Hi all, I’ve used Tesseract in the past but the results were a bit underwhelming. Now I have used the OCR space engine, and I must say I’m impressed. The one things that bothers me is that it spits back the results as one big text, while Tesseract gave back the results per line. Is is possible to do this with the free OCR engine?
Perfect timing - this will be possible with our next system update. If all goes well, it will be available next week already.
That is absolutely awesome to hear. I will wait it out, thanks for the reply!
If you could update this post when it’s live, that would be great!
The feature is live now. To enable the “line by line” one column mode with OCR.space you can use the new
If you test your documents with the online OCR on the front page, check the new “Do receipt scanning and/or table recognition” box. This sets
isTable=true when it calls the API.