Changes

Jump to navigation Jump to search
no edit summary
Line 61: Line 61:     
== Computer vision ==
 
== Computer vision ==
      
Why it's important: all product data comes from photos of the product and labels. Today most of this data is entered manually. In order to be able to scale, we need to extract more data from photos automatically.
 
Why it's important: all product data comes from photos of the product and labels. Today most of this data is entered manually. In order to be able to scale, we need to extract more data from photos automatically.
Line 70: Line 69:  
* Archive of the images we have for a subset of popular products (8 Gb): https://static.openfoodfacts.org/images/popular-products.tar.gz
 
* Archive of the images we have for a subset of popular products (8 Gb): https://static.openfoodfacts.org/images/popular-products.tar.gz
 
* Images for all products that were added during a specific day: https://static.openfoodfacts.org/data/new_products_images_20180301.tar.gz
 
* Images for all products that were added during a specific day: https://static.openfoodfacts.org/data/new_products_images_20180301.tar.gz
 +
 +
* '''Slack channels: #ai-computervision #ai-machinelearning'''
 +
* '''Github AI / machine learning: openfoodfacts-ai'''
    
=== Improve OCR for ingredients ===
 
=== Improve OCR for ingredients ===
Line 109: Line 111:     
Background: We have started in the past year to ramp up effort, and we have processed 1,5 million images with OCR and general entity, barcode and QR-code recognition. The result is 1,5 million matching JSON files with bounding boxes.
 
Background: We have started in the past year to ramp up effort, and we have processed 1,5 million images with OCR and general entity, barcode and QR-code recognition. The result is 1,5 million matching JSON files with bounding boxes.
 +
 +
* '''Slack channels: #ai-machinelearning'''
 +
* '''Github AI / machine learning: openfoodfacts-ai'''
    
=== Automatically classify products ===
 
=== Automatically classify products ===
Line 123: Line 128:  
* Bad nutrition facts
 
* Bad nutrition facts
 
** e.g. by looking at outliers for products of the same category
 
** e.g. by looking at outliers for products of the same category
 +
 +
== Backend server and database ==
 +
 +
* '''Slack channels: #productopener #perl #mongodb'''
 +
* '''Github server backend: https://github.com/openfoodfacts/openfoodfacts-server'''
 +
 +
=== Backend Improvements, New Features and Performance ===
 +
 +
* The Open Food Facts backend and web site is coded in Perl and the data is stored in MongoDB
 +
* We currently have performance issues with MongoDB requests that could be optimized
 +
* There are many other areas for improvements for the backend, see https://github.com/openfoodfacts/openfoodfacts-server
      Line 128: Line 144:     
=== Taxonomy Editor ===
 
=== Taxonomy Editor ===
 +
 +
* '''Slack channels: #taxonomies #perl #python #php #nodejs'''
    
* We define and use multilingual taxonomies for categories, labels, ingredients and other fields.
 
* We define and use multilingual taxonomies for categories, labels, ingredients and other fields.
Line 133: Line 151:  
* They are currently defined in text files hosted on our wiki: https://en.wiki.openfoodfacts.org/Global_taxonomies but it is becoming unmanageable (the biggest taxonomy for categories is 37k lines long).
 
* They are currently defined in text files hosted on our wiki: https://en.wiki.openfoodfacts.org/Global_taxonomies but it is becoming unmanageable (the biggest taxonomy for categories is 37k lines long).
 
* We need a tool that makes it easy to edit the taxonomy and translate it.
 
* We need a tool that makes it easy to edit the taxonomy and translate it.
 +
* The code that handles taxonomies is coded in Perl, but the taxonomy editor could be coded in any language (e.g. python, nodejs, php etc.)
   −
=== Backend Improvements, New Features and Performance ===
     −
* The Open Food Facts backend and web site is coded in Perl and the data is stored in MongoDB
  −
* We currently have performance issues with MongoDB requests that could be optimized
  −
* There are many other areas for improvements for the backend, see https://github.com/openfoodfacts/openfoodfacts-server
      
== 2018- 2017 Project ideas ==
 
== 2018- 2017 Project ideas ==

Navigation menu