converter for OCR from images

manotroll · 04-21-2023, 09:42 PM

I have some books that the publisher in my country does not sell in digital format and I would like to convert them to use on kindle
I have the advantage of increasing the size of the text I can read at night with its own light and the book is 98% text.
but I did not find a way to do this in caliber does it support this feature?

kovidgoyal · 04-21-2023, 10:03 PM

No calibre does not have any OCR capabilities.

manotroll · 04-22-2023, 09:13 AM

and there is no possibility of having this support in the future?

kovidgoyal · 04-22-2023, 10:01 AM

calibre is open source anyone can contribute code to it. I will say this is not on my horizon.

feuille · 04-28-2023, 02:01 AM

Quote:

Originally Posted by manotroll

and there is no possibility of having this support in the future?

I'm currently working on a GUI plugin that adds a text layer to the PDF format for a selected book. I will publish it in the next few days.

Quoth · 04-28-2023, 02:20 PM

However I think text from PDF images via OCR is a workflow best done before the final version is added to the Library. It's not conversion in the sense mobi, azw3, epub etc to each other are. It needs human proofing and editing.

feuille · 04-29-2023, 04:07 AM

Quote:

Originally Posted by Quoth

However I think text from PDF images via OCR is a workflow best done before the final version is added to the Library.

Agreed when it comes to creating a new format from a scan. I do it so, too.
In my use case, however, it is about adding a text layer to a PDF whose layout should not be changed, for example to enable full-text search (FTS) and text extraction.
In my experience, with a good scan and the correct configuration of the OCR software (Tesseract), the recognition errors are relatively small and hardly affect the FTS. If you copy a piece of text for a quote, you can easily check it against the original layout. Also, before writing the text layer, I plan to offer the scan result in a text editor, with the possibility of proofreading.

Quoth · 04-29-2023, 05:49 AM

My experience of unproofed OCR text layer is the Internet Archive. Indeed it's only any use for text search and not great for that.

mvivar · 05-09-2023, 08:08 AM

I have recently converted a pdf non text just image into an epub. It took me a couple of hours to convert it into text.
There are some ocr softwares very accurate, but the one I had less errors was the one of google drive.
Make sure your pdf do not exceed 2 mb. You can split it.
Upload the files to google drive.
Right button, open with google docs.
And done.
Then you can download it as txt, or docx, etc... and convert it into epub.
Good luck!

04-21-2023, 09:42 PM	#1
manotroll Junior Member Posts: 7 Karma: 10 Join Date: Aug 2020 Device: Kindle Paperwhite 2021	converter for OCR from images I have some books that the publisher in my country does not sell in digital format and I would like to convert them to use on kindle I have the advantage of increasing the size of the text I can read at night with its own light and the book is 98% text. but I did not find a way to do this in caliber does it support this feature?

Similar Threads
Thread	Thread Starter	Forum	Replies	Last Post
Anyone used iPad for OCR, proofreading or editing book images?	graycyn	Apple Devices	6	09-11-2020 06:35 PM
no text extraction for pdf with images and OCR	fxp33	Conversion	7	12-15-2015 07:22 AM
Can you OCR the images inside of .pdf files?	klmmc13	Workshop	39	10-30-2014 08:07 PM
Free PDF to text OCR Converter	Thasaidon	Deals and Resources (No Self-Promotion or Affiliate Links)	1	04-02-2012 11:58 AM
free PDF to EPUB converter with images	rmm1	Apple Devices	1	05-15-2010 12:43 AM

04-21-2023, 10:03 PM	#2
kovidgoyal creator of calibre Posts: 43,858 Karma: 22666666 Join Date: Oct 2006 Location: Mumbai, India Device: Various	No calibre does not have any OCR capabilities.

04-22-2023, 09:13 AM	#3
manotroll Junior Member Posts: 7 Karma: 10 Join Date: Aug 2020 Device: Kindle Paperwhite 2021	and there is no possibility of having this support in the future?

04-22-2023, 10:01 AM	#4
kovidgoyal creator of calibre Posts: 43,858 Karma: 22666666 Join Date: Oct 2006 Location: Mumbai, India Device: Various	calibre is open source anyone can contribute code to it. I will say this is not on my horizon.

04-28-2023, 02:20 PM	#6
Quoth the rook, bossing Never. Posts: 11,158 Karma: 85874891 Join Date: Jun 2017 Location: Ireland Device: All 4 Kinds: epub eink, Kindle, android eink, NxtPaper11	However I think text from PDF images via OCR is a workflow best done before the final version is added to the Library. It's not conversion in the sense mobi, azw3, epub etc to each other are. It needs human proofing and editing.

04-29-2023, 05:49 AM	#8
Quoth the rook, bossing Never. Posts: 11,158 Karma: 85874891 Join Date: Jun 2017 Location: Ireland Device: All 4 Kinds: epub eink, Kindle, android eink, NxtPaper11	My experience of unproofed OCR text layer is the Internet Archive. Indeed it's only any use for text search and not great for that.

05-09-2023, 08:08 AM	#9
mvivar Junior Member Posts: 2 Karma: 10 Join Date: May 2023 Device: kindle	I have recently converted a pdf non text just image into an epub. It took me a couple of hours to convert it into text. There are some ocr softwares very accurate, but the one I had less errors was the one of google drive. Make sure your pdf do not exceed 2 mb. You can split it. Upload the files to google drive. Right button, open with google docs. And done. Then you can download it as txt, or docx, etc... and convert it into epub. Good luck!

Advert

Advert