TextileNet: Towards Zero-shot Text-style Segmentation of Manuscripts
2026-07-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed TextileNet, a computer program trained only on fake data that can analyze the texture of handwriting in old documents. They tested it without extra training on real historical manuscripts to see if it could identify different handwriting styles and even guess writer gender. They also created a quiz to compare human and machine ability to tell apart handwriting styles, involving both experts and non-experts. Their results show that TextileNet works well for identifying handwriting but suggest caution when trying to determine gender from handwriting alone.
writer identificationpaleographyconvolutional neural networksynthetic training datazero-shot learningtexture embeddingshandwriting analysisgender identificationhistorical manuscriptsvisual quiz
Authors
Anguelos Nicolaou, Antonella Ambrosio, Desiree Di Donato, Georg Vogeler
Abstract
Automatic writer identification systems have progressed remarkably in recent years, yet their deployment in archival paleography remains limited by the scarcity of labeled training data, open scribe sets, and degraded image quality. We present TextileNet, a fully convolutional multi-task network trained exclusively on synthetic data to produce dense pixel-level texture embeddings, which we transfer zeroshot to historical manuscript analysis. As an original contribution to evaluation methodology, we designed a paleographic visual quiz of 80 pair and triplet questions and administered it to a range from lay participants to senior paleographers under strict anonymity, establishing to our knowledge for the first time a human baseline for script-style discrimination on late medieval text. We employ TextileNet embeddings to perform zero-shot retrieval on sub-word granularity for hand and gender identification. Our experimental results help in building the credibility of TextileNet in the paleographic domain, but more than that demonstrate in experimental terms that the question of gender in handwriting needs to be treated with caution.