0

I want to ask about image preprocessing for classification tasks with cnn. I standardized the input data (mean = 0, standard deviation = 1), I got results with a range of [-1.1]. How to use that technique with result range [0,1]? so that the image can be visualized.

hilyap
  • 1
  • 2

1 Answers1

0

Also known as min-max scaling or min-max normalization, it is the simplest method and consists of rescaling the range of features to scale the range in [0, 1]. The general formula for normalization is given as:

enter image description here

Here, max(x) and min(x) are the maximum and the minimum values of the feature respectively.

We can also do a normalization over different intervals, e.g. choosing to have the variable laying in any [a, b] interval, a and b being real numbers. To rescale a range between an arbitrary set of values [a, b], the formula becomes:

enter image description here

Ikram Ul Haq
  • 76
  • 5
  • thanks for the answer, but can we normalize input data that has gone through standardization? I mean, in the pixel image we have a range of [0,255] then we standardize (mean=0, std=1) to [-1.1] then we normalize again to [0,1]? I do this because there is a paper that says that "learning in CNNs proceeds best when the inputs are standardized (i.e. mean zero, and unit variance)" – hilyap Dec 07 '21 at 08:41