Required is a tool to extract data from receipts.
Using OCR or any technology necessary, gathering and storing all data in the receipt in the form of tables. Including price, name of product and UPC code.
program is to work on a cloud computing system.
1. this service will be a part of a bigger project, thus the need for "cloud computing". other then that, the amount will indeed be very vast.
2. the images will be added to a folder and the program will need to OCR each new receipt that is added.
3. attached are examples of receipt pics. they are in hebrew. notice the name, price and UPC codes. the program should identify hebrew fonts as well as english.
4. It is probably needed to change the contrast of the images or any other manipulation befor using OCR. the program should do this automatically.
5. the most important part is reliable decoding of - UPC,name,price of each product. this is crucial.