1. developing OCR now
- Posted by Norm Goundry <bonk1000 at HOTMAIL.COM>
May 14, 1999
-
Last edited May 15, 1999
I am starting this week to bring my Chinese translation program up to a
higher level, and this means embedding significant OCR capability into it.
I am not having any problems with EU (the whole program is written in it)
but I just wondered if any of you have used the available routines to do
image recognition?
I will explain how I am doing it for those who are interested; such as the
fact that it employs a modified genetic algorithm and fuzzy logic
hybridization. Sometime by the end of the week it will be beginning to work
with the over 45,000 completely different Chinese characters it will have to
deal with (far more than anything else out there, even including the most
expensive corporate and government Heavy Iron applications).
So if anyone is interested in discussing the topic of OCR for EU let's do
it.
Norm
