Re: PCA - What next!?

There are many available techniques for face recognition, which can be
found in the face recognition homepage:
www.face-rec.org

The simplest and best approach is PCA or eigenfaces approach, which
can be used either to recognize, or to reduce the dimensionality.

To recognize using the weights, you can use euclidean distance,
Correlation distance, covariance distance, and many other distances
available.

TO save the bounding rectangle of a face, you have to set the Image
Region of Interest(ROI) and save the image.
After saving, reset the ROI.

Regards, :D
Paramesh.

--- In OpenCV@xxxxxxxxxxxxxxx, "kirkl_tamworth" <kirkl_tamworth@...>
wrote:
>
> Hi all,
> 
> I have successfully compiled the PCA example provided in the files 
> section, which outputs the eigenvalues and such. I have two queries:
> 
> 1. Can you help me with where I go from here to perform face-
> recognition? I have 25 face images ready to use and would greatly 
> appreciate some help with completing the Eigenface approach. 
> 
> 2. I have also managed to incorporate the face detection sample into a 
> C# application, but I'm not sure how to extract the face from the 
> image, given that I know the bounding rectangle. Is there an OpenCV 
> function that can do this for me?
> 
> My first query is much more important than the second and I would 
> really, really appreciate some help with this. Thanks.
> 
> Kirk
>






Change settings: http://www.yahoogroups.com/mygroups, select
   Get Emails (get all posts)
   Daily Digest (one summary email per day)
   Read on the web (read posts on the web only)Or Unsubscribe by mailing 
OpenCV-unsubscribe@xxxxxxxxxxxxxxx