Does anyone know where I can find a receipt dataset?
Automating receipt processing with deep learning
21–30 of 35 posts
Re: Automating receipt processing with deep learning
#22Earlier quoted context omitted.
> Need to digitize documents, receipts or invoices but too lazy to code? Head over to Nanonets and build OCR models for free! I think that once you go down the path of OCR'ing your own invoices, you better start a company around it.
Gonna be honest, I think it's a dead-end. The solution IMO will come from the supply side; Easier to get receipts digitally from the store / vendor / seller, than to spend all this effort on converting physical receipts to digital. Sure - there's good retro usage, I'd rather push for sellers to offer you digital receipts. In fact, I already get that from my local supermarket. My bank card is registered to their app,…
> Easier to get receipts digitally
if the need was there you'd already get a qr code to a shortlink to a rest api to fetch the data. existing tech, well defined behavior, augments existing data transfer without being incompatible with the current clients (the squishy humans)
Re: Automating receipt processing with deep learning
#23Earlier quoted context omitted.
> Need to digitize documents, receipts or invoices but too lazy to code? Head over to Nanonets and build OCR models for free! I think that once you go down the path of OCR'ing your own invoices, you better start a company around it.
Gonna be honest, I think it's a dead-end. The solution IMO will come from the supply side; Easier to get receipts digitally from the store / vendor / seller, than to spend all this effort on converting physical receipts to digital. Sure - there's good retro usage, I'd rather push for sellers to offer you digital receipts. In fact, I already get that from my local supermarket. My bank card is registered to their app,…
Arn't most of the major retailers already sending the receipt line items to the CC processors? Once folks get more comfortable with realizing this is happening, Visa/Mastercard can start offering receipt organization through their card management apps.
Re: Automating receipt processing with deep learning
#24Sensibill (a former boss designed their system) has done pretty well at interpreting receipts in various formats.
Re: Automating receipt processing with deep learning
#25Is this dedicated receipt OCR significantly better then the out-of-the box OCR you get from Google Cloud Vision, Abbyy or OCR.space?
As standard OCR gets better and better, the room for specialized OCR solutions is becoming smaller.
Re: Automating receipt processing with deep learning
#26So what is the state of art? Is there a decent software available, that actually works? An app that a small company could use easily, say, for employee expense reports with reliable data parsing and automatic expense/tax calculations?
I've been using waveapps.com. their receipt processor allows me to forward any I get in email via pdf. They have an app to upload a pic as well. Have yet to have an issue. Even the Costco ones that have a line through them. It's been great. And it's "free".
I use waveapps too and I'm pretty sure they're Mechanical Turking their receipt transcription. Sometimes it takes too long for it to be an automated process.
Re: Automating receipt processing with deep learning
#27It's a nice overview article for anyone interested in the topic of IE from financial documents. However, for industrial level solutions Tesseract does not cut it. Abbyy is the best OCR engine on the market currently. Receipt IE works just fine with rules supported by a small BiLSTM as fallback just because receipts do not contain a lot of text. With invoices this approach is suboptimal. On a general note no DL approa…
Wow Abbyy is 26 years old. Nice to see software that lasts that sort of time.
I remember playing with their OCR (FineReader, I think it was called?) when it came as part of shareware bundles on magazine CDs in the mid-90s...
Re: Automating receipt processing with deep learning
#28What is the point of spamming [1] HN with this low-effort content marketing for Nanonets that barely scratches the surface of the topic but instead is full of obnoxious calls to action? [1]: https://i.imgur.com/eIhwtjo.png
> Need to digitize documents, receipts or invoices but too lazy to code? Head over to Nanonets and build OCR models for free! I think that once you go down the path of OCR'ing your own invoices, you better start a company around it.
My company has been using Receipt Bank for a few years. God knows what technology they use internally - I don’t care. They have a sweet app that scans receipts and then sucks them into a beautiful back end interface that the book keepers use to align statement items with their backup. Yes, this is a solved problems.
Re: Automating receipt processing with deep learning
#29What is the point of spamming [1] HN with this low-effort content marketing for Nanonets that barely scratches the surface of the topic but instead is full of obnoxious calls to action? [1]: https://i.imgur.com/eIhwtjo.png
I agree with some of the sibling comments -- it's reasonably in-depth with some practical examples.
However, this sort of "content marketing by tweaking submission titles to the same blog repeatedly" posting behaviour would be flagged to oblivion if done by a non-YCombinator funded company...
Re: Automating receipt processing with deep learning
#30Earlier quoted context omitted.
> Need to digitize documents, receipts or invoices but too lazy to code? Head over to Nanonets and build OCR models for free! I think that once you go down the path of OCR'ing your own invoices, you better start a company around it.
Gonna be honest, I think it's a dead-end. The solution IMO will come from the supply side; Easier to get receipts digitally from the store / vendor / seller, than to spend all this effort on converting physical receipts to digital. Sure - there's good retro usage, I'd rather push for sellers to offer you digital receipts. In fact, I already get that from my local supermarket. My bank card is registered to their app,…
> My bank card is registered to their app, so every time I swipe my card or scan my app (when paying with cash), I get a receipt on the app
That's great but why does this need to be an app? Why can't it be sent via email or have a website I can log into? I'm not downloading an app for every company I want to do business with.