Cascade Classifier Preprocessing Question

edit

Hello Open CV Community,

When the current sliding window (e.g. 50x50) has twice the size of the training data samples (e.g. 25x25), how does the Cascade Classifier predict it???

I thought of two possible solutions, but i dont know which on is correct:

A: The image from the sliding window is resized to the format of the training data samples.

or

B: It doesn't matter because the feature calculation is format independent?

This question is for the purpose of understanding the Cascade Classifier process. I hope somebody can help.

Thank you very much,

Derrick