Re:Writing a fuzzy receipt parser in Python
by laito on Tuesday October 06, 2015 @10:44AM
(#10339190)
Hey, this is pretty cool. I actually tried something similar. (Keeping a list of shop names and matching it with tesseract's results)
I was trying hough transform for slight image rotations. I wasn't aware of imagemagick's textcleaner script. That could have save me a lot of trouble :)
I got roadblocked by the problem of having various kinds of receipts with absolutely no layout in common. I figured it would need a lot of training for the system to have a decent accuracy and left it for another day.
[ Parent
| on HN ]
Re:Writing a fuzzy receipt parser in Python
by omn1 on Tuesday October 06, 2015 @11:31AM
(#10339536)
Yeah, relying on the layout never worked for me as well.
For instance even the supermarket address is not standardized. Some shops use:
> Market name > Examplestreet 12 > 19393 Examplecity
while others use:
> Market name > 19393 Examplecity > Examplestreet 12
We're not even talking about the invoice/receipt layout. It's different all the time.
Re:Writing a fuzzy receipt parser in Python
by mseri on Tuesday October 06, 2015 @12:34PM
(#10340109)
Cool. We did a similar thing at an hack, integrated with Dropbox and an automatic monthly receipt generation. I think most if not all the code should still be in pieces on our github accounts