Metraipolis › archive › dc_8ba7560f7ddf
Zero-Shot SAM2 Segmentation and Vision Transformer-Based Recognition of Elamite Cuneiform Symbols from Degraded Tablet Images — arXiv:2608.18544
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.18544
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T13:52:32.341Z
- SHA-256 of the archived text
cea6a2caf003c6519b372ac5705c7d98021773d68539ff6b12fd6558de78bd3c- Stable URL of this page
https://metraipolis.com/documento/dc_8ba7560f7ddf
How to cite
Zero-Shot SAM2 Segmentation and Vision Transformer-Based Recognition of Elamite Cuneiform Symbols from Degraded Tablet Images — arXiv:2608.18544 — arXiv (en), https://arxiv.org/abs/2608.18544 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8ba7560f7ddf (Metraipolis archive dc_8ba7560f7ddf, sha256 cea6a2caf003c6519b372ac5705c7d98021773d68539ff6b12fd6558de78bd3c)
BibTeX
@misc{dc8ba7560f7ddf,
title = {Zero-Shot SAM2 Segmentation and Vision Transformer-Based Recognition of Elamite Cuneiform Symbols from Degraded Tablet Images — arXiv:2608.18544},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.18544},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8ba7560f7ddf; sha256 cea6a2caf003c6519b372ac5705c7d98021773d68539ff6b12fd6558de78bd3c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18544. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Automated recognition of ancient cuneiform script poses a compound signal-degradation problem: the three-dimensional relief of clay tablets creates spatially varying illumination and cast shadows, surface erosion introduces structured noise that overlaps with genuine sign impressions, and severe class imbalance across 141 sign categories undermines classifier reliability. We introduce EpigraphNet, a segmentation-guided transformer pipeline evaluated on the Persepolis Fortification Archive. From 1,239 annotated tablet images, brightness-adaptive morphological preprocessing and zero-shot SAM2-Large segmentation generate clean binary symbol masks, which a fine-tuned Vision Transformer (ViT-B/16) with inverse-frequency class weighting then classifies. EpigraphNet reaches 86.41% top-1 accuracy on a 132-class benchmark, a 17.21 percentage-point gain over the strongest CNN baseline (ResNet-101, 69.20%) and 5.31-12.91% over four modern backbones (DeiT-B/16, Swin-B, ConvNeXt-B, EfficientNet-B4) under identical conditions. The full pipeline runs at approximately 18 ms per sign on an NVIDIA A100 GPU. A lower Spearman correlation between sign frequency and per-class performance indicates more balanced recognition across frequent and rare classes. Implementation is available at: this http URL Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.HC). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2608.18544 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T13:50:23.974Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).