Take the 2-minute tour ×
Super User is a question and answer site for computer enthusiasts and power users. It's 100% free, no registration required.

I need to organize a large number of scanned receipts. The receipts are scanned in PDF, and I need is software that will intelligently look at a document and parse out date, location / vendor, total amount paid, etc. The key is that these fields need to extracted from each document for tabulation; it isn't enough to just have them OCRed for search purposes.

I think I am essentially looking for similar functionality as is in the NeatReceipts scanners, but without the need to do the scanning. Are there any 3rd party tools for doing this sort of specialized parsing or OCR?

share|improve this question

2 Answers 2

Well, the NeatWorks software can import PDFs as if you scanned them (there's an option to import in the Quick Scan UI).

Depending on volume, time sensitivity, data sensitivity, etc. you might also check out Shoeboxed, an online service that lets you either mail, scan, upload photos, etc. of receipts and business cards, then provides the information from them. It's kind of like NeatWorks in the cloud.

Shoeboxed pricing is high enough that if you're going to be in an office scanning then you're better off with the Neat products, but if you want to be able to simply take pictures of receipts, etc. while on the go then Shoeboxed may be a better bet for you (if more expensive over time). Shoeboxed may also be more amenable to truly batch processing since you can email in documents.

share|improve this answer

Have a look at ABBYY FlexiCapture, it's made for specialized OCR of single-type documents: forms, invoices, recepiets etc

ABBYY FlexiCapture 10 is intelligent, accurate and scalable document capture and data extraction software. It provides a single entry point to automatically transform the stream of different forms and documents of any structure and complexity to usable and accessible data ready to be exported into your business applications and databases

share|improve this answer
    
Care to explain what it does and/or how this solves the problem? Just posting links as an answer is frowned upon, especially when its used to endorse your own product –  Ivo Flipse Dec 6 '11 at 10:47
    
Sorry for not being specific enough. I beleive this software is just what the author is looking for, as it's made for specialized OCR of single-type documents: forms, invoices, recepiets etc. –  Nikolay Dec 7 '11 at 7:27
    
And here's the copy-paste description from the link i provided: ABBYY FlexiCapture 10 is intelligent, accurate and scalable document capture and data extraction software. It provides a single entry point to automatically transform the stream of different forms and documents of any structure and complexity to usable and accessible data ready to be exported into your business applications and databases. –  Nikolay Dec 7 '11 at 7:28
    
See, this makes your post much much better and even worth an upvote :-) –  Ivo Flipse Dec 7 '11 at 8:26
1  
Actually I'm not sure this really does the trick: as far as I can tell it ABBYY FlexiCapture doesn't actually parse receipts on its own. It is more of a configurable platform for enterprise-level document management (including parsing). I'm looking for something consumer / end-user focused. Thanks for the pointer tho! –  Ramon Apr 17 '12 at 18:41

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.