# EpiSAM: Character Segmentation in Challenging Stone Inscriptions

arXiv: https://arxiv.org/abs/2606.28859 · HTML: https://mlsanity.com/paper/2606.28859/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 54 references that are in the map.
- First posted on arXiv 27 Jun 2026.

## Builds on (most cited first, 26 of 26)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [Character Region Awareness for Text Detection](https://mlsanity.com/paper/1904.01941/) (2019)
- [EAST: An Efficient and Accurate Scene Text Detector](https://mlsanity.com/paper/1704.03155/) (2017)
- [TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes](https://mlsanity.com/paper/1807.01544/) (2018)
- [Convolutional Character Networks](https://mlsanity.com/paper/1910.07954/) (2019)
- [DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer](https://mlsanity.com/paper/2207.04491/) (2022)
- [DTrOCR: Decoder-only Transformer for Optical Character Recognition](https://mlsanity.com/paper/2308.15996/) (2023)
- [Multi-Oriented Text Detection with Fully Convolutional Networks](https://mlsanity.com/paper/1604.04018/) (2016)
- [Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation](https://mlsanity.com/paper/2401.17904/) (2024)
- [docExtractor: An off-the-shelf historical document element extraction](https://mlsanity.com/paper/2012.08191/) (2020)
- [Arbitrary Shape Text Detection via Segmentation with Probability Maps](https://mlsanity.com/paper/2208.12419/) (2022)
- [Scene Text Detection via Holistic, Multi-Channel Prediction](https://mlsanity.com/paper/1606.09002/) (2016)
- [CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks](https://mlsanity.com/paper/2006.06244/) (2020)
- [Ancient Script Image Recognition and Processing: A Review](https://mlsanity.com/paper/2506.19208/) (2025)
- [General Detection-based Text Line Recognition](https://mlsanity.com/paper/2409.17095/) (2024)
- [ICDAR 2025 Competition on FEw-Shot Text line segmentation of ancient handwritten documents (FEST)](https://mlsanity.com/paper/2509.12965/) (2025)
- [Clustering-based Feature Representation Learning for Oracle Bone Inscriptions Detection](https://mlsanity.com/paper/2508.18641/) (2025)
- [SegHist: A General Segmentation-based Framework for Chinese Historical Document Text Line Detection](https://mlsanity.com/paper/2406.15485/) (2024)
- [Review of Computational Epigraphy](https://mlsanity.com/paper/2406.06570/) (2024)
- [Optical Character Recognition using Convolutional Neural Networks for Ashokan Brahmi Inscriptions](https://mlsanity.com/paper/2501.01981/) (2024)
- [Few-Shot Connectivity-Aware Text Line Segmentation in Historical Documents](https://mlsanity.com/paper/2508.19162/) (2025)
- [Unveiling Text in Challenging Stone Inscriptions: A Character-Context-Aware Patching Strategy for Binarization](https://mlsanity.com/paper/2601.03609/) (2026)

## Built on by (most cited first, 1 of 1)

- [Impact of Iterative Fine-Tuning on Transcription Accuracy in Complex Historical Sanskrit Manuscripts](https://mlsanity.com/paper/2608.18696/) (2026)

## Abstract (arXiv)

Stone inscriptions are invaluable sources of historical and linguistic knowledge, yet their automated analysis remains a major challenge due to surface irregularities, erosion, and low visual contrast. Conventional document and handwriting analysis techniques fail to perform well in these scenarios. In this work, we propose character detection as a core strategy for robust inscription analysis. We introduce EpiSAM, a prompt-guided transformer framework for character segmentation in stone inscriptions. Rather than treating characters in isolation, EpiSAM employs a novel neighbor-aware strategy, explicitly predicting adjacent characters alongside the target. These contextual cues resolve boundary ambiguities, improving mask generation and enabling more accurate character segmentation. Furthermore, we expand an existing stone inscription dataset by adding dense polygonal annotations for characters, thereby enabling comprehensive research on Southeast Asian epigraphy. Experimental results show that EpiSAM achieves consistent improvements over existing baselines, while also exhibiting strong zero-shot generalization in challenging epigraphic scenarios.