A Jibo-Labeled Classical Hiragana Image Dataset for Computational Paleography: Bootstrapped Variant Annotation at Scale
Michael R. Zeng, Herman Chau, Paul S. Atkins · 2026
Extended abstract accepted for the International Workshop on Computational Paleography (IWCP 2026, 4th edition), 4 September 2026, Vienna, Austria, a workshop of ICDAR 2026, presented as a poster with a flash presentation. Published here for open access and citation. Workshop Organisers: Isabelle Marthot-Santaniello, Universität Basel, Basel, Switzerland Hussein Mohammed, Universität Hamburg, Hamburg, Germany Workshop page: IWCP 2026 : CSMC : University of Hamburg Computational paleography benefits from methods that preserve variation in sign forms, not only readings. In premodern Japanese materials, a central issue is the polygraphy of the phonetic syllabary called hiragana. Hiragana are Chinese characters carrying semantic and phonetic values that are written in a highly cursivized style to signal that they are to be read solely for their phonetic value.