Do OCR only on a specific place in the document

How are you?
Is there a way for me to do the OCR on a specific place in the document and to extract the data only from the specific coordinate I’m selecting?

I was to set the exact coordinates in the file - Top: X, Bottom: Y , Left: Z and Right: W all in cm or any other way.

How can it be done?
Thanks! Ram

Hi, the OCR API itself does not have this feature yet. The recommended workaround is to crop the image before sending it to the OCR API.

Or is this a PDF? If so, how many pages?

1 Like

Thanks for the reply.

Yes - This is a PDF.
I can pass one page per call.

I can try and convert it to an image and to crop it - but if there will be a way to do it via the OCR API directly to the PDF it will be best.

Any way - Thanks!