Bag-of-words demonstration
From Chorus
Revision as of 10:35, 10 January 2011 by Cimpaniulia (Talk | contribs)
| Domain | Visual Feature Extraction |
| Media | |
| Task | |
| Creation Date | |
| Copyright | The code is for teaching/research purposes only. |
| URL | http://people.csail.mit.edu/fergus/iccv2005/bagwords.html |
Description
A simple approach to classifying images is to treat them as a collection of regions, describing only their appearance and igorning their spatial structure. Similar models have been successfully used in the text community for analyzing documents and are known as "bag-of-words" models, since each document is represented by a distribution over fixed vocabulary(s). Using such a representation, methods such as probabalistic latent semantic analysis (pLSA) and latent dirichlet allocation (LDA) are able to extract coherent topics within document collections in an unsupervised manner.
Copyright Remarks
The code is for teaching/research purposes only.
