[HN Gopher] Our search for the best OCR tool (2019)
       ___________________________________________________________________
        
       Our search for the best OCR tool (2019)
        
       Author : longrod
       Score  : 45 points
       Date   : 2022-07-11 08:11 UTC (1 days ago)
        
 (HTM) web link (source.opennews.org)
 (TXT) w3m dump (source.opennews.org)
        
       | pronoiac wrote:
       | I went looking for a similar comparison a few months ago, and saw
       | this: https://research.aimultiple.com/ocr-accuracy/ It compared
       | ABBYY FineReader 15, Amazon Textract, Google Cloud Platform
       | Vision API, Microsoft Azure Computer Vision API, and Tesseract
       | OCR Engine. I ended up using OCRmyPDF / Tesseract out of
       | convenience, but doing a second pass with Google Cloud Vision,
       | AWS Textract, or Abbyy is somewhere on my to-do list.
        
         | ce4 wrote:
         | I went with this instead of OCRmyPDF:
         | 
         | https://gitlab.com/kebekus/scantools/
        
           | pronoiac wrote:
           | I hadn't heard of scantools! Do you have anything to say
           | about it? Why you chose it, features, etc.?
        
       | nicodjimenez wrote:
       | For STEM applications, nothing beats Mathpix OCR.
       | 
       | FB Research uses it, London Stock Exchange uses it, Chegg uses it
       | (in fact even recently transitioned to Mathpix OCR from Google
       | vision), and many, many other companies and individuals.
       | 
       | Disclaimer: I'm the founder.
        
       | nammi wrote:
       | Does anyone use OCR to convert BluRay subtitles (.sup) to
       | plaintext .srt files? I've used tools like SupRip and BDSup2Sub,
       | but they've all required pretty significant cleanup afterwards.
       | 'l', '1', and 'I' especially get mixed up a lot
        
         | leokennis wrote:
         | Assuming all these subtitles (at least per movie) are in the
         | same font, isn't it enough to tell/correct it once that "this
         | is an I" and "this is a 1", and then it knows for the entire
         | .sup?
        
           | nammi wrote:
           | That's what I figured, but in practice I wasn't able to do
           | that without having to manually enter most subtitles. The
           | tools are relatively old, so I was hoping something newer had
           | figured it out
        
       | longrod wrote:
       | Found this comparison while researching OCR. It doesn't have the
       | latest libraries like PaddleOCR but the performance of different
       | OCR libraries is still quite apparent.
        
         | ducktective wrote:
         | I think among the easy-to-use FOSS CLI tools, the competition
         | is between Tesseract and PaddlePaddle. I'm interested to know
         | how they fare against each other. I'm mainly interested in
         | using them in `ocrmypdf`
        
           | mdp2021 wrote:
           | If you prefer not to install it at this stage, there is a
           | chance that PaddlePaddle has a web interface - maybe you
           | could try and see the results against a document also
           | processed with Tesseract (also those in the article, if the
           | scans are available).
        
       | bufo wrote:
       | The iOS / Apple OCR Swift API is drastically better than the ones
       | I've tried online (eg. Microsoft) or the open source ones
       | (Tesseract). Highly recommended. You can get fairly high
       | throughput with M1 chips. The CNN is accelerated by the neural
       | chip and the language model is accelerated by the GPU.
        
       | simonw wrote:
       | I had spectacular results from AWS Textract recently - which when
       | this article was written (2019) wasn't yet openly available.
       | 
       | I fed it thousands of pages of historical scanned documents -
       | including handwritten journals from the 1800s - and it could read
       | them better than I could!
       | 
       | I built a tool to use it (since running it in bulk against PDFs
       | in a bucket took a few too many steps) and wrote about my
       | experiences with it here:
       | https://simonwillison.net/2022/Jun/30/s3-ocr/
        
         | amelius wrote:
         | Great that it works for you, but I'm not too happy about big
         | companies assuming that my product is connected to the
         | internet.
        
       | noodlesUK wrote:
       | What I really want is something with a similar set of convenient
       | APIs and CLIs like ocrmypdf [1] that supports some of the more
       | recent ML based systems. Ocrmypdf has really good ergonomics for
       | me in terms of ease of scripting.
       | 
       | Something like DocTR [2] with the same api would be fantastic.
       | 
       | [1] https://ocrmypdf.readthedocs.io/en/latest/
       | 
       | [2] https://mindee.github.io/doctr/
        
       | albatrosstrophy wrote:
       | How about foreign languages? I've never had one good enough for
       | Arabic. 3 years ago when needed it for a project, no OCR I found
       | could read a properly scanned Arabic page. Had to go on Fiverr
       | and paid a transcriber instead.
        
       | Rochus wrote:
       | Interesting report. As far as I understand in total no of the
       | systems was really better in all categories (or did I miss
       | something?). A summary would have been helpful. Also it would be
       | interesting whether the neural network based or the traditional
       | Tesseract engine was used. I did similar experiments for a
       | project six years ago and ended up with Tesseract and a custom
       | traineddata file.
        
       | iisan7 wrote:
       | What do folks think about these document types as a corpus for
       | comparing tools? It's missing images and handwriting samples, but
       | those types of documents might just be too variable to make
       | conclusions about.
       | 
       | I remember Baidu's OCR giving excellent English results, but it
       | looks like their API is deprecated now. Out of curiousity, I ran
       | these samples through easyOCR by JaidedAI. Results at
       | https://pastebin.com/RjzVd5Sf.
        
         | sgc wrote:
         | I OCR books, so they are not a good sample. I would want to
         | compare at least 10 pages per sample, with more typical
         | problems such as skewed, rounded pages from photos, artifacts,
         | damaged source pages (tears and creases) etc. They do reproduce
         | some problems with changing fonts and layout, but a big piece
         | of the puzzle is custom dictionaries and layout _training_. It
         | 's fine for a once over, but not a deep dive.
        
       ___________________________________________________________________
       (page generated 2022-07-12 23:01 UTC)