotus Sutra Manuscripts Digitisation Project, which is currently conserving and digitising nearly 800 Chinese Lotus Sutra manuscripts to make them freely available on the IDP website. The manuscripts were acquired by Sir Aurel Stein after they were discovered in a hidden cave in Dunhuang, China in 1900. They are thought to have been sealed there at the beginning of the 11th century. They are now part of the Stein Collection at the British Library and, together with the international partners of the IDP, we are working to make them available digitally.
The majority of the Lotus Sutra manuscripts are scrolls and, after they have been treated by our dedicated Digitisation Conservators, our expert Senior Imaging Technician Isabelle does an outstanding job of imaging the fragile manuscripts. My job is then to prepare the images for publication online. This includes checking that they have the correct technical metadata such as image resolution and colour profile, are an accurate visual representation of the physical object and that the text can be clearly read and interpreted by researchers. After nearly 1000 years in a cave, it would be a shame to make the manuscripts accessible to the public for the first time only to be obscured by a blurry image or a wayward piece of fluff!
With the scrolls measuring up to 13 metres long, most are too long to be imaged in one go. They are instead shot in individual panels, which our Senior Imaging Technicians digitally “stitch” together to form one big image. This gives online viewers a sense of the physical scroll as a whole, in a way that would not be possible in real life for those scrolls that are more than two panels in length unless you have a really big table and a lot of specially trained people to help you roll it out.
Or.8210/S.1530: individual panels
Or.8210/S.1530: stitched image
This post-processing can create issues, however. Sometimes an error in the stitching process can cause a scroll to appear warped or wonky. In the stitched image for Or.8210/S.6711, the ruled lines across the top of the scroll appeared wavy and misaligned. But when I compared this with the images of the individual panels, I could see that the lines on the scroll itself were straight and unbroken. It is important that the digital images faithfully represent the physical object as far as possible; we don’t want anyone thinking these flaws are in the physical item and writing a research paper about ‘Wonky lines on Buddhist Lotus Sutra scrolls in the British Library’. Therefore, I asked the Senior Imaging Technician to restitch the images together: no more wonky lines. However, we accept that the stitched images cannot be completely accurate digital surrogates, as they are created by the Imaging Technician to represent the item as it would be seen if it were to be unrolled fully.
Or.8210/S.6711: distortion from stitching. The ruled line across the top of the scroll is bowed and misaligned
Similarly, our Senior Imaging Technician applies ‘digital black’ to make the image background a uniform colour. This is to hide any dust or uneven background and ensure the object is clear. If this is accidentally overused, it can make it appear that a chunk has been cut out of the scroll. Luckily this is easy to spot and correct, since we retain the unedited TIFFs and RAW files to work from.
Or.8210/S.3661, panel 8: overuse of digital black when filling in tear in scroll
Sometimes the scrolls are wonky, or dirty or incomplete. They are hundreds of years old, and this is where it can become tricky to work out whether there is an issue with the images or the scroll itself. The stains, tears and dirt shown in the images below are part of the scrolls and their material history. They give clues to how the manuscripts were made, stored, and used. This is all of interest to researchers and we want to make sure to preserve and display these features in the digital versions. The best part of my job is finding interesting things like this. The fourth image below shows a fossilised insect covering the text of the scroll!
Black stains: Or.8210/S.2814, panel 9
Torn and fragmentary panel: Or.8210/S.1669, panel 1
Insect droppings obscuring the text: Or.8210/S.2043, panel 1
We want to minimise the handling of the scrolls as much as possible, so we will only reshoot an image if it is absolutely necessary. For example, I would ask a Senior Imaging Technician to reshoot an image if debris is covering the text and makes it unreadable - but only after inspecting the scroll to ensure it can be safely removed and is not stuck to the surface. However, if some debris such as a small piece of fluff, paper or hair, appears on the scroll’s surface but is not obscuring any text, then I would not ask for a reshoot. If it does not affect the readability of the text, or any potential future OCR (Optical Character Recognition) or handwriting analysis, it is not worth the risk of damage that could be caused by extra handling.
Reshoot: Or.8210/S.6501: debris over text / No reshoot: Or.8210/S.4599: debris not covering text.
These are a few examples of the things to which the HMD Digitisation Officers pay close attention during QC. Only through this careful process, can we ensure that the digital images accurately reflect the physicality of the scrolls and represent their original features. By developing a QC process that applies the best techniques and procedures, working to defined standards and guidelines, we succeed in making these incredible items accessible to the world.
Read more about Lotus Sutra Project here: IDP Blog
Posted by Mahendra Mahey, former Manager of British Library Labs or "BL Labs" for short
[estimated reading time of around 15 minutes]
This is is my last day working as manager of BL Labs, and also my final posting on the Digital Scholarship blog. I thought I would take this chance to reflect on my journey of almost 9 years in helping to set up, maintain and enabling BL Labs to become a permanent fixture at the British Library (BL).
BL Labs was the first digital Lab in a national library, anywhere in the world, that gets people to experiment with its cultural heritage digital collections and data. There are now several Gallery, Library, Archive and Museum Labs or 'GLAM Labs' for short around the world, with an active community which I helped build, from 2018.
I am really proud I was there from the beginning to implement the original proposal which was written by several colleagues, but especially Adam Farquhar, former head of Digital Scholarship at the British Library (BL). The project was at first generously funded by the Andrew W. Mellon foundation through four rounds of funding as well as support from the BL. In April 2021, the project became a permanently funded fixture, helped very much by my new manager Maja Maricevic, Head of Higher Education and Science.
The great news is that BL Labs is going to stay after I have left. The position of leading the Lab will soon be advertised. Hopefully, someone will get a chance to work with my helpful and supportive colleague Technical Lead of Labs, Dr Filipe Bento, bright, talented and very hard working Maja and other great colleagues in Digital Research and wider at the BL.
The beginnings, the BL and me!
I met Adam Farquhar and Aly Conteh (Former Head of Digital Research at the BL) in December 2012. They must have liked something about me because I started working on the project in January 2013, though I officially started in March 2013 to launch BL Labs.
I must admit, I had always felt a bit intimidated by the BL. My first visit was in the early 1980s before the St Pancras site was opened (in 1997) as a Psychology student. I remember coming up from Wolverhampton on the train to get a research paper about "Serotonin Pathways in Rats when sleeping" by Lidov, feeling nervous and excited at the same time. It felt like a place for 'really intelligent educated people' and for those who were one for the intellectual elites in society. It also felt for me a bit like it represented the British empire and its troubled history of colonialism, especially some of the collections which made me feel uncomfortable as to why they were there in the first place.
I remember thinking that the BL probably wasn't a place for some like me, a child of Indian Punjabi immigrants from humble beginnings who came to England in the 1960s. Actually, I felt like an imposter and not worthy of being there.
Nearly 9 years later, I can say I learned to respect and even cherish what was inside it, especially the incredible collections, though I also became more confident about expressing stronger views about the decolonisation of some of these. I became very fond of some of the people who work or use it, there are some really good kind-hearted souls at the BL. However, I never completely lost that 'imposter and being an outsider' feeling.
What I remember at that time, going for my interview, was having this thought, what will happen if I got the position and 'What would be the one thing I would try and change?'. It came easily to me, namely that I would try and get more new people through the doors literally or virtually by connecting them to the BL's collections (especially the digital). New people like me, who may have never set foot, or had been motivated to step into the building before. This has been one of the most important reasons for me to get up in the morning and go to work at BL Labs.
So what have been my highlights? Let's have a very quick pass through!
BL Labs Launch and Advisory Board
I launched BL Labs in March 2013, one week after I had started. It was at the launch event organised by my wonderfully supportive and innovative colleague, Digital Curator Stella Wisdom. I distinctly remember in the afternoon session (which I did alone), I had to present my 'ideas' of how I might launch the first BL Labs competition where we would be trying to get pioneering researchers to work with the BL's digital collections.
God it was a tough crowd! They asked pretty difficult questions, questions I myself was asking too which I still didn't know the answer too either.
My first gut feeling overall after the event was, this is going to be hard work. This feeling and reality remained a constant throughout my time at BL Labs.
In early May 2013, we launched the competition, which was a really quick and stressful turnaround as I had only officially started in mid March (one and a half months). I remember worrying as to whether anyone would even enter! All the final entries were pretty much submitted a few minutes before the deadline. I remember being alone that evening on deadline day near to midnight waiting by my laptop, thinking what happens if no one enters, it's going to be disaster and I will lose my job. Luckily that didn't happen, in the end, we received 26 entries.
I am a firm believer that we can help make our own luck, but sometimes luck can be quite random! Perhaps BL Labs had a bit of both!
After that, I never really looked back! BL Labs developed its own kind of pattern and momentum each year:
hunting around the BL for digital collections to make into datasets and make available
helping to make more digital collections openly licensed
having hundreds of conversations with people interested in connecting with the BL's digital collections in the BL and outside
working with some people more intensively to carry out experiments
developing ideas further into prototype projects
telling the world of successes and failures in person, meetings, events and social media
launching a competition and awards in April or May
roadshows before and after with invitations to speak at events around the world
the summer working with competition winners
late October/November the international symposium showcased things from the year
'Nothing interesting happens in the office' - Roadshows, Presentations, Workshops and Symposia!
One of the highlights of BL Labs was to go out to universities and other places to explain what the BL is and what BL Labs does. This ended up with me pretty much seeing the world (North America, Europe, Asia, Australia, and giving virtual talks in South America and Africa).
My greatest challenge in BL Labs was always to get people to truly and passionately 'connect' with the BL's digital collections and data in order to come up with cool ideas of what to actually do with them. What I learned from my very first trip was that telling people what you have is great, they definitely need to know what you have! However, once you do that, the hard work really begins as you often need to guide and inspire many of them, help and support them to use the collections creatively and meaningfully. It was also important to understand the back story of the digital collection and learn about the institutional culture of the BL if people also wanted to work with BL colleagues. For me and the researchers involved, inspirational engagement with digital collections required a lot of intellectual effort and emotional intelligence. Often this means asking the uncomfortable questions about research such as 'Why are we doing this?', 'What is the benefit to society in doing this?', 'Who cares?', 'How can computation help?' and 'Why is it necessary to even use computation?'.
Making those connections between people and data does feel like magic when it really works. It's incredibly exciting, suddenly everyone has goose bumps and is energised. This feeling, I will take away with me, it's the essence of my work at BL Labs!
A full list of over 200 presentations, roadshows, events and 9 annual symposia can be found here.
Competitions, Awards and Projects
Another significant way BL Labs has tried to connect people with data has been through Competitions (tell us what you would like to do, and we will choose an idea and work collaboratively with you on it to make it a reality), Awards (show us what you have already done) and Projects (collaborative working).
At the last count, we have supported and / or highlighted over 450 projects in research, artistic, entrepreneurial, educational, community based, activist and public categories most through competitions, awards and project collaborations.
We also set up awards for British Library Staff which has been a wonderful way to highlight the fantastic work our staff do with digital collections and give them the recognition they deserve. I have noticed over the years that the number of staff who have been working on digital projects has increased significantly. Sometimes this was with the help of BL Labs but often because of the significant Digital Scholarship Training Programme, run by my Digital Curator colleagues in Digital Research for staff to understand that the BL isn't just about physical things but digital items too.
Browse through our project archive to get inspiration of the various projects BL Labs has been involved in or highlighted.
Putting the digital collections 'where the light is' - British Library platforms and others
When I started at BL Labs it was clear that we needed to make a fundamental decision about how we saw digital collections. Quite early on, we decided we should treat collections as data to harness the power of computational tools to work with each collection, especially for research purposes. Each collection should have a unique Digital Object Identifier (DOI) so researchers can cite them in publications. Any new datasets generated from them will also have DOIs, allowing us to understand the ecosystem through DOIs of what happens to data when you get it out there for people to use.
However, BL Labs has not stopped there! We always believed that it's important to put our digital collections where others are likely to discover them (we can't assume that researchers will want to come to BL platforms), 'where the light is' so to speak. We were very open and able to put them on other platforms such as Flickr and Wikimedia Commons, not forgetting that we still needed to do the hard work to connect data to people after they have discovered them, if they needed that support.
Our greatest success by far was placing 1 million largely undescribed images that were digitally snipped from 65,000 digitised public domain books from the 19th Century on Flickr Commons in 2013. The number of images on the platform have grown since then by another 50 to 60 thousand from collections elsewhere in the BL. There has been significant interaction from the public to generate crowdsourced tags to help to make it easier to find the specific images. The number of views we have had have reached over a staggering 2 billion over this time. There have also been an incredible array of projects which have used the images, from artistic use to using machine learning and artificial intelligence to identify them. It's my favourite collection, probably because there are no restrictions in using it.
Read the most popular blog post the BL has ever published by my former BL Labs colleague, the brilliant and inspirational Ben O'Steen, a million first steps and the 'Mechanical Curator' which describes how we told the world why and how we had put 1 million images online for anyone to use freely.
It is wonderful to know that George Oates, the founder of Flickr Commons and still a BL Labs Advisory Board member, has been involved in the creation of the Flickr Foundation which was announced a few days ago! Long live Flickr Commons! We loved it because it also offered a computational way to access the collections, critical for powerful and efficient computational experiments, through its Application Programming Interface (API).
I loved working with artists, its my passion! They are so creative and often not restricted by academic thinking, see the work of Mario Klingemann for example! You can browse through our archives for various artistic projects that used the BL's digital collections, it's inspiring.
I was also involved in the first British Library Fashion Student Competition won by Alanna Hilton, held at the BL which used the BL's Flickr Commons collection as inspiration for the students to design new fashion ranges. It was organised by my colleague Maja Maricevic, the British Fashion Colleges Council and Teatum Jones who were great fun to work with. I am really pleased to say that Maja has gone on from strength to strength working with the fashion industry and continues to run the competition to this day.
I am really proud of helping to create the international GLAM Labs community with over 250 members, established in 2018 and still active today. I affectionately call them the GLAM Labbers, and I often ask people to explore their inner 'Labber' when I give presentations. What is a Labber? It's the experimental and playful part of us we all had as children and unfortunately many have lost when becoming an adult. It's the ability to be fearless, having the audacity and perhaps even naivety to try crazy things even if they are likely to fail! Unfortunately society values success more than it does failure. In my opinion, we need to recognise, respect and revere those that have the courage to try but failed. That courage to experiment should be honoured and embraced and should become the bedrock of our educational systems from the very outset.
Two years ago, many of us Labbers 'ate our own dog food' or 'practised what we preached' when me and 15 other colleagues came together for 5 days to produce a book through a booksprint, probably the most rewarding professional experience of my life. The book is about how to set up, maintain, sustain and even close a GLAM Lab and is called 'Open a GLAM Lab'. It is available as public domain content and I encourage you to read it.
Online drop-in goodbye - today!
I organised a 30 minute ‘online farewell drop-in’ on Wednesday 29 September 2021, 1330 BST (London), 1430 (Paris, Amsterdam), 2200 (Adelaide), 0830 (New York) on my very last day at the British Library. It was heart-warming that the session was 'maxed out' at one point with participants from all over the world. I honestly didn't expect over 100 colleagues to show up. I guess when you leave an organisation you get to find out who you actually made an impact on, who shows up, and who tells you, otherwise you may never know.
Those that know me well know that I would have much rather had a farewell do ‘in person’, over a pint and praying for the ‘chip god’ to deliver a huge portion of chips with salt/vinegar and tomato sauce’ magically and mysteriously to the table. The pub would have been Mc'Glynns (http://www.mcglynnsfreehouse.com/) near the British Library in London. I wonder who the chip god was? I never found out ;)
The answer to who the chip god was is in text following this sentence on white on white text...you will be very shocked to know who it was!- s
Spoiler alert it was me after all, my alter ego
Mahendra's online farewell to BL Labs, Wednesday 29 September, 1330 BST, 2021. Left: Flowers and wine from the GLAM Labbers arrived in Tallinn, 20 mins before the meeting! Right: Some of the participants of the online farewell
Leave a message of good will to see me off on my voyage!
It would be wonderful if you would like to leave me your good wishes, comments, memories, thoughts, scans of handwritten messages, pictures, photographs etc. on the following Google doc:
I will leave it open for a week or so after I have left. Reading positive sincere heartfelt messages from colleagues and collaborators over the years have already lifted my spirits. For me it provides evidence that you perhaps did actually make a difference to somone's life. I will definitely be re-reading them during the cold dark Baltic nights in Tallinn.
I would love to hear from you and find out what you are doing, or if you prefer, you can email me, the details are at the end of this post.
BL Labs Sailor and Captain Signing Off!
It's been a blast and lots of fun! Of course there is a tinge of sadness in leaving! For me, it's also been intellectually and emotionally challenging as well as exhausting, with many ‘highs’ and a few ‘lows’ or choppy waters, some professional and others personal.
I have learned so much about myself and there are so many things I am really really proud of. There are other things of course I wish I had done better. Most of all, I learned to embrace failure, my best teacher!
I think I did meet my original wish of wanting to help to open up the BL to as many new people who perhaps would have never engaged in the Library before. That was either by using digital collections and data for cool projects and/or simply walking through the doors of the BL in London or Boston Spa and having a look around and being inspired to do something because of it.
I wish the person who takes over my position lots of success! My only piece of advice is if you care, you will be fine!
Anyhow, what a time this has been for us all on this planet? I have definitely struggled at times. I, like many others, have lost loved ones and thought deeply about life and it's true meaning. I have also managed to find the courage to know what’s important and act accordingly, even if that has been a bit terrifying and difficult at times. Leaving the BL for example was not an easy decision for me, and I wish perhaps things had turned out differently, but I know I am doing the right thing for me, my future and my loved ones.
Though there have been a few dark times for me both professionally and personally, I hope you will be happy to know that I have also found peace and happiness too. I am in a really good place.
I would like to thank former alumni of BL Labs, Ben O'Steen - Technical Lead for BL Labs from 2013 to 2018, Hana Lewis (2016 - 2018) and Eleanor Cooper (2018-2019) both BL Labs Project Officers and many other people I worked through BL Labs and wider in the Library and outside it in my journey.
Where I am off to and what am I doing?
My professional plans are 'evolving', but one thing is certain, I will be moving country!
To Estonia to be precise!
I plan to live, settle down with my family and work there. I was never a fan of Brexit, and this way I get to stay a European.
I would like to finish with this final sweet video created by writer and filmaker Ling Low and her team in 2016, entitled 'Hey there Young Sailor' which they all made as volunteers for the Malaysian band, the 'Impatient Sisters'. It won the BL Labs Artistic Award in 2016. I had the pleasure and honour of meeting Ling over a lovely lunch in Kuala Lumpa, Malaysia, where I had also given a talk at the National Library about my work and looked for remanants of my grandfather who had settled there many years ago.
I wish all of you well, and if you are interested in keeping in touch with me, working with me or just saying hello, you can contact me via my personal email address: [email protected] or follow my progress on my personal website.
Happy journeys through this short life to all of you!
The Chevening Fellowship Programme is the UK government’s international awards scheme aimed at fostering knowledge exchange and collaboration, and developing global leaders. In 2015, the Foreign, Commonwealth & Development Office (FCDO) has partnered with the British Library to offer professionals two new fellowships every year, and recently the two organisations have announced the renewal of their partnership until 2024/25.
These fellowships are unique opportunities for one-year placements at the Library, working with exceptional collections under the Library’s custodianship. The Library has hosted international fellows through this scheme since 2016, with each fellowship framing a distinct project inspired by Library collections. Past and present Chevening Fellows at the Library have focused on geographically diverse collections, from Latin America through Africa to South Asia, with different themes such as archival material from Latin America and the Caribbean, African-language printed books, Nationalism, Independence, and Partition in South Asia and Big Data and Libraries.
We are thrilled to (re-)announce that one of the two placements available for the 2022/2023 academic year will focus on automating the recognition of historical Chinese handwritten texts. This fellowship, originally announced two years ago, had to be postponed due to the pandemic – and we are excited to be able to offer it again. This is a special opportunity to work in the Library’s Digital Research Team, and engage with unique historical collections digitised as part of the International Dunhuang Project and the Lotus Sutra Manuscripts Digitisation Project. Focusing on material from Dunhuang (China), part of the Stein collection, this fellowship will engage with new digital tools and techniques in order to explore possible solutions to automate the transcription of these handwritten texts.
End piece of a Chinese Lotus Sutra Scroll (shelfmark: Or.8210/S.1606). Digitised as part of the Lotus Sutra Manuscripts Digitisation Project.
The context for this fellowship is the Library’s efforts towards making its collection items available in machine-readable format, to enable full-text search and analysis. The Library has been digitising its collections at scale for over two decades, with digitisation opening up access to diversely rich collections. However, it is important for us to further support discovery and digital research by unlocking the huge potential in automatically transcribing our collections. Until recently, Western languages print collections have been the main focus, especially newspaper collections. A flagship collaboration with the Alan Turing Institute, the Living with Machines project, has been applying Optical Character Recognition (OCR) technology to UK newspapers, designing and implementing new methods in data science and artificial intelligence, and analysing these materials at scale.
Taking a broader perspective on Library collections, we have been exploring opportunities with non-Western collections too. Library staff have been engaging closely with the exploration of OCR and Handwritten Text Recognition (HTR) systems for English, Bangla and Arabic. Digital Curators Tom Derrick, Nora McGregor and Adi Keinan-Schoonbaert have teamed up with PRImA Research Lab and the Alan Turing Institute to ran four competitions in 2017-2019, inviting providers of text recognition methods to try them out on our historical material. We have been working with Transkribus as well – for example, Alex Hailey, Curator for Modern Archives and Manuscripts, used the software to automatically transcribe 19th century botanical records from the India Office Records. An ongoing work led by Tom Derrick is to OCR our digitised collection of Bengali printed texts, digitised as part of the Two Centuries of Indian Print project.
Regions, text lines and illustrations demarcated as ground truth, as shown in Transkribus (Shelfmark: Or 3366). Digitised and available on Qatar Digital Library.
Another screenshot from Transkribus, showing automatically transcribed Bengali printed text (Shelfmark: VT 1914 d). Digitised as part of the Two Centuries of Indian Print project.
The Chevening Fellow will contribute to our efforts to identify OCR/HTR systems that can tackle digitised historical collections. They will explore the current landscape of Chinese handwritten text recognition, look into methods, challenges, tools and software, use them to test our material, and demonstrate digital research opportunities arising from the availability of these texts in machine-readable format.
This fellowship programme will start in September 2022 for a 12-month period of project-based activity at the British Library. The successful candidate will receive support and supervision from Library staff, and will benefit from professional development opportunities, networking and stakeholder engagement, gaining access to a range of organisational training and development opportunities (such as the Digital Scholarship Training Programme), as well as staff-level access to unique British Library collections and research resources.