Re: Features Extraction

Epa Uwimana <[email protected]>
Newsgroups gmane.comp.gnu.gift.general
Message-ID <[email protected]>
Thanks a lot

Epa Uwimana

Quoting David Squire <[email protected]>:

> Epa Uwimana wrote:
> > Hello,
> >  
> > I installed gift on my machine and was able to add my collection
> and
> > indexed them but I am running into some problems to extract
> features.
> > Would someone tell me how I can extract features from a specific
> image
> > using GIFT?
> 
> You can use the program gift-extract-features that is built and
> installed when you install GIFT. It requires a 256x256 PPM image file
> as
> a parameter on the command line. If your image file is, for example,
> 001.gif, you would do:
> 
> >convert -geometry 256x256 001.gif 001.ppm; gift-extract-features
> 001.ppm; rm 001.ppm
> 
> This will create a file 001.fts in the same directory, that includes
> the
> extracted features.
> 
> > What would be steps to follow for anybody who wants to use GIFT to
> indexing and features extraction only?
> 
> The gift-add-collection.pl program extracts features and builds the
> index files for all the images in a directory. If you just want to
> extract features and index using those GIFT components, that is what
> you
> need to use, just as if you were going to use the gift query engine
> as well.
> 
> You will need to dig in the source code to understand the format of
> the
> feature and index files.
> 
> > Any idea where I can find a new README?
> 
> There isn't one.
> 
> Regards,
> 
> David
> 
> -- 
> Dr. David McG. Squire, Senior Lecturer. On sabbatical in 2006.
> Caulfield School of Information Technology, Monash University,
> Australia
> CRICOS Provider No. 00008C      
> http://www.csse.monash.edu.au/~davids/
> 
> 
> 
> _______________________________________________
> help-GIFT mailing list
> [email protected]
> http://lists.gnu.org/mailman/listinfo/help-gift
> 
>
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.