Posted in OCR
I am not a programmer!! But I create specifications for them.
We are looking to add smart OCR to our ROR app. By smart, I mean that can read, pair, and export tabular data from a scanned/exported paper invoice (pdf, jpg, etc.). We don't have any experience with this.
The options are wide: dedicated engines with api's (white box), up to Amazon (Textract)/Google/Microsoft engines that we would need to do a little more work with (but have lower cost per document).
Any thoughts or suggestions?