Tag: Open Source
-
A Python Tool for Restoring Spatial Search to VLM Transcriptions
When Large Language Models (LLMs) began cleaning up optical character recognition (OCR) output, or when Vision Language Models (VLMs) bypassed OCR and transcribed page images directly, something improved for researchers but something else broke. The text itself became dramatically cleaner: proper reading order, accurate spelling, no hyphens fracturing words across line breaks (example: “Pythagoras” rendered…
-
From Field Notes to Metadata: Exploring OCR and Chandra for MLP Workflows
By Chloë Farr and Kate Fryer The Mountain Legacy Project (MLP) is a group of passionate researchers who work with historic and modern mountain photographs to document landscape change over time. Repeat photography is central to this work. By returning to the same locations where historic survey photographs were taken MLP researchers can create visual…
-
Making Scanned Data Tables Usable with AI
Back in October 2025, Nick Rochlin, our Science and Data Librarian, sent me a folder of scans of data tables typed in the 1980s. A student had contacted Nick asking if there was an automated way to convert their paper data tables into a format that would allow for computational analysis. There didn’t seem to be…