Making IIIF Official at the Internet Archive | Internet Archive Blogs

“After eight years hosting an experimental IIIF service for public benefit, the Internet Archive is moving forward with important steps to make its International Image Interoperability Framework (IIIF) service official. Each year, the Internet Archive receives feedback from friends and partners asking about our long-term plans for supporting IIIF. In response, the Internet Archive is announcing an official IIIF service which aims to increase the resourcing and reliability of the Internet Archive’s IIIF service, upgrade the service to utilize the latest version 3.0 of the IIIF specification, and graduate the service from the iiif.archivelab.org domain to iiif.archive.org. The upgrade also expands the Internet Archive’s IIIF support beyond images to also include audio, movies, and collections — enabling deep zoom on high-resolution images, comparative item analysis, portability across media players, annotation support, and more….”

AI in medical imaging grand challenges: translation from competition to research benefit and patient care

Abstract:  Artificial intelligence (AI), in one form or another, has been a part of medical imaging for decades. The recent evolution of AI into approaches such as deep learning has dramatically accelerated the application of AI across a wide range of radiologic settings. Despite the promises of AI, developers and users of AI technology must be fully aware of its potential biases and pitfalls, and this knowledge must be incorporated throughout the AI system development pipeline that involves training, validation, and testing. Grand challenges offer an opportunity to advance the development of AI methods for targeted applications and provide a mechanism for both directing and facilitating the development of AI systems. In the process, a grand challenge centralizes (with the challenge organizers) the burden of providing a valid benchmark test set to assess performance and generalizability of participants’ models and the collection and curation of image metadata, clinical/demographic information, and the required reference standard. The most relevant grand challenges are those designed to maximize the open-science nature of the competition, with code and trained models deposited for future public access. The ultimate goal of AI grand challenges is to foster the translation of AI systems from competition to research benefit and patient care. Rather than reference the many medical imaging grand challenges that have been organized by groups such as MICCAI, RSNA, AAPM, and grand-challenge.org, this review assesses of the role of grand challenges in promoting AI technologies for research advancement and for eventual clinical implementation, including their promises and limitations.

Pictures at an exhibition: How to share your imaging data – Hartley – Journal of Microscopy – Wiley Online Library

Abstract:  Open access to data underpinning published results is a key pillar of scientific reproducibility. Making data available at scale also provides opportunities for data reuse, encouraging the development of new analysis approaches. In this poster article, accompanying a recorded talk, we will explain the benefits of publicly archiving your image data alongside your published manuscripts, as well as highlight what resources are available to do this. This will include the BioImage Archive, EMBL-EBI’s new resource for biological image data, https://www.ebi.ac.uk/bioimage-archive/. We will look at how image data submission works, how to prepare in advance for archiving your data, and upcoming developments.

 

The Beaverbrook Art Gallery launches its online digital collection of nearly 5000 works of art

“The entire Beaverbrook Art Gallery permanent collection of works is now viewable online on the gallery’s website for members of the public to study and enjoy, and this is joined with new animated videos and activities for children.

Beginning as a COVID-19 project, the curatorial team at the Beaverbrook undertook the major project of reviewing, documenting, and photographing the entire collection housed at the gallery. Ranging from paintings, to sketches, prints, photographs and sculpture, the entire art collection has been re-catalogued and photographed with a state-of-the-art digital process. The photographs, along with artwork and artist information, have now been uploaded to a browsable database that is available to the public.”

Small bowel capsule endoscopy examination and open access database with artificial intelligence: The SEE?artificial intelligence project – PMC

Abstract:  Objectives

Artificial intelligence (AI) may be practical for image classification of small bowel capsule endoscopy (CE). However, creating a functional AI model is challenging. We attempted to create a dataset and an object detection CE AI model to explore modeling problems to assist in reading small bowel CE.

Methods

We extracted 18,481 images from 523 small bowel CE procedures performed at Kyushu University Hospital from September 2014 to June 2021. We annotated 12,320 images with 23,033 disease lesions, combined them with 6161 normal images as the dataset, and examined the characteristics. Based on the dataset, we created an object detection AI model using YOLO v5 and we tested validation.

Results

We annotated the dataset with 12 types of annotations, and multiple annotation types were observed in the same image. We test validated our AI model with 1396 images, and sensitivity for all 12 types of annotations was about 91%, with 1375 true positives, 659 false positives, and 120 false negatives detected. The highest sensitivity for individual annotations was 97%, and the highest area under the receiver operating characteristic curve was 0.98, but the quality of detection varied depending on the specific annotation.

Conclusions

Object detection AI model in small bowel CE using YOLO v5 may provide effective and easy?to?understand reading assistance. In this SEE?AI project, we open our dataset, the weights of the AI model, and a demonstration to experience our AI. We look forward to further improving the AI model in the future.

Michelangelo’s David and cultural heritage images. The Italian pseudo-intellectual property and the end of public domain – Kluwer Copyright Blog

“On 20 April 2023, the Italian Civil Court of first instance of Florence (Tribunale civile di Firenze) issued a decision that held unlawful the reproduction by lenticular technique of the image of Michelangelo’s David and its juxtaposition with the image of a male model on the cover of GQ magazine. The reproduction was not authorized by the public museum Gallerie degli Uffizi in Florence where the masterpiece is kept….

These recent controversies over the commercial use of images of Michelangelo’s David and Leonardo’s Vitruvian Man emerge from the Italian courts’ decisions while – paradoxically – the reproduction of the image of Botticelli’s Venus for the Italian Ministry of Tourism’s “Open to meraviglia” advertising campaign triggered a controversy about the role of the (Italian) State as custodian of (humanity’s) cultural heritage. In other words, the use of a modified version of The Birth of Venus by Botticelli in the advertising campaign demonstrates that the Italian State, on the one hand purports to decide when the use of cultural heritage is compatible with the “cultural heritage’s scope”, while on the other hand finds it natural to use a controversial modification of a masterpiece like The Birth of Venus to promote tourism….

At the same time, the Italian Ministry of Culture has published new “Guidelines for the determination of the minimum amounts of fees and charges for the concession of use of property handed over to state institutes and places of culture of the Ministry of Culture (Ministerial Decree of April 11, 2023, No. 161)”. These new Guidelines have also triggered a heated debate: some learned societies and scientific associations have raised concerns about the application of the Guidelines to academic publishing. For example, according to the Guidelines, a university press has to pay the Public Sector (Ministry of Culture or public museum) for the reproduction, in a book, of images of public cultural property. As in the Tribunale di Venezia and Tribunale di Firenze’s decisions, the idea is to transform the State into a commercial actor competing with other companies in the market of the commercial reproduction of cultural heritage images….

This conceptual confusion hides the real interest at stake: the creation of a new form of pseudo-intellectual property (in this case, a pseudo-copyright) that would attribute to the Italian State the power to exclusively control the commercial use of cultural heritage images….”

WorldFAIR Project (D13.2) Cultural Heritage Image Sharing Recommendations Report | Zenodo

Abstract:  Deliverable 13.2 for the WorldFAIR Project’s Cultural Heritage Work Package (WP13). Although the cultural heritage sector has only recently begun to think of traditional gallery, library, archival and museum (‘GLAM’) collections as data, long established practices guiding the management and sharing of information resources has aligned the domain well with the FAIR principles for research data, evidenced in complementary workflows and standards that support discovery, access, reuse, and persistence. As explored in the previous report by Work Package 13 for the WorldFAIR Project, D13.1 Practices and policies supporting cultural heritage image sharing platforms, memory institutions are in an important position to influence cross-domain data sharing practices and raise critical questions about why and how those practices are implemented.

Deliverable 13.2 aims to build on our understanding of what it means to support FAIR in the sharing of image data derived from GLAM collections. This report looks at previous efforts by the sector towards FAIR alignment and presents 5 recommendations designed to be implemented and tested at the DRI that are also broadly applicable to the work of the GLAMs. The recommendations are ultimately a roadmap for the Digital Repository of Ireland (DRI) to follow in improving repository services, as well as a call for continued dialogue around ‘what is FAIR?’ within the cultural heritage research data landscape.

WorldFAIR Project (D13.2) Cultural Heritage Image Sharing Recommendations Report –

“Deliverable 13.2 for the WorldFAIR Project’s Cultural Heritage Work Package (WP13). Although the cultural heritage sector has only recently begun to think of traditional gallery, library, archival and museum (‘GLAM’) collections as data, long established practices guiding the management and sharing of information resources has aligned the domain well with the FAIR principles for research data, evidenced in complementary workflows and standards that support discovery, access, reuse, and persistence. As explored in the previous report by Work Package 13 for the WorldFAIR Project, D13.1 Practices and policies supporting cultural heritage image sharing platforms, memory institutions are in an important position to influence cross-domain data sharing practices and raise critical questions about why and how those practices are implemented.

Deliverable 13.2 aims to build on our understanding of what it means to support FAIR in the sharing of image data derived from GLAM collections. This report looks at previous efforts by the sector towards FAIR alignment and presents 5 recommendations designed to be implemented and tested at the DRI that are also broadly applicable to the work of the GLAMs. The recommendations are ultimately a roadmap for the Digital Repository of Ireland (DRI) to follow in improving repository services, as well as a call for continued dialogue around ‘what is FAIR?’ within the cultural heritage research data landscape.

The report is available on Zenodo.”

The Smithsonian Puts 4.5 Million High-Res Images Online and Into the Public Domain, Making Them Free to Use | Open Culture

“More items are being added to Smithsonian Open Access all the time, each with its own story to tell — and all accessible not just to Americans, but internet users the world over. In that sense it feels a bit like the Chicago World’s Fair of 1893, better known as the World’s Columbian Exposition, with its mission of revealing America’s scientific, technological, and artistic genius to the whole of human civilization. You can see a great many photos and other artifacts of this landmark event at Smithsonian Open Access, or, if you prefer, you can click the “just browsing” link and behold all the historical, cultural, and formal variety available in the Smithsonian’s digital collections, where the spirit of Columbia lives on.”

One more way AI can help us harness one of the most underutilized datasets in the world

“Satellite data may be one of the most underutilized datasets in the world. 

At Planet alone, we have six years of documented history — which means we have over 2,000 images on average for every point on earth’s landmass. This dataset at high resolution never existed before Planet came along and created it. 

What this dataset means is that you can see a lot of change…if you know where to look. 

We’re pulling down 30TB of data daily (nearly 4 million images!) off of ~200 satellites, and it would be impossible for humans to look at, consume and derive insights from all of that manually. Some days, it can literally feel like the world’s largest hidden picture puzzle. 

That’s why we crucially need artificial intelligence (AI) and machine learning (ML) to detect and inform us about what’s in this imagery. Given the size of our archive, it’s a veritable playground for Planeteers and our partners to train AI and ML models and to build algorithms that can extract objects and patterns – to find newly-built roads, identify collapsed or raised buildings, monitor change in forests throughout time, or track surveillance balloons over oceans – all possible today….”

Call for Participation in a new Working Group on Image Sharing Practices in Cultural Heritage – CODATA, The Committee on Data for Science and Technology

“Are you a professional working in the Cultural Heritage sector, interested in exploring how your institution or research area could improve the findability, accessibility, interoperability and reusability of the digital images you collect and create? The DRI is opening a call for participation for a short-term Working Group, which will meet over a 5 month period from January to May 2023, to review and refine a set of recommendations for aligning practices across the Cultural Heritage sector with the FAIR principles for data sharing. The DRI is particularly keen to add members to the Working Group from currently underrepresented regions: South America, Australasia and Africa, though any interested parties should get in touch.

These recommendations are being produced as part of the WorldFAIR Project, a major global collaboration between partners from thirteen countries across Africa, Australasia, Europe, and North and South America.  WorldFAIR will advance the implementation of the FAIR data principles, in particular those for Interoperability, by developing a cross-domain interoperability framework and recommendations for FAIR assessment in a set of eleven disciplines or cross-disciplinary research areas. The DRI is leading the WorldFAIR case study for Cultural Heritage….”

WorldFAIR Project (D13.1) Cultural Heritage Mapping Report: Practices and policies supporting Cultural Heritage image sharing platforms | Zenodo

Abstract:  Deliverable 13.1 for the WorldFAIR Project’s Cultural Heritage Work Package (WP13) outlines current practices guiding online digital image sharing by institutions charged with providing care and access to cultural memory, in order to identify how these practices may be adapted to promote and support the FAIR Principles for data sharing.

The report has been compiled by the Digital Repository of Ireland as a key information resource for developing the recommendations forthcoming in Deliverable 13.2. The DRI is Ireland’s national repository for the arts, humanities and social sciences. A Working Group of cultural heritage professionals has been invited to contribute feedback.

There are well-established standards and traditions driving the various approaches to image sharing in the sector, both local and global, which influence everything from the creation of digital image files, their intellectual organisation and level of description, to statements of rights governing use. Additionally, there are technological supports and infrastructures that have emerged to facilitate these practices which have significant investment and robust community support. These practices and technologies serve the existing communities of users well, primarily the needs of government, business and higher education, as well as the broader general public. Recommendations for adapting established collections delivery mechanisms to facilitate the use of cultural heritage images as research data would ideally not supersede or duplicate processes that also serve these other communities of users, and any solutions proposed in the context of the WorldFAIR Project must be made in respect of these wider contexts for image sharing.

New from WorldFAIR! Cultural Heritage Mapping Report: ‘Practices and policies supporting Cultural Heritage image sharing platforms’ – out now – CODATA, The Committee on Data for Science and Technology

“New WorldFAIR Project Deliverable 13.1 ‘Cultural Heritage Mapping Report: Practices and Policies supporting Cultural Heritage image sharing platforms’ outlines current practices guiding online digital image sharing by institutions charged with providing care and access to cultural memory, in order to identify how these practices may be adapted to promote and support the FAIR principles for data sharing.

This report looks closely at the policies and best practices endorsed by a range of professional bodies and institutions representative of Galleries, Libraries, Archives and Museums (the ‘GLAMs’) which facilitate the acquisition and delivery, discovery, description, digitisation standards and preservation of digital image collections. The second half of the report further highlights the technical mechanisms for aggregating and exchanging images that have already produced a high degree of image interoperability in the sector with a survey of six national and international image sharing platforms: DigitalNZ, Digital Public Library of America (DPLA), Europeana, Wikimedia Commons, Internet Archive and Flickr….”

Open Buildings

“Building footprints are useful for a range of important applications, from population estimation, urban planning and humanitarian response, to environmental and climate science. This large-scale open dataset contains the outlines of buildings derived from high-resolution satellite imagery in order to support these types of uses. The project is based in Ghana, with an initial focus on the continent of Africa and new updates on South Asia and South-East Asia….”