OCR/Roadmap

From Open Food Facts wiki
Revision as of 16:54, 2 May 2015 by Teolemon (talk | contribs)

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:

  • Google Drive OCR or Google Goggles
  • Ocropus
  • OpenCV
  • Moodstocks

Targets:

  • Logos (standardized)
  • Text
  • Standardized layouts (US Nutrition labels)
  • Standardized text (quantities, EU Packaging codes)
  • Barcodes (extraction in uploaded images)
  • Image orientation: check that the text is properly oriented to guess if the image is properly oriented.

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.