Take the 2-minute tour ×
Ask Ubuntu is a question and answer site for Ubuntu users and developers. It's 100% free, no registration required.

I have seen some ebooks/papers that were apparently scanned from their paper versions but the text in the ebooks/papers can amazingly be copied out. I suppose the directly-scanned versions must have been processed by some Optical Character Recognition software.

So I would like to know what are the recommended Optical Character Recognition softwares? Especially those that are either for Ubuntu or free? If those for Windows are far more superior, please let me know as well.

I am particularly interested in those OCRs that can accept a scanned pdf file as input and still produce as output another pdf file that looks the same as the input one but with its text copyable.

Thanks and regards!

Please limit one software per answer

share|improve this question
add comment

10 Answers 10

up vote 9 down vote accepted

Tesseract OCR Install Tesseract OCR

The original engine was developed back in the late 80's by HP and IBM but it has proven to be one of the best Ocular Recognition Softwares I've used. It's recently undergone many updates to the engine and has become one of the most comprehensive OCR tools on the market. Outscoring against most all other OCR tools (with something in the higher 90 percentile of text matches) it can easily transform standard document type-face to text.

The following is an example:

tesseract ScannedDocument.png out

Will produce a file called out.txt

share|improve this answer
    
Thanks! I did not see that Tesseract supports output pdf. Do you know about this? –  Tim Oct 22 '10 at 2:56
    
@Tim, natively I don't believe Tesseract supports many input/output formats. However, as JanC's answer mentions, gscan2pdf uses Tesseract for OCR, and as it's name implies, it supports PDF output. –  Tim Lytle Oct 22 '10 at 10:56
add comment

Another project that should be able to do this is gscan2pdf Install gscan2pdf. This project can also use Tesseract, as well as other open source OCR tools.

share|improve this answer
add comment

I dont know any OCR for Ubuntu, but for Windows there is one that have the features you need. That is ABBYY FineReader this is the page but it is not free

share|improve this answer
1  
I used FineReader exactly as Tim wants (for opening protected PDFs) –  Extender Oct 22 '10 at 2:57
add comment

Free solution exists in repos, CunieForm (and YAGF as Gnome frontend for it)

share|improve this answer
    
Thanks! Does CunieForm support pdf as input and output formats? I did not see this on its Wikipedia page and its official page. –  Tim Oct 22 '10 at 3:08
    
Maybe no, but split PDF to series of TIFF is simple task anyway :) –  Extender Oct 22 '10 at 5:18
add comment

It seems like the Decapod project does or will export to PDF, so Tesseract must somehow export the necessary information to know where what text was found.

share|improve this answer
add comment

Adobe Acrobat (not reader, not a free application) is capable of OCR-ing a scanned PDF document and adding an invisible text layer on top of the image, so that the text could be selected and copied. Unfortunately I don't have it handy to check where exactly that feature is located in Acrobat's UI, but I've been successfully using it couple of times for the same purpose as you mentioned.

And yes, this is a Windows software, not Linux one, but according to Wine HQ application database, it works under Wine.

share|improve this answer
add comment

The best OCR software is usually embedded in printers/scaners/copiers. The Canon IRC 3880 in my office can output great OCR'd pdfs easier and faster than any desktop program that I know. Put the book on the tray (unbound), select your mail address, press the green button.

Most of the OCR's pdf that you can find on the net come for similar machines. The problem is that the price is too high for home usage (around 12000 euros IRC).

share|improve this answer
add comment

My favorite free, online OCR software is offered by Ricoh Innovations. This is a beta program, but I find it works quite well. Check it out at: http://beta.rii.ricoh.com/betalabs/content/document-conversion

share|improve this answer
add comment

FineReader also has an online version. It claims to be able to process PDFs as input format --- http://finereader.abbyyonline.com/en/Help/Faq/

share|improve this answer
add comment

OCRFeeder

It is a GUI application.

enter image description here

It uses tesseract-ocr or ocrad as OCR engine.

Can install with Software Center or with,

sudo apt-get install ocrfeeder
share|improve this answer
add comment

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.