OCR/ICR

what are the best OCR / ICR tools. what we have are scattered images/pdfs to pull the data from. unfortunately , i cannot share the images or pdfs
NirvanamanagerAsked:
Who is Participating?
I wear a lot of hats...

"The solutions and answers provided on Experts Exchange have been extremely helpful to me over the last few years. I wear a lot of hats - Developer, Database Administrator, Help Desk, etc., so I know a lot of things but not a lot about one thing. Experts Exchange gives me answers from people who do know a lot about one thing, in a easy to use platform." -Todd S.

Michael-BestCommented:
Your scanner comes with OCR software that is best matched for the scanner.
If you want third party OCR software then see:
"The Best OCR Software of 2015 | Top Ten Reviews"
Link:
http://ocr-software-review.toptenreviews.com/

FYI read:
https://en.wikipedia.org/wiki/Comparison_of_optical_character_recognition_software
0
KimputerCommented:
The best document management suite seems to be from Nuance, being in the market from when floppies where still being used. If only you use it, the plain Paperport 14 version sets you back only 99 US dollars.
The best way is to scan the documents (or import existing), tag them yourself (like "invoice", "business", "personal"). If you leave your PC on though, usually there's a scheduled task to run through the PDF's again with OCR. In no time, the search command "FC1155" would return the PDF where FC1155 is really there (for instance an invoice number).
Of course, if the scan is of bad quality, it could be that that number is not recognised (maybe recognised as "PCi11S"). Therefore, the most trustworthy ones are the one scanned properply (straight, sharp, clear and easy to read printed text).
There's still no magic that can OCR handwriting properly though.
If the suite is working for you and you later need to add more people in the work flow, you have to upgrade to the networked versions.

As you can see, it's different than just OCR. If that's what you want though, then just use the first post above me.
1
Joe Winograd, Fellow&MVEDeveloperCommented:
First, a comment on an earlier post. There's no such thing as "OCR software that is best matched for the scanner". All modern OCR software can operate on an image, and all have the ability to scan documents using the scanner manufacturers' industry-standard scanning drivers, such as ISIS, SANE, TWAIN, WIA, and WIA 2.0 (the exception is when there are proprietary drivers, such as the Fujitsu ScanSnap series). The software that is bundled with scanners is based on whatever deal the scanner manufacturer negotiated with the OCR vendor. For example, Brother devices typically have Nuance's PaperPort bundled with it, which contains Nuance's own OmniPage OCR software built into it. Fujitsu often bundles ABBYY FineReader OCR with its scanners, as well as Adobe Acrobat, which contains built-in OCR (Acrobat calls it Text Recognition or Recognize Text). All of these are fine OCR packages that will work with the images produced from any scanner — and all can scan with the manufacturers' scanner drivers.

ICR (Intelligent Character Recognition) is much more difficult than OCR (Optical Character Recognition). While OCR has become very accurate, ICR is still problematic. There's an even newer approach called Intelligent Word Recognition (IWR). ICR recognizes cursive handwriting a character at a time, while IWR recognizes full words and phrases in cursive handwriting. The accuracy of ICR and IWR is way below that of OCR, and varies significantly from doc to doc. You will need to test it on your docs to see if the accuracy is acceptable. In many cases, it isn't, and a more cost-effective approach is heads-down data entry.

All of that said, two excellent OCR packages are ABBYY FineReader and Nuance's OmniPage:
http://www.abbyy.com/finereader/
http://www.nuance.com/for-individuals/by-product/omnipage/index.htm

Note this claim from ABBYY: "ABBYY provides highly accurate OCR, ICR, OMR and barcode recognition technologies..." And this one from Nuance: "Everything you need for scanning, OCR, ICR, OMR, PDF..." I suggest being skeptical of both ICR claims.

I use both ABBYY FineReader and OmniPage Ultimate, and can say that both are very accurate, but I can't say that one is always better than the other. I've tested them on the same documents, and sometimes one is better, sometimes the other is, but for the most part, the accuracy is similar - both very good!

Another idea is Nuance's PaperPort product, which is not a dedicated OCR package, but can perform OCR via Nuance's OmniPage, which is included "under the covers" (the OmniPage OCR engine is built into PaperPort):
http://nuance.com/for-individuals/by-product/paperport/index.htm

PaperPort is a robust scanning/imaging package that does a lot more than just OCR (but for pure OCR, is not as robust as OmniPage and FineReader). I use PaperPort extensively (more than OmniPage and FineReader combined). Its OCR capabilities (via the built-in OmniPage) may be adequate for your purposes. But if not, then go with OmniPage or FineReader. Note that PaperPort comes in Standard and Advanced editions. The comparison matrix is in the file "Comparison Matrix of PP14 Standard and PP14 Professional.pdf" at this PaperPort wiki:
http://sites.google.com/site/wikipaperport/files

I have written extensively about PaperPort here at EE. Check my user profile for articles that may be valuable if you go with PaperPort. In particular, be sure to upgrade to the latest version (if the copy you purchase is an earlier point release than 14.5):
PaperPort 14 - Free Upgrade to Version 14.5

And if you're running Windows 10 (or planning to), be sure to read this:
PaperPort 14 in Windows 10 - A First Look

It's a shame you can't share the images or PDFs, because I'd be happy to run some tests for you. Perhaps you can redact the private/sensitive portions of a few docs. But if not, the trial versions of the products should be able to help you decide. Regards, Joe
1

Experts Exchange Solution brought to you by

Your issues matter to us.

Facing a tech roadblock? Get the help and guidance you need from experienced professionals who care. Ask your question anytime, anywhere, with no hassle.

Start your 7-day free trial
It's more than this solution.Get answers and train to solve all your tech problems - anytime, anywhere.Try it for free Edge Out The Competitionfor your dream job with proven skills and certifications.Get started today Stand Outas the employee with proven skills.Start learning today for free Move Your Career Forwardwith certification training in the latest technologies.Start your trial today
Office 365

From novice to tech pro — start learning today.

Question has a verified solution.

Are you are experiencing a similar issue? Get a personalized answer when you ask a related question.

Have a better answer? Share it in a comment.