Open Source OCR for Large Collections of Scanned Documents - Art Rhyno

[kba]

[zuphilip]

Some points from @artunit's talk:

• concentrates on OCR of newspapers on microfilms/microfiches
• concentrates on ABBYY vs. Tesseract
  • comparison slide: https://youtu.be/gcjCiS9pJ3A?t=1439
• mentions the Line Segment Detector: http://www.ipol.im/pub/art/2012/gjmr-lsd/
• mentions the Olena project: https://www.lrde.epita.fr/wiki/Olena
• distributed OCR with Hadoop
• mentions his repo https://github.com/artunit/ossocr
• discussion in the end
  • backup, storage on hard drives
  • OCRropus (based on Tesseract at this time): Python based, effective for book pages not newspapers
  • What is Google's role in Tesseract?
  • How to present that all in the end? Annotations for the users?