Museen der Stadt Wien – Stadtarchäologie

Navigation Menu

Machine visions

Learning systems in cultural heritage research Call for Papers Jaap Evert Abrahamse (1) | Erik Schmitz (2) | Rowin van Lanen (1, 3)((1) Cultural Heritage Agency of the Netherlands | (2) Amsterdam City Archives | (3)  Wageningen University and Research) Keywords: pattern recognition, image recognition, HTR, big data analysis, machine learning, computer-aided research Call: In the 1980s, the Austrian computer scientist Hans Moravec formulated his famous paradox, stating that reasoning, which is typical for humans, requires relatively little computation, as opposed to mobility and perception. Since then, computer power has grown rapidly. At the moment it is the concept of perception that proves an interesting though challenging feature for cultural heritage researchers. Present-day computers can generate more data, they can see sharper than humans and they can look through more data in less time. We see the emergence of more and more self-learning systems using human-computer interaction for text and pattern recognition and comparison in large digitized datasets like (handwritten) texts from archives, architectural designs, archaeological drawings and reconstructions, images of buildings, digital elevation maps or georeferenced historic maps.In this session, we welcome researchers involved in the implementation of such or comparable techniques. Contributors are not limited to showing only their results, but are also encouraged to focus on work in progress and best practices. Furthermore, presenters are invited to reflect on the future development of these types of computer-aided research in heritage. In 2009 Moravec wrote that in the foreseeable future robot researchers will work alongside humans. Therefore, during the final discussion we would like to debate whether or not we expect computers to take the next step from recognition towards classification and interpretation. For instance, by connecting or linking information from datasets too large to humanly handle. These outcomes might fuel the more theoretical discussion: could computers be used not only to answer questions formulated in the past, but also help to define new questions and in doing so explore new territories? Submission (open April 15, 2020)Mind the...

Read More

Nuclear Techniques in cultural heritage artefacts investigations

Call for Papers Dinara ABBASOVA(Vienna, Austria) Keywords: Nuclear techniques; artefacts characterization; X-ray fluorescence spectrometry; Elemental analysis Call: Application of different methods of analysis in characterization of Cultural Heritage (CH) Artefacts in nowadays is widely used worldwide. Specificity of analyzing subject insists selection of methods of analysis. From one hand determination of the subject chemical composition is very important from another hand specificity of the subject make it difficult and impossible for analysis by classic methods. For investigation of Cultural Heritage Artefacts only non-invasive and non-destructive methods can be applied. From this point of view application of nuclear techniques are most suitable for this purpose. It has a potential for non-destructive and reliable investigation of CH artefacts. Thus, elemental analysis is extremely important in identification of unknown chemical structure of archaeological samples and taking into account all written above X-ray Fluorescence (XRF), Ion Beam Analysis (IBA): (Particle Induced Gamma-ray Emission (PIGE), Proton Induced X-ray Emission (PIXE)), Prompt gamma activation analysis (PGAA) , Neutron Activation Analysis (NAA), Rutherford backscattering (RBS) by use of appropriate detector systems, Scanning Electron Microscopy (SEM) in combination with energy (or wavelength) dispersive microanalysis has been extensively applied to obtain information on the elemental composition of Artefacts. Neutron activation analysis (NAA) has been recognized as the method of choice for archaeological provenance investigations since the 1970s. Energy dispersive X ray fluorescence (EDXRF) is a non-invasive technique using portable equipment convenient for analysis of items which cannot be moved from collections. With the same level of detection limits, SEM-EDX, providing imaging and elemental analysis of tiny details accurately selected on the surface of an object. Also, neutron tomography produces high-resolution three-dimensional images that are required to survey an object for attenuation features. These and many other’s instruments, its advantages and disadvantages, different archaeological samples characterization and diagnostics, dating and provenance tests will be discussed in this sectionI prefer to see application of different non invasive techniques such as described in abstract. ED-XRD, ED-XRF, XRF, PIXE, PIGE, NAA application for CH artefacts: porcelain, pottery, pigments, paintings, jewelry and etc.   REFERENCE: IAEA, Radiation Technology Series # 2, Submission (open April 15, 2020)Mind the...

Read More

Modelling the Unseen

Call for Papers Daniele VILLA | Lorenzo CECCON(Politecnico di Milano, Italy) Keywords: AI, HBIM, Remote Sensing, Diagnostics, Ontologies Call: AI shows great potential in helping formulate H-BIM model hypotheses of surveyed heritage sites. It can in fact link together, on the one hand, survey data from a specific site and, on the other hand, wide data-sets of other already analysed heritage sites:  raw survey data and corresponding validated reconstructions as shared in common repositories. Based on such data – structured according to ontologies that embed previous research results as wrapped into the H-BIM model – AI could “make sense” of the survey data at stake and help build the relevant H-BIM model embedding such semantic taxonomy. It would then “suggest” reconstruction hypotheses, both as regards the inner structure and materiality of the surveyed sites, such as the wall material composition layers, and the historical/philological development thereof, such as the construction phases and “styles” of the site. The session will highlight the current uses of AI for Cultural Heritage, including, but not limited to, point cloud segmentation, bimification, model-fitting techniques and fragment re-composition. It will invite scholars to devise a new paradigm in the use of AI to create historical “Digital-Twins”, to be progressively fit to the survey and historical findings over-time. The H-BIM model would then not just represent a final reconstruction result, rather help in the process of hypothesizing and testing reconstruction hypotheses, including the site diachronic development and decay history. Special attention shall be thus dedicated to the structuring of Open Data Repositories and of the sematic HBIM families contained therein, as a key “bridging” knowledge-base between survey data and H-BIM modelling, i.e. the taxonomic “glasses” through which AI would see the world. The aim is encouraging the research community to create a sound common process and knowledge build up to “fuel” and exploit AI tools. Submission (open April 15, 2020)Mind the...

Read More

AI methods for representation and processing of digital cultural heritage

Call for Paper Günther GÖRZ (1) | Christoph SCHLIEDER (2)((1) FAU Erlangen-Nürnberg | (2) Otto-Friedrich-Universität Bamberg, Germany) Keywords: knowledge representation, natural language processing, image analysis, reasoning, learning Call: The digital transition opens new perspectives for researchers interested in cultural processes. An increasing part of the material and immaterial heritage of Western culture is accessible via digital representations such as digital editions of manuscripts, multispectral images of paintings or 3D models of archaeological findings. Digital representations have the obvious advantage of permitting simultaneous remote access.Additional effort is needed to include more cultural creations in the digital transition. Beyond that, the sheer number of those creations already digitally accessible raises new challenges for humanities scholars. The task of analyzing and linking the many pieces of information becomes more important and difficult than ever.AI methods provide solutions to some of the challenges involved. The Semantic Web technology stack, for instance, permits knowledge-based algorithms to assist scholars in the task of linking large cultural data sets. Another issue is the vagueness and uncertainty omnipresent in the historic study of cultural processes. AI research has devised a number of methods able to deal with these phenomena. It is important, however, to realize that humanities scholars have specific requirements.The session gathers interested AI researchers and humanities scholars. We encourage submissions that report on work in progress or present a synthesis of emerging research trends. Topics of interest include, but are not limited to: Knowledge representation for scholarly digital editionsNatural language processing in corpus linguisticsImage classification and analysisOntological approaches to semantic heterogeneityKnowledge graphs in the humanitiesReasoning about and learning from uncertain or ambiguous evidence Submission (open April 15, 2020)Mind the...

Read More

Computational photography and AI for image based research

Advanced Archaeological Training Vera CHIQUET | Peter FORNARO(University of Basel, Digital Humanities Lab, Switzerland) Keywords: AI, objects, metadata, photography, research Description: Research using digital visual methods and artificial intelligence is an increasingly important field of archaeology and object sciences in general. We would like to carry out our course as advanced archaeological training at the CHNT25, that we are currently undertaking in collaboration with the Classical Studies Department of the University of Basel and the Antikenmuseum Basel.In this interdisciplinary project which is done by the Digital Humanities Lab of the University of Basel, the aim is to apply Computational Photography and machine learning methods to assets of cultural relevance. We combine traditional archaeological research work by focusing on a specific field, the Roman clay lamps. We will have recorded these with Reflexion Transformation Imaging (RTI) by the time the conference is held. We will then be generating metadata with the scientists and archaeologists to train the machine learning approach. We use the annotated images  for artificial intelligence image classification as reference data.Using the small collection of Roman clay lamps, we have the opportunity to work on the documentation of archaeological objects and to collect human-based datasets for the annotated images that can be used for AI image classification.By our hands-on training on working with photographic resources of archaeological heritage, we monitored how single photographs but also image groups are described. Based on these experiences, we discuss the potential of machine learning components for semi-automatic image annotation and clustering. We are interested in object-specific meta information but also on contextual metadata that describe the connection between objects and are the criteria for clustering. The combination of rich semantic metadata and machine learning means increased functionality and value of digital source material for archaeological...

Read More

Documenting, Digital Restoring and Recontextualizing. (Comparing experiences)

Call for Short Paper (Round Table) Cristiana BARANDONI | Paolo GIULIERINI(Museo Archeologico Nazionale di Napoli, Italy) Keywords: 3D models, photogrammetry, virtual reality, public archaeology, communication strategy Call: This Round Table will be an opportunity to take stock of the researches and experiences put in place by archaeological museums to recreate the context from which works of art come from.  Coming from excavations often conducted in the Nineteenth and early Twentieth centuries, most of the archaeological finds exhibited in museums have great difficulty relating to an increasingly demanding public, more and more expecting the use of virtual and augmented reality, as a preferred medium to meet the past. This RT wants to compare a series of (digital) experiences by which museums try to bring the public of non-professionals closer to the knowledge of the past but above all to the recognition of the contexts of origin. Usually the amount of scientific data acquired by researchers is of considerable importance: now we need to start a debate on how to use these data proficiently, in order to reconstruct the story of the finds and make it available for collective knowledge. It is now a consolidated practice that after analytical and archaeological studies, systematic photogrammetric campaigns transform objects into digital resources: 3D models obtained offer an unmissable opportunity to rewrite events and collecting history. It is not only focusing in terms of material and scholarly knowledge of the object in question, but also the story from the moment of discovery to the display in museum rooms, chronology that also includes all the restoration phases to which the same objects have been subjected.  What happens to items on display?  If museums work hardly with the goals of digitally documenting, restoring, and recontextualizing archaeological finds, are they also able to evaluate how much their commitment reaches the various audiences?Digital is a challenge museums can’t miss, not only to find new physical-technical indicators but even merely profitable and quantitative: 3D modelling, digital restoring and recontextualization can give museums a chance to open the Past to whoever in need, keeping firm standards of being both a physical place but also “systems of relationships”, subjects to constant...

Read More