Text/character recognition in Adobe
Is anyone familiar with building queries to run text/character recognition in Adobe pdf documents? Does it require software outside of Adobe?
For context, I need to look through medical records for data like lab results and such based on a medical case definition. If there is a way to do this without manually scrolling through 100 pages, please let me know.
Thank you!
Thank you!
https://cran.r-project.org/web/packages/tesseract/vignettes/intro.html
THanks
Thank you for the link to the OCR tutorial; I was able to read the pdf file into R. Is there a way to then do a search (command F or similar) to look for information within the pdf/png in R. For example, if I read in one page of this made-up medical record
| AST | 458 | Ug/l
| AKP | 394 | Ug/l
| TBil | 7 | Ug/l
| Hep b | Negative | 4/5/21
| Hep c | Positive | 4/5/21
| Igg | negative | 4/5/21
where I want to search for any mentions of "AST" and be directed to "| AST | 458 | Ug/l"
Any pointers greatly appreciated.