Difference between revisions of "OCR/Results"

From Open Food Facts wiki
Jump to navigation Jump to search
Line 48: Line 48:
  
 
== What to do ==
 
== What to do ==
=== Cropped front images ===
 
=== Cropped ingredient images ===
 
=== Cropped nutrition images ===
 
=== Raw images ===
 
 
=== Versions of the same product ===
 
=== Versions of the same product ===
 +
* All versions of images selected have been processed
 +
* All images ever uploaded  have been processed
 
=== Check complete products ===
 
=== Check complete products ===
 +
* Check how similar ingredients lists are to what is detected
 +
* Check if brands are suggested that are not here (eg Umbrella brands)
 +
* Extract addresses
 +
* Extract URLs
 +
 
=== Suggest values for incomplete products ===
 
=== Suggest values for incomplete products ===
 +
* Try to suggest possible categories based on extracted text
 +
* Try to suggest brands, both based on the Brand JSON field and on Raw text extraction
 +
 
=== Search engine (internal/external) considerations ===
 
=== Search engine (internal/external) considerations ===
 +
* Add raw output as hidden text to enable search engine to index incomplete products
 +
* Add hidden field to enable the internal search engine to find incomplete products
 +
== Kind of images processed ==
 +
==== Cropped front images ====
 +
==== Cropped ingredient images ====
 +
==== Cropped nutrition images ====
 +
==== Raw images ====

Revision as of 12:20, 24 January 2016

How to process the 1.4 million JSON files we've generated

Example

Image

ingredients.12.400.jpg

Output

http://static.openfoodfacts.ovh/images/products/40193045/ingredients.12.full.json

{  
   u'responses':[  
      {  
         u'textAnnotations':[  
            {  
               u'locale':u'de',
               u'description':               u'Doppelrahmstufe\nAT Kasezubereitung 60% F.LT\nzutaten:Frischkase,
               2               gefriergetrockne\nter Gorgonzola,
               Salz,
               Verdickungsmittet\nJohannisbrotkernmehl und Guarkemmehlt\nAroma,
               Stickstoff zum Aufschlagen\nNach dem Offnen alsbald verzehren\nUngeoffnet gekuhlt mindestens\nhaltbar bis:siehe Boden\nBY 706\nIn Deutschland hergestellt\n',
               u'boundingPoly':{  
                  u'vertices':[  
                     {  
                        u'y':232,
                        u'x':190
                     },
                     {  
                        u'y':232,
                        u'x':1500
                     },
                     {  
                        u'y':1410,
                        u'x':1500
                     },
                     {  
                        u'y':1410,
                        u'x':190
                     }
                  ]
               }
            }
         ]
      }
   ]
}

Comments

What to do

Versions of the same product

  • All versions of images selected have been processed
  • All images ever uploaded have been processed

Check complete products

  • Check how similar ingredients lists are to what is detected
  • Check if brands are suggested that are not here (eg Umbrella brands)
  • Extract addresses
  • Extract URLs

Suggest values for incomplete products

  • Try to suggest possible categories based on extracted text
  • Try to suggest brands, both based on the Brand JSON field and on Raw text extraction

Search engine (internal/external) considerations

  • Add raw output as hidden text to enable search engine to index incomplete products
  • Add hidden field to enable the internal search engine to find incomplete products

Kind of images processed

Cropped front images

Cropped ingredient images

Cropped nutrition images

Raw images