Initial scripts assess OCR quality and identify texts within a JSON corpus, suggesting improvements.
Yesterday, I wrote of a challenge that I faced in working out which texts in a corpus have decent OCR and, then, which texts they actually are. This morning, I put together a small script that has a first go at this. I enclose this below for anybody who is interested.
No takes yet. Share an insight, caveat, or question.
Martin Paul Eve (2016) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: