On Mon, June 12, 2006 9:32, Tony Meyer said: > [Tim Stone, regarding classifying image-based spam] >> As the Open Source adage goes... you itch, you scratch <wink> Who >> itches enough to implement this? IIRC, we had a long discussion about >> this a long time ago, and decided that if enough image spam were being >> misclassified, we might take a look at it this idea. I don't have >> enough misclassifications to give me an irresistable itch.... > > FWIW, I'm both itching and scratching. I haven't bothered spambayes- > dev with posts about my failed ideas (I will post when there's > something I think is worth testing by others), but if there are > others who are interested in working on this at the moment, please > speak up and I'll be more vocal about the failures. > > (I am documenting the failures, and will put that somewhere at some > point).
As another Open Source adage goes... do only one thing, and do that thing perfectly. Please don't overload spambayes with ocr capabilities or other kitchensinks. All spambayes should do (imho) is tokenize an email, and give a score to each token. What I think *might* be an interesting approach, is chaining different software together. But only for those extremely rare cases when spambayes doesn't get enough information from the headers. It's an interesting thought experiment - but ony that: a thought experiment. After several months of using spambayes I don't feel any itch at all... -- Amedee _______________________________________________ [email protected] http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html
