• Post Reply Bookmark Topic Watch Topic
  • New Topic

Java Open Source OCR for SPAM  RSS feed

 
William Frederico
Greenhorn
Posts: 9
  • Mark post as helpful
  • send pies
  • Quote
  • Report post to moderator
Hello,

Hope I picked the right forum! Looking at enhancing the SPAM detection on my server. One of the "defeat mechanisms" spammers are using are emails with an innoculous word list in the body (to poison my Bayesian) and an attached image file with the real advertisement for Viagra and Cialis and all that junk.

I'm looking for a (preferably open source) utility for OCR recognition. Basicall, I want an object that I to send it an image file and it returns the text it recognizes in the image.

Does anything like this exist? Please point me to any projects that might give me this ability. Also, curious about your thoughts on this idea ... can this work or will it be too slow to be practical?

Thanks for any help!
 
Aleksandr Grinberg
Greenhorn
Posts: 1
  • Mark post as helpful
  • send pies
  • Quote
  • Report post to moderator
I am also looking for OCR library for java.
If you have found somthing good, just drop me a line .

Thanks a lot !
Aleksandr
[ March 31, 2006: Message edited by: Aleksandr Grinberg ]
 
Ulf Dittmer
Rancher
Posts: 42970
73
  • Mark post as helpful
  • send pies
  • Quote
  • Report post to moderator
OCR is a hard task. I doubt that anything exists as open source.
 
It is sorta covered in the JavaRanch Style Guide.
  • Post Reply Bookmark Topic Watch Topic
  • New Topic
Boost this thread!