Difference between revisions of "OCR/Roadmap"

From Open Food Facts wiki
Jump to navigation Jump to search
 
(17 intermediate revisions by 2 users not shown)
Line 1: Line 1:
 
Currently, all products are edited manually. This project is about automatic or semi-automatic detection of a number of things using OCR and Computer vision.
 
Currently, all products are edited manually. This project is about automatic or semi-automatic detection of a number of things using OCR and Computer vision.
  
Tools:
+
== Product Opener improvements ==
* Google Drive OCR or Google Goggles
+
* Process all uploaded images using Tesseract and/or the New Cloud based engine
* Ocropus
+
* Return JSON to mobile client and/or web client for suggestions to the user
* OpenCV
+
* Add support to search into OCR results
* Moodstocks
 
  
Targets:
+
== TODO ==
* Logos (standardized)
+
* Process Open Beauty Facts images
* Text
+
* Process the Belgian Food Photographs
 +
 
 +
== Short term goals ==
 +
* Use the right standard dict for each language
 +
* Integrate custom lists from Global Ingredients Taxonomy
 +
* USDA UNII list of ingredients (will also work for Open Beauty Facts)
 +
 
 +
 
 +
=== Testing ===
 +
==== Create a golden set of products that are complete ====
 +
* Product
 +
** Category: "Ingredients complete" "Ingredient images selected"
 +
** Get the ingredients image
 +
** Get the canonical (typed by contributors) ingredient list
 +
** Get the ingredients list generated with the current OCR system
 +
** Generate the ingredient list on your laptop based on the image, and the custom dictionary above
 +
** Compare the result with the canonical/golden test and report some accuracy measures
 +
* Draft Script: https://lite6.framapad.org/p/OFF_OCR_Script
 +
=== Easy wins ===
 +
* Process all images and make products searchable, even if not filled yet
 +
 
 +
==  Long-term goals ==
 +
* Get dictionaries translations from Wikidata
 +
* Investigate Ocropus for complex layout extractions
 +
* Investigate Open CV for detection of patterns, logos…
 +
 
 +
== Targets ==
 +
* Logos of brands (Getting them from POD ?)
 +
* Logos of Labels (standardized)
 +
* Text (distorted - bottle case, diagonally - with low light, bright light)
 
* Standardized layouts (US Nutrition labels)
 
* Standardized layouts (US Nutrition labels)
 +
** Store in separate image for further reference
 
* Standardized text (quantities, EU Packaging codes)
 
* Standardized text (quantities, EU Packaging codes)
 +
** Store in separate image for further reference
 
* Barcodes (extraction in uploaded images)
 
* Barcodes (extraction in uploaded images)
 +
** Store in separate image for further reference
 
* Image orientation: check that the text is properly oriented to guess if the image is properly oriented.
 
* Image orientation: check that the text is properly oriented to guess if the image is properly oriented.
 +
* Deep Learning
 +
** Product photo on packaging - guess category based on product picture
 +
** Container: guess whether it's a bottle, cardboard…
 +
Extracting areas is already great work: if we can extract logos or patterns, it will be faster for humans to double check and turn that into text.
  
Extracting areas is already great work: if we can extract logos or patterns, it will be faster for humans to double check and turn that into text.
+
[[Category:Roadmap]]
 +
[[Category:Project]]
 +
[[Category:ProductOpener]]
 +
[[Category:OCR]]
 +
[[Category:Artificial Intelligence]]

Latest revision as of 13:44, 19 February 2018

Currently, all products are edited manually. This project is about automatic or semi-automatic detection of a number of things using OCR and Computer vision.

Product Opener improvements

  • Process all uploaded images using Tesseract and/or the New Cloud based engine
  • Return JSON to mobile client and/or web client for suggestions to the user
  • Add support to search into OCR results

TODO

  • Process Open Beauty Facts images
  • Process the Belgian Food Photographs

Short term goals

  • Use the right standard dict for each language
  • Integrate custom lists from Global Ingredients Taxonomy
  • USDA UNII list of ingredients (will also work for Open Beauty Facts)


Testing

Create a golden set of products that are complete

  • Product
    • Category: "Ingredients complete" "Ingredient images selected"
    • Get the ingredients image
    • Get the canonical (typed by contributors) ingredient list
    • Get the ingredients list generated with the current OCR system
    • Generate the ingredient list on your laptop based on the image, and the custom dictionary above
    • Compare the result with the canonical/golden test and report some accuracy measures
  • Draft Script: https://lite6.framapad.org/p/OFF_OCR_Script

Easy wins

  • Process all images and make products searchable, even if not filled yet

Long-term goals

  • Get dictionaries translations from Wikidata
  • Investigate Ocropus for complex layout extractions
  • Investigate Open CV for detection of patterns, logos…

Targets

  • Logos of brands (Getting them from POD ?)
  • Logos of Labels (standardized)
  • Text (distorted - bottle case, diagonally - with low light, bright light)
  • Standardized layouts (US Nutrition labels)
    • Store in separate image for further reference
  • Standardized text (quantities, EU Packaging codes)
    • Store in separate image for further reference
  • Barcodes (extraction in uploaded images)
    • Store in separate image for further reference
  • Image orientation: check that the text is properly oriented to guess if the image is properly oriented.
  • Deep Learning
    • Product photo on packaging - guess category based on product picture
    • Container: guess whether it's a bottle, cardboard…

Extracting areas is already great work: if we can extract logos or patterns, it will be faster for humans to double check and turn that into text.