
www.Usenet.com
| <-- __Chronological__ --> | <-- __Thread__ --> |
Hi, Brian, Thanks a lot for answering my(ours) post... > Are you trying to separate the girl from the background? What's the > goal that you're trying to accomplish with this segmentation? And why > did you scale up the image? Yeah, I originally want to do some processing which I did not know myself(magically?)...and see the results... but after reading your answer, I guess I will also try "K-means classification"... and I can classify "homogeous" and "non-homogeneous" pixels... > Another thing you might want to look at is feature clustering methods, > such as described by the Fuzzy C-Means algorithm. This algorithm does > a very good job defining clusters given several sets of feature > vectors. Another approach is called K-Means clustering. Again, there > are many papers on-line that you can find just by searching, but > here's a link to some Fuzzy-C code that you might find useful... > > http://homepage.ntlworld.com/paul.mather/book.html > This is a great resouce! I guess the FAQ editor should put this resource into FAQ and mark it! I immediately bookmarked it and will borrow the book soon... the only little pity is that the codes are in C... having been a C programmer for over 15 years I am now quite tired about C... whenever you implement an idea, much more work is devoted into debugging... If there are matlab codes, there will be even better! Anyway, it is already very great! and I will get the book to read! Thank you very much, Brian! -Walala
| <-- __Chronological__ --> | <-- __Thread__ --> |