Phyto-Vision: A Reproducible Workflow for the Computational Excavation of Global Botanical Iconography

Poster presented at DARIAH Annual Event, 2026

The history of botany is fundamentally a history of its visual culture, shaped by a contested global encounter between diverse indigenous traditions and the classificatory systems of European empires. These imperial practices frequently marginalized or subsumed sophisticated epistemic traditions, such as those found in the Chinese Bencao systems, Mesoamerican codices, and Ayurvedic herbals, which prioritized different modes of relating to the natural world. We introduce Phyto-Vision, a workflow that transforms digitised botanical pages into a structured visual dataset for large-scale analysis of botanical illustrations.

By extracting and grouping illustrations at scale, the workflow reveals patterns of visual standardisation that underpinned imperial botanical infrastructures, while also allowing comparison with parallel traditions such as the Bencao, in which image and inscription were integrated for diagnostic precision. 

The computational isolation of illustrations parallels earlier practices of specimen isolation and visual collation, but extends them across heterogeneous global archives. The system treats extracted illustrations as structured visual objects that can be compared longitudinally and cross-culturally. In this sense, Phyto-Vision translates historical visual logics into machine-readable form, opening new possibilities for analysing how classificatory systems were stabilised, circulated, and transformed.

Project website: https://phytovision.vercel.app/home