Interactive System for Reducing Error Propagation in Multi-Stage Ancient Egyptian Text Analysis

Interactive System for Reducing Error Propagation in Multi-Stage Ancient Egyptian Text Analysis

Maksim Golyadkin, Innokentiy Humonen, Ilya Makarov

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence
Demo Track. Pages 8397-8400. https://doi.org/10.24963/ijcai.2026/965

We introduce a web tool that puts the full image-to-text pipeline for Ancient Egyptian hieroglyphs inside a single annotation workspace. Instead of only producing a final transcription, our system exposes editable intermediate results so users can validate and correct the pipeline step by step. User edits are stored as image-aligned annotations, which supports both text analysis and dataset creation. Quantitative results indicate improved efficiency and output quality relative to a manual baseline. A demonstration video is available at Google Drive.
Keywords:
AI: Computer Vision
AI: Natural Language Processing
AI: Multidisciplinary Topics and Applications