Re: efficient window based computation

Try these papers ....

1. If you are doing cross-correlation based matching, you can use 
integral image.
Paper: "Fast Normalized Cross-Correlation"


2. If you are computing hitogram-based feature matching, try 
Paper: "Integral Histogram: A Fast Way to Extract Histograms in 
Cartesian space"


3. If you have other projection filtes for matching, try
Paper: "Real-Time Pattern Matching Using Projection Kernels" 
Paper: "Non-orthogonal binary subspace and its applications in computer 
vision"
(you may also want to see: "Over-Complete Wavelet Approximation of a 
Support Vector Machine for Efficient Classification" )


There are also some other fast computation of gabor filtering, gaussian 
filtering, etc ... for matching based on extracted features


--- In OpenCV@xxxxxxxxxxxxxxx, "maverick990557" <maverick990557@xxxx> 
wrote:
>
> Can anyone help me with this. I am looking for a very efficient way to
> perform window based matching. I have to pick a window (of say WxW)
> around each pixel and then compute some image statistics. I am looking
> for some efficient data structure or function or some look up table
> approach, other than the dirty way of going through each pixel and
> picking a window around it. 
> 
> Thanks
>






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