Hi everyone,<\/p>\n
I’m working on a small project that tries to read grocery receipts and automatically categorize the items (milk \u2192 dairy, apples \u2192 produce, etc).<\/p>\n
The surprisingly hard part is that every store prints receipts differently. Walmart, Tesco, Costco, Aldi, and others all have their own formats, abbreviations, tax layouts, loyalty sections, and discount lines.<\/p>\n
To make the parser reliable, I need a few real examples of receipts from different stores.<\/p>\n
If you happen to have a receipt from one of these stores, it would help a lot if you could share one.<\/p>\n
Examples of stores I’m currently looking for include:<\/p>\n
US: Walmart, Kroger, Costco, Whole Foods, Target, Publix, Trader Joe’s, Aldi <\/p>\n
Canada: Loblaws \/ No Frills, Costco, Sobeys, Walmart <\/p>\n
UK: Tesco, Sainsbury’s, Asda, Aldi, Lidl <\/p>\n
Australia: Woolworths, Coles <\/p>\n
Singapore: FairPrice \/ NTUC <\/p>\n
Switzerland: Migros, Coop <\/p>\n
Japan: Aeon \/ MaxValu, Ito-Yokado <\/p>\n
South Korea: E-Mart, Homeplus<\/p>\n
What works best:<\/p>\n
\u2022 a quick photo of the receipt <\/p>\n
\u2022 a scanned receipt <\/p>\n
\u2022 a digital\/email receipt <\/p>\n
You can blur or crop anything personal like card numbers or addresses. The only parts I really need are:<\/p>\n
\u2022 the store name\/header <\/p>\n
\u2022 item lines <\/p>\n
\u2022 prices <\/p>\n
\u2022 tax\/discount sections<\/p>\n
Even one receipt helps because each retailer has its own format.<\/p>\n
If you’re willing to help, you can:<\/p>\n
\u2022 post an image here <\/p>\n
\u2022 DM me <\/p>\n
\u2022 share an Imgur \/ Google Drive link<\/p>\n
I\u2019d really appreciate it. And once the parser is in good shape, I\u2019m happy to share the dataset and parsing rules with the community as well.<\/p>\n
Thanks for helping a nerdy little project learn how to read grocery receipts \ud83d\ude42<\/p>\n<\/div>\n
submitted by \/u\/Sanju-05 <\/a>
[link]<\/a><\/span> [comments]<\/a><\/span><\/p>
