[New Plugin] - Free OCR - Extract text from your PDF's, JPG's or PNG's

Adding as well this one which may be useful

2 Likes

I know this post is quite old but I really must know how to store the extracted text in your database as a list. If anyone could help, thank you so much

What plugin are you using ?

im using free OCR plugin

Apologies, I could have helped you with the other plugin I recommended, I do not know this one.

Hi Guys, bumping this one!

I’m using Google Vision OCR. Setup is done. Working as I believe it should, it’s just that it doesn’t seem that is good enough, so maybe missing something.
My problem is to read this document here (or similar documents) and extract the info into fields.

However, the response of the OCR is a list of texts that don’t mean much. I still need to read it, with my human eyes, to make sense of where the information is. Here is a glimpse of the output list of texts:

For example, the actual invoice number is not in the same text (or line) of the label “Invoice Number”. They are not even in adjacent lines. So there’s no way to make sense of what is the invoice number. I tried to get the line indexes of the information I’m interested and tried to matched with another document that is almost identical in form and the lines were not exactly the same, so bottom line reading it with the OCR is useless.

Is anything that I’m missing here? Any thoughts?

Bumping this one? Anyone to help?

Hi @hetnon.freitas !

We have built an invoice parser plugin that might work for you. Please DM us so we can arrange a test.

I believe this would solve your problem. Sent with :love_letter: