Problem
Research questions and friction points this paper is trying to address.
cuneiform
sign detection
OCR
Electronic Babylonian Library
large-scale dataset
Automated sign detection across the Electronic Babylonian Library: A large-scale dataset and end-to-end cuneiform OCR pipeline
🤖 AI Summary
This study addresses the inefficiency and limited scalability of manual cuneiform tablet interpretation by proposing the first end-to-end optical character recognition (OCR) framework for cuneiform script. The approach integrates deformable DETR for symbol detection, automatic tablet surface extraction, heuristic line grouping, and n-gram–based text similarity evaluation to align detected symbols with textual structure—without relying on prior linguistic knowledge. Applied to nearly 88,000 cuneiform tablets, the method successfully identifies approximately 2.9 million signs, achieving a 28–37% improvement in COCO detection metrics over previous work. This advancement significantly enhances the feasibility of large-scale automated processing and interpretable analysis of cuneiform corpora.
📝 Abstract
Learning to read cuneiform tablets is an extremely demanding task; consequently, of the roughly half million excavated tablets, only a small fraction has been analysed by Assyriologists. Computer vision offers a promising avenue for decipherment but requires large, densely annotated datasets. To address this limitation, the largest annotated cuneiform sign dataset to date is used, and a Deformable Detection Transformer (DETR)-based object detection model is evaluated under two class granularities of 173 and 106 classes. The proposed system integrates automatic tablet-side extraction, heuristic line grouping, and n-gram-based textual similarity evaluation to bridge visual sign detection and textual structure, and achieves consistent improvements of up to 28-37% over prior work on COCO-style detection metrics. At inference, the method is applied to 87,668 tablet fragments from the Electronic Babylonian Library (eBL) corpus, producing nearly 2.9 million sign detections. Although the approach operates without linguistic priors and remains sensitive to tablet damage and layout variability, it provides a scalable and interpretable foundation for corpus-wide cuneiform analysis and supports future integration with multimodal and linguistic modelling frameworks.
Innovation
Methods, ideas, or system contributions that make the work stand out.
cuneiform OCR
Deformable DETR
large-scale dataset
end-to-end pipeline
textual structure integration
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
