An overview of computational analysis, and exploration of strategies and challenges.

Anatomy and Physiology of a Digital Book

• Two books - page images and companion OCR - (sample book from HTDL)
  • What our eyes like to read is images
  • What machines read  needs to be constrained and predictable.
• Books have metadata -
  
  • bibliographic (catalog view, MARC view)
  • structural
• OCR - where does it come from?
• OCR issues
• • language specific dictionaries
  • font styles
  • image resolution

Tokenization - we want to count words, why tokenize?