17 Aug 2004
CS 5244: Multimedia
24/44
Robust Document Understanding
¡OCR
and document understanding are (currently) fragile
technologies
lFull
scan Þ OCR Þ store pipeline makes many
assumptions
lWhat are some?
¡________________
¡________________
¡________________
¡________________
¡________________
Scholarly and
historical DL
are much harder!
are much harder!