daiR: an R package for OCR with Google Document AI
Thomas Hegghammer · The Journal of Open Source Software · 2021
Statement of needOptical character recognition (OCR) promises to open up centuries worth of text to computational analysis.But OCR software has long been sensitive to visual noise and weak on non-Western languages.In April 2021, Google launched Document AI (DAI), a server-based processor offering high-accuracy OCR for over sixty languages (Vanguri, 2021).The daiR (Hegghammer, 2021b) package provides an R interface to the Document AI API along with additional tools for output parsing and visualization.