Can we use this feature to Get/Search text while automating flash and VDI Environments?

@alexcabuz That’s Exciting :smiley: :smiley:

Can’t wait for this to be in production. As I will be automating Invoicing processes in the near future.

Does this mean we don’t need to work with OCR Engine like ABBYY etc??

Can we use this feature to Get/Search text while automating flash and VDI Environments?

Hi @anasm. This does not replace Flexicapture from Abbyy, because that one covers many other usecases, like forms, and semi-structured documents which are not invoices or receipts. However, it handles situations with very many diverse layouts, which are tedious and expensive to define in Abbyy. So if you deal with hundreds or thousands of different vendors, then these ML models will get you going instantly, without any configuration.

Regarding your second question, this is not yet designed to work with images scraped from the screen, unless you do it manually, save the image and pass the jpg into the extractor. Also, it needs to be images of invoices and receipts.

Hope this helps,
Alex.

3 Likes