Whenever I send an image like the attached one, I only get the words REV back but not the number 1 that's under it. More unique number shapes like 2, 3, 4, etc. are usually recognized but the number 1 is rarely recognized.

Single characters are having a very tough time being recognized, even in the most optimal conditions for OCR (shown in the attached PDF). Also attached is a text view of how the content gets OCR-ed.

I saw that this is a recognized problem in a few ideas from a couple of years ago, but I was wondering if any progress was made in fixing this known problem.

Functionally, this provides issues with OCR-ing tables that have a "Quantity" or any other amount less than 10.

Please consider add Traditional Chinese into support list of local container.

I am trying to upload the identity proof and trying to verify with the user input. Some characters are replaced with other characters. like 1 is replaced with 7 ... so the date of birth will change..

Right Now, OCR can't detect MRZ on documents like photo Id or passport. Get this information is a 'must' for many applications that need to verify legal documents

All I'm trying to recognize is single letters. Such as S, M, L, XL and so forth. Why is Microsoft's OCR unable to recognize these characters?