Ask HN: Open source OCR library? • Hacker News Board

Re: Ask HN: Open source OCR library?

#21

Post by jahewson » Thu, Jun 25, 2015, 5:57 AM UTC

t0 wrote: post #3

The accuracy of GOCR is very high and it doesn't require any learning. http://manpages.ubuntu.com/manpages/dapper/man1/gocr.1.html

GOCR is ok, certainly much better than GNU Ocrad, but I've had much better results with Tesseract.

Re: Ask HN: Open source OCR library?

#22

Post by kornish » Thu, Jun 25, 2015, 5:58 AM UTC

stevewepay wrote: post #6

I used Tesseract and OpenCV to process Words With Friends tiles.

Haha, this is awesome. Have you written about your program anywhere? Would love to hear more about it.

Re: Ask HN: Open source OCR library?

#23

Post by SXX » Thu, Jun 25, 2015, 6:02 AM UTC

Few years ago I used Cuneiform, but looks like it's dead now.

Re: Ask HN: Open source OCR library?

#24

Post by dharma1 » Thu, Jun 25, 2015, 6:02 AM UTC

Tesseract with ccv for SWT works but is a bit of a slow dog. Anyone used deep learning (caffe maybe?) for OCR?

Re: Ask HN: Open source OCR library?

#25

Post by derefr » Thu, Jun 25, 2015, 6:04 AM UTC

jlangenauer wrote: post #12

Tesseract is ok, but I gather that a lot of the good work in the last few years on it has remained closed source within Google. If you want to do text extraction, look at things like Stroke Width Transform to extract regions of text before passing them to Tesseract.

Does Google provide any "OCR as a service" API that takes advantage of their closed-source advances? I know something OCR-ish happens when you upload an image-PDF to Google Docs, but I don't remember if there's any way to get the resulting text out.

Re: Ask HN: Open source OCR library?

#26

Post by dharma1 » Thu, Jun 25, 2015, 6:04 AM UTC

JeremyWei wrote: post #16

you may try baidu OCR API https://github.com/JeremyWei/baidu-ocr

Is that trainable for new alphabets? API use policy?

Re: Ask HN: Open source OCR library?

#27

Post by jahewson » Thu, Jun 25, 2015, 6:12 AM UTC

WalterGR wrote: post #11

byoung2 wrote: post #2

https://code.google.com/p/tesseract-ocr/ is pretty good

Tesseract does no layout analysis. So if the source image contains text columns or pull quotes or similar, the output text will just be each row of text, from the far left to the far right.

Take a look at https://github.com/tmbdev/ocropy for layout analysis (at one point this project was called OCRopus).

Re: Ask HN: Open source OCR library?

#28

Post by physcab » Thu, Jun 25, 2015, 6:22 AM UTC

I tried using Tesseract and could not get it to work reliably. I tried a bunch of different pre-processing techniques and it turned into a very frustrating experience.

When I compared Tesseract to Abbyy, the difference was night and day. Abbyy straight out of the box got me 80%-90% accuracy of my text. Tesseract got around 75% at best with several layers deep of image pre-processing.

I know you said open source, and just wanted to say, I went down that path too and discovered in my case, proprietary software really was worth the price.

Re: Ask HN: Open source OCR library?

#29

Post by AlexMuir » Thu, Jun 25, 2015, 6:41 AM UTC

physcab wrote: post #28

I tried using Tesseract and could not get it to work reliably. I tried a bunch of different pre-processing techniques and it turned into a very frustrating experience. When I compared Tesseract to Abbyy, the difference was night and day. Abbyy straight out of the box got me 80%-90% accuracy of my text. Tesseract got around 75% at best with several layers deep of image pre-processing. I know you said open source, and…

Exact same experience here. Omnipage also produced excellent results.

Re: Ask HN: Open source OCR library?

#30

Post by ivanca » Thu, Jun 25, 2015, 6:56 AM UTC

Judging by the comments there is much space for improvement on open source OCR libraries, maybe someone with experience in the field should start a kickstarter for it, there must some here in HN itself; maybe something with CLI and GUI and layout recognition.