Revision history [back]

Hello Open CV Community,

Situation: The Cascade Classifier Detection uses a sliding window of different sizes (image pyramid). The CC is trained with 20x20 px images and the current frame of the sliding window has the size of 50x50.

Does the CC resize the current sliding window frame to the trained size (20x20 pixel) and detect it afterwards or does the CC detection process doesn't care about the image size? (maybe because the features are using average values)

This question is for the purpose of understanding the Cascade Classifier process.

Thank you very much,

Derrick

Hello Open CV Community,

Situation: The Cascade Classifier Detection uses a When the current sliding window of different sizes (image pyramid). The CC is trained with 20x20 px images and the current frame of the sliding window (e.g. 50x50) has twice the size of 50x50.the training data samples (e.g. 25x25), how does the Cascade Classifier predict it???

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

A: The image from the CC resize the current sliding window frame is resized to the trained size (20x20 pixel) and detect it afterwards or does format of the CC detection process training data samples.

or

B: It doesn't care about the image size? (maybe matter because the features are using average values)feature calculation is format independent?

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

Thank you very much,

Derrick