# Precalculate the Normalization of a filter size

If we have an Image I and a Gabor filter created at specific size and orientation, assume that is 11x11.

I saw some persons who normalize the size of the filter, but i didn't understand what was meant by "precalculate the normalization of the filter size". And within the normalization, they square the image, for example : Isquare = I^2. So why the image is squared ?

Each pixel of the filter has a magnitude (intensity). The square function equivalently calculate the power density of the pixel. The normalization is to scale the filter power to 1. That's where I^2 at the denominator comes from.
Normally, ,,normalization'' means to make the L2 norm (sum of squares) of a signal $1$. This is usually achieved by calculating the inverse of the sum of squares and multiplying by it.