![otomatic feat. etc etc original mix otomatic feat. etc etc original mix](https://http2.mlstatic.com/D_NQ_NP_2X_621397-MLB31719158959_082019-F.jpg)
The reader is actively looking for specific bits of information instead of methodically scanning the document top-to-bottom. Sometimes known as “reading with a purpose”. We believe receipt reading is a selective process. We probably have a very smart mechanism to avoid such obstacles – selective reading. This mix of cue may be confusing, but not detrimental to understanding. The grand total is also not the only emphasized amount, the cash returned (405Yen) is also emphasized. The grand total is also not the lowest amount in the document, like one might expect.
![otomatic feat. etc etc original mix otomatic feat. etc etc original mix](https://img1.wsimg.com/isteam/ip/04433131-cbb7-4d56-8eab-043900564722/logo/62182fd7-c82f-4299-b13b-37d25eb795ac.png)
First, the largest amount on the document (2,022Yen) is not the grand total, it is in fact the cash received. In the former example there are many curve balls and obstacles to dodge, in terms of understanding the receipt content. How did you achieve such a feat in such a short amount of time?īeyond just reading the numbers (fortunately the numeral system in Japan is Western Arabic), what contextual information did you use? Did you examine the variation in type face (weight, size)? Location of the number on the page? Adjacency to other elements such as other numbers, text or symbols? You recalled other receipts in languages that you can read? How about the numbers – did they follow a pattern you used to make sense of them? Did you notice how knowing the Yen-USD exchange rate is imperative for understanding which expense this was?
![otomatic feat. etc etc original mix otomatic feat. etc etc original mix](http://www.urban75.org/blog/images/comacchio-ferrera-italy-09.jpg)
But still – extracting information from this receipt document was not challenging even without understanding a single word, or understanding if something is a word at all. For argument’s sake, let’s say you cannot read Japanese. Well done! I didn’t know you can read Japanese. Taking a wild guess here – you got most things right, and you did it really fast too. To make things fair, we will reveal that under current YEN-USD trade rates 1,000Yen is about $9 USD. This is not a test, the answers are below. Coincidentally, these are some of the bits of information we would need if we wanted to ask the tax authorities of Japan to reimburse us for the VAT we paid. Please extract the following information from it: (1) grand total amount paid, (2) VAT paid, (3) date of purchase, (4) what service was given? (taxi, hotel, restaurant, parking, etc.). Before you is a receipt image taken recently in Japan. When words have no meaning, we must rely on other cues and prior information. And we found that asking the computer to read a receipt is very much similar to asking a person who cannot read (a certain language) to do the same. In Way2VAT we analyze receipts so we can understand them, automatically.
![otomatic feat. etc etc original mix otomatic feat. etc etc original mix](https://venturebeat.com/wp-content/uploads/2020/03/Untitled-3.png)
So us humans read receipts without actually “reading” them, we don’t parse the text into sentences and words and construct meaning – rather we rely on our big brains to help decode the information on them and extract the useful information. Receipts have very little text, possibly not even a single valid sentence, but they are very highly structured. Surprisingly, we do that with very little support from the receipt document itself. When we look at a receipt we immediately understand what it is about.