Breaking the Code on Broken Tablets: The Learning Challenge for Annotated Cuneiform Script in Normalized 2D and 3D Datasets

Mara, Hubert; Bogacz, Bartosz

doi:10.1109/icdar.2019.00032

Cited by 8 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset is created by using transliterations from He-iCuBeDa [6] and searching for the "@seal" tag. Tablets with no transliteration are discarded.…”

Section: Classifying Seal Presencementioning

confidence: 99%

“…The processing, therefore, needs to be in 3D to include all information [5]. As a result, datasets have been created of 3D scanned tablets [2,6,7]. Deep learning, therefore, needs to be performed in 3D to process the tablets thoroughly.…”

Section: Introductionmentioning

confidence: 99%

“…A successful network for processing 3D scanned tablets is introduced by Bogacz et al [5]. Using the Heidelberg Cuneiform Benchmark Dataset (HeiCuBeDa) [6] a dataset for classification of tablet time period is introduced. To process this data a novel network was created.…”

Section: Introductionmentioning

confidence: 99%

“…Best viewed digitally. Left Side Text Presence[6] and searching for the "@left" tag. The resulting training set is heavily unbalanced as 48 tablets have left side signs, and 276 do not.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Deep learning classification of large-scale point clouds: A case study on cuneiform tablets

Hagelskjær¹

2022

Preprint

View full text Add to dashboard Cite

This paper introduces a novel network architecture for the classification of large-scale point clouds. The network is used to classify metadata from cuneiform tablets. As more than half a million tablets remain unprocessed, this can help create an overview of the tablets. The network is tested on a comparison dataset and obtains state-of-the-art performance. We also introduce new metadata classification tasks on which the network shows promising results. Finally, we introduce the novel Maximum Attention visualization, demonstrating that the trained network focuses on the intended features.

show abstract

“…The dataset is created by using transliterations from He-iCuBeDa [6] and searching for the "@seal" tag. Tablets with no transliteration are discarded.…”

Section: Classifying Seal Presencementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Best viewed digitally. Left Side Text Presence[6] and searching for the "@left" tag. The resulting training set is heavily unbalanced as 48 tablets have left side signs, and 276 do not.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Deep learning classification of large-scale point clouds: A case study on cuneiform tablets

Hagelskjær¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Even though information about the 3D acquisition process is not provided and, therefore, to be considered lost, the workflow presented in this publication can be followed starting in stage 3. We could produce metadata using the previously described GigaMesh software [49], which showed that the overall quality is suitable for given tasks in assyriology as well as the related machine learning experiments. However, half of the tablets have only half of the spatial resolution possible.…”

Section: Application Case 2: Quality Of Cuneiform Tablet 3d Scansmentioning

confidence: 99%

Metadata schema and ontology for capturing and processing of 3D cultural heritage objects

et al. 2021

Self Cite

View full text Add to dashboard Cite

Motivated by the increased use of 3D acquisition of objects by cultural heritage institutions, we were investigating ontologies and metadata schemes for the acquisition process to provide details about the 3D capturing, which can be combined with preexisting ontologies describing an object. Therefore we divided the 3D capturing workflow into common steps starting with the object being placed in front of a 3D scanner to preparation and publication of the 3D datasets and/or derived images. While the proposed ontology is well defined on a coarse level of detail for very different techniques, e.g. Stucture from Motion and LiDAR we elaborated the metadata scheme in very fine detail for 3D scanners available at our institutions. This includes practical experiments with measurement data from past and current projects including datasets published at Zenodo as guiding examples and the source code for their computation. Additionally, the free and Open Source GigaMesh Software Framework’s analysis and processing methods have been extended to provide metadata about the 3D processing steps like mesh cleaning as well as 2D image generation. Finally, we discuss the current limitations and give an outlook about future extensions.

show abstract

PaleoCodage—Enhancing machine-readable cuneiform descriptions using a machine-readable paleographic encoding

Homburg

2021

Digital Scholarship in the Humanities

View full text Add to dashboard Cite

This publication introduces PaleoCodage, a new machine-readable way to capture cuneiform paleographic shapes. Many different systems of listing and describing cuneiform signs exist, but none of the systems can be used to describe the shape, i.e. paleographic features of cuneiform signs. PaleoCodage aims to fill this missing link of description which can benefit the Semantic Web community of linked open data dictionaries, the assyrologist community in documenting signs and their variants and the cuneiform image recognition community in providing a gold standard encoding to match against. The publication evaluates the encoding on more than 200 Unicode cuneiform signs, describes already available application cases, a linked data vocabulary for paleography and concludes by describing future work on further validating PaleoCodage and applying the paleographic vocabulary to more languages.

show abstract

Breaking the Code on Broken Tablets: The Learning Challenge for Annotated Cuneiform Script in Normalized 2D and 3D Datasets

Cited by 8 publications

References 7 publications

Deep learning classification of large-scale point clouds: A case study on cuneiform tablets

Deep learning classification of large-scale point clouds: A case study on cuneiform tablets

Metadata schema and ontology for capturing and processing of 3D cultural heritage objects

PaleoCodage—Enhancing machine-readable cuneiform descriptions using a machine-readable paleographic encoding

Contact Info

Product

Resources

About