Parent Topic: Improving Performance
Reducing CPU Usage
When considering which resampling technique to use, it is important to realize that Cubic Convolution can take substantially more computation effort than Bilinear, or Nearest Neighbour resampling. On today's fast workstations, this is less of a factor than it once was; however, if you believe that your registration time is being limited by the required amount of computation (CPU usage), switching from Cubic Convolution to another resampling method will speed things up.

Another factor affecting CPU usage is the order of the polynomial used to perform the geometric warping. The polynomials have to be evaluated for each pixel in the output image. High order polynomials require substantially more operations to compute than low order polynomials.


Parent Topic: Improving Performance
About PCI Help Gateway