News for hackers. Stuff that matters.

Ask HN: What OCR tool do you use in your project?

I am working on a project where I want to extract data from PDF document. Sometimes these are scanned PDF or forms.

I am looking for for an OCR tool (paid or open source) which can effectively extract data from poorly scanned documents and forms. What do you use?

( 8 comments | 2 points | on HN )
Re:Ask HN: What OCR tool do you use in your project? by beardyw on Monday July 17, 2023 @12:14PM (#36760008)
A bit off topic but I've just started using Google Lens to extract whole pages from books with my phone. Near perfect conversion to text is great for taking notes.
Re:Ask HN: What OCR tool do you use in your project? by vikasr111 on Monday July 17, 2023 @01:15PM (#36760989)
Google Lens works great in individual use cases, wonder what they are using behind the scene.

In my case I need to extract data on server side, so a library/API will be most suitable.

Re:Ask HN: What OCR tool do you use in your project? by smoldesu on Monday July 17, 2023 @11:49AM (#36759697)
I still use Tesseract. It's not the fastest or most-accurate anymore, but it gets what I need off of PDF files.
Re:Ask HN: What OCR tool do you use in your project? by vikasr111 on Monday July 17, 2023 @11:58AM (#36759814)
Does it work well with scanned PDF? In my experiments it was not giving the correct output.
Re:Ask HN: What OCR tool do you use in your project? by james-revisoai on Tuesday July 18, 2023 @08:50AM (#36771352)
Explore different page segmentation modes and make sure you are using v4 (it's a massive step up)
Re:Ask HN: What OCR tool do you use in your project? by sandreas on Monday July 17, 2023 @08:33PM (#36766189)
* * *
Re:Ask HN: What OCR tool do you use in your project? by itake on Tuesday July 18, 2023 @11:41AM (#36774286)
What languages do you need to support? Off the shelf models don't work well on non-Latin languages. You may need to train your own.
Re:Ask HN: What OCR tool do you use in your project? by is_true on Tuesday July 18, 2023 @03:52PM (#36778260)
We started using tesseract for a project that needed to extract text from video frames. But in the end we moved to easyocr, as it needed less preprocessing for our use case.