Azure has a separate service to read forms and formatted docs. https://azure.microsoft.com/en-us/services/cognitive-service...

Thanks I was not aware! I’ll have to figure out how to easily test it (AWS tectrsct is actually really nice in that regard)

Do you know how good it is? I have a LOT of structured documents that I need to OCR.

MSFT person here - give it a try! sign up, and you get a free trial that can allow you to easily benchmark.

Interesting. That is actually something I've been looking for and I do have a msdn sub.

fyi that defaulted to indian rupee as default currency for me (UK based & zero indian connections). Weird

Have you tried the tabula free program? I use it for some finance work reading filings.

http://tabula.technology/

Yep! It's great, but is maybe 60% there, so I'm looking for something that can extract much more structure from a document. I doubt what I'm looking for will exist for another 10 years, though.

is it feasible to create loose templates for where the data is and extract that way? i have a mothballed project that did pretty well. it was able to discern different templates from a mass of documents.

I'm curious, if you email me a sample I can tell you what's possible.

I found a relatively recent (Feb. 2019) comparison of OCR software and services [1]. It may be interesting to you, especially the "Texas Campaign Filing" comparison, which seems to have (nested) tables.

[1] https://source.opennews.org/articles/so-many-ocr-options/

That's a good point not explained in the article: there are a huge number of use cases for OCR. In this case, the use is extracting words that can be used in full-text search, so structural extraction isn't a key criteria.

Edit: and now it's hopefully clarified in the article itself. :)

  In this case, the use is extracting words that can be used in full-text search, so structural extraction isn't a key criteria.

In case someone wants to know more, the former is known as "full page OCR" and the latter as "data capture"/"document processing" (or IDP, intelligent document processing).

Full page OCR for machine printed text is considered a solved problem (but not for handwritten text). Data capture is hard to do and involves extracting specific fields from documents.

The first big cloud company going into data capture territory was Amazon with AWS Textract (calling it OCR++). There's also Document Understanding AI (Google) and Azure Form Recognizer in Beta, as mentioned by others in this thread.

The big 3 RPA companies (UiPath, Automation Anywhere, Blue Prism) have also gone into data capture (calling it cognitive or intelligent RPA).

ABBYY (with FlexiCapture) and Kofax (who recently acquired Nuance's imaging division, the 2nd most popular OCR engine after ABBYY's) are the traditional IDP players.

So does Google Cloud: https://cloud.google.com/solutions/document-understanding/

Thnaks - looks like table extraction is in Alpha. I submitted a request to check it out!

just on the note of tables, have you tried the table extraction and OCR on Microsoft Excel on iPhone? It may also be on Android, i just tried it on iPhone, and man! it works great!

I have - its really good but for our use case (thousands of PDFs a day) that wouldn’t be reasonable :-(

What kind of post processing? I'm not an expert, but usually we have done a lot of preprocessing (like binarization,etc) before we call cloud ocr services.

This comes up a lot with financial statements and government data as well. The government stuff is getting much better though.

What is the accuracy that you're getting from it?