Libre OCR

shevirsy · 09-12-2014, 05:31 AM

I have a few PDFs made from library scans of rather old documents. The fonts look to me like those of today. The scans are not excellent, but they are made with a flatbed scanner and not those ripoffs with a camera where the page is twisted and you see a hand peeking from one side.

Do you have experience with libre software? Do you know tutorials or forum posts that can explain to a newbie? I have experience working with graphics. Not with OCR.

Toxaris · 09-12-2014, 07:13 AM

I have no knowledge of a good free OCR tool that even comes close to commercial ones.

shevirsy · 09-13-2014, 02:05 AM

Quote:

Originally Posted by Toxaris

I have no knowledge of a good free OCR tool that even comes close to commercial ones.

I have missed that thread where the OP asks "Do you have knowledge of a libre software pack that is better than the closed source counterpart".

Anyway, I have asked something different. You might reread.

Jellby · 09-13-2014, 02:41 AM

Try Tesseract. Not very user-friendly and probably not for newbies. And as Toxaris said, you won't get very much in the quality department.

As for the questions you asked: Yes. No.

shevirsy · 09-13-2014, 03:36 AM

Quote:

Originally Posted by Jellby

Try Tesseract. Not very user-friendly and probably not for newbies. And as Toxaris said, you won't get very much in the quality department.

I have tried it. In terms of usability is on the opposite side of Abbyy Finereader. Sad.

rkomar · 09-13-2014, 07:39 PM

The k2pdfopt program can do OCR on a scanned PDF using tesseract. It can even embed the results into the PDF file as a text layer. k2pdfopt has a zillion options, so I'm not sure it's easier to use than bare tesseract, but you can try it for nothing and see.

09-12-2014, 05:31 AM	#1
shevirsy Banned Posts: 28 Karma: 31454 Join Date: Sep 2014 Location: France Device: Kindle 3	Libre OCR I have a few PDFs made from library scans of rather old documents. The fonts look to me like those of today. The scans are not excellent, but they are made with a flatbed scanner and not those ripoffs with a camera where the page is twisted and you see a hand peeking from one side. Do you have experience with libre software? Do you know tutorials or forum posts that can explain to a newbie? I have experience working with graphics. Not with OCR.

Similar Threads
Thread	Thread Starter	Forum	Replies	Last Post
Best OCR error I've seen yet	Section8	General Discussions	26	07-02-2016 07:21 AM
Reading comfort of Aluratek Libre Color 7″ LCD & Libre Pro 5" ePaper	wandermaybe	Ectaco jetBook	5	05-13-2012 06:03 PM
How to convert an OCR file to a Non-OCR one	res9282	PDF	1	08-05-2011 05:58 AM
Do I have to OCR?	Ceryta	Workshop	7	05-07-2011 11:03 AM
OCR to use	pepak	Workshop	17	05-26-2008 05:30 PM

09-12-2014, 07:13 AM	#2
Toxaris Wizard Posts: 4,520 Karma: 121692313 Join Date: Oct 2009 Location: Heemskerk, NL Device: PRS-T1, Kobo Touch, Kobo Aura	I have no knowledge of a good free OCR tool that even comes close to commercial ones.

09-13-2014, 02:41 AM	#4
Jellby frumious Bandersnatch Posts: 7,570 Karma: 20150435 Join Date: Jan 2008 Location: Spaniard in Sweden Device: Cybook Orizon, Kobo Aura	Try Tesseract. Not very user-friendly and probably not for newbies. And as Toxaris said, you won't get very much in the quality department. As for the questions you asked: Yes. No.

09-13-2014, 07:39 PM	#6
rkomar Wizard Posts: 3,067 Karma: 18821071 Join Date: Oct 2010 Location: Sudbury, ON, Canada Device: PRS-505, PB 902, PRS-T1, PB 623, PB 840, PB 633	The k2pdfopt program can do OCR on a scanned PDF using tesseract. It can even embed the results into the PDF file as a text layer. k2pdfopt has a zillion options, so I'm not sure it's easier to use than bare tesseract, but you can try it for nothing and see.

Advert

Advert