Character retrieval of vectorized cuneiform script

Bogacz, Bartosz; Gertz, Michael; Mara, Hubert

doi:10.1109/icdar.2015.7333777

Cited by 14 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This includes methods that process vectorized cuneiform, with the intermediate step of skeletonization. They use autograph-like 2D vector drawings generated from 3D-scanned cuneiform meshes [26] or raster images [27], to decompose vectorized cuneiform signs into wedge features, including the deinition of sign-level similarity measures [3] or decompose spline drawings into single wedges and cuneiform signs based on part-structured models [5], and convert the vector drawings into graph representations of cuneiform signs [4]. However, neither of these methods can provide a solution for the cuneiform classiication problem on photographic reproductions.…”

Section: Computer Aided Cuneiform Analysismentioning

confidence: 99%

Illumination-based Augmentation for Cuneiform Deep Neural Sign Classification

Rest

Fisseler

Weichert

et al. 2022

J. Comput. Cult. Herit.

View full text Add to dashboard Cite

Automated content-based search for arbitrary cuneiform signs in photographic reproductions is a challenging task in the analysis of ancient documents, a central component of which is a reliable cuneiform sign classification. We present an illumination-based approach to generate synthetic training data for cuneiform sign classification via deep neural networks to overcome common issues with the transferability of machine learning training results. Starting from an analysis of the negative impact of illumination variations in the processed cuneiform data, we employ an illumination augmentation to 2D training data generated from annotated 3D datasets. We demonstrate that our method is able to overcome the high visual variance of most digitized 2D cuneiform reproductions and achieve an illumination invariant generalization. The effectiveness of our approach is evaluated by its successful application to several subsets of a cuneiform script dataset with an originally poor transferability of mutual training results. Furthermore, we show that a sufficient sampling of the illumination space mostly removes the necessity to match the training data to specific target illumination conditions. The practical applicability of our approach is validated by applying it to a larger dataset, raising the overall classification accuracy by 4 percentage points to 90%, resulting in a classification error reduction of 28.5% when compared to results without the proposed data augmentation.

show abstract

Section: Computer Aided Cuneiform Analysismentioning

confidence: 99%

Illumination-based Augmentation for Cuneiform Deep Neural Sign Classification

Rest

Fisseler

Weichert

et al. 2022

J. Comput. Cult. Herit.

View full text Add to dashboard Cite

show abstract

“…Automatic optical character recognition cannot be used to reliably identify cuneiform signs, neither in their two-dimensional (2D) representations (hand copies) nor in three-dimensional (3D) scans of actual clay tablets (8)(9)(10)(11)(12). Various visual recognition algorithms are being applied to cuneiform, but the results are yet in their infancy (13)(14)(15)(16). Therefore, one has to rely on a limited corpus of manually transliterated texts.…”

Section: Significancementioning

confidence: 99%

Restoration of fragmentary Babylonian texts using recurrent neural networks

Fetaya

Lifshitz

Aaron

et al. 2020

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

The main sources of information regarding ancient Mesopotamian history and culture are clay cuneiform tablets. Many of these tablets are damaged, leading to missing information. Currently, the missing text is manually reconstructed by experts. We investigate the possibility of assisting scholars, by modeling the language using recurrent neural networks and automatically completing the breaks in ancient Akkadian texts from Achaemenid period Babylonia.

show abstract

“…This wedge model includes wedge component based features, like edges and depth points and a heuristic classification of wedge types. Based on generating 2D contour line vector representations of wedges, Bogacz et al (2015a,b) proposed two approaches to classify cuneiform signs: One of them is based on graph representations, which are compared by graph kernels (Bogacz et al, 2015b), and the other computes the optimal assignment between vector representations (Bogacz et al, 2015a). Rothacker et al (2015) proposed a Bag-of-Features and HMM based approach for automatically retrieving cuneiform structures on image representations from 3D scans.…”

Section: Related Workmentioning

confidence: 99%

Recognizing Cuneiform Signs Using Graph Based Methods

Kriege,

Fey,

Fisseler

et al. 2018

Preprint

View full text Add to dashboard Cite

The cuneiform script constitutes one of the earliest systems of writing and is realized by wedge-shaped marks on clay tablets. A tremendous number of cuneiform tablets have already been discovered and are incrementally digitalized and made available to automated processing. As reading cuneiform script is still a manual task, we address the real-world application of recognizing cuneiform signs by two graph based methods with complementary runtime characteristics. We present a graph model for cuneiform signs together with a tailored distance measure based on the concept of the graph edit distance. We propose efficient heuristics for its computation and demonstrate its effectiveness in classification tasks experimentally. To this end, the distance measure is used to implement a nearest neighbor classifier leading to a high computational cost for the prediction phase with increasing training set size. In order to overcome this issue, we propose to use CNNs adapted to graphs as an alternative approach shifting the computational cost to the training phase. We demonstrate the practicability of both approaches in an experimental comparison regarding runtime and prediction accuracy. Although currently available annotated real-world data is still limited, we obtain a high accuracy using CNNs, in particular, when the training set is enriched by augmented examples.

show abstract

Character retrieval of vectorized cuneiform script

Cited by 14 publications

References 19 publications

Illumination-based Augmentation for Cuneiform Deep Neural Sign Classification

Illumination-based Augmentation for Cuneiform Deep Neural Sign Classification

Restoration of fragmentary Babylonian texts using recurrent neural networks

Recognizing Cuneiform Signs Using Graph Based Methods

Contact Info

Product

Resources

About