Background Dataset for Training

[tamirru]

Hello,
I have prepared the dataset for my classification, but how should I handle the background class? Do I have to create a random set of background dataset? and why is it necessary? is it just acting as negative images?

Thank you,

[hayderm]

You can prepare background windows by using UoI. if UoI less than 0.5 then you can consider them as background windows.

It is necessary because some of proposals will be discarded as negative windows during test phase.