Changes

Jump to navigation Jump to search
Line 62: Line 62:     
Background: We currently only do basic OCR for ingredients. There is a lot of room for improvement.  
 
Background: We currently only do basic OCR for ingredients. There is a lot of room for improvement.  
 +
 +
Sample data set:
 +
* Archive of the images we have for a subset of popular products (8 Gb): https://static.openfoodfacts.org/images/popular-products.tar.gz
    
=== Improve OCR for ingredients ===
 
=== Improve OCR for ingredients ===
Line 76: Line 79:  
=== Brands and labels detection ===
 
=== Brands and labels detection ===
   −
* Automatically recognize brands and labels
+
* Automatically recognize brands and labels (organic, fair trade etc.)
 +
 
 +
=== Packaging recognition ===
 +
 
 +
* Is it a can, a bottle, a cardboard pack etc.
 +
 
 +
=== Product recognition ===
    +
* Recognize the front of products using the camera of the mobile phone, without scanning barcodes
 +
* Ideally offline and on device recognition (without having to take a picture and sending it to a server)
    
== Data science ==
 
== Data science ==

Navigation menu