Content deleted Content added
Mauromaiorca (talk | contribs) No edit summary |
Mauromaiorca (talk | contribs) fixed the formula for non-linear normalization |
||
Line 23:
Normalization might also be non linear, this happens when there isn't a [[linear]] relationship between <math>I</math> and <math>I_N</math>. An example of non-linear normalization is when the normalization follows a [[sigmoid function]], in that case, the normalized image is computed according to the formula
:<math>I_N=(\text{newMax}-\text{newMin})\frac{1}{1+e^{-\frac{I-\beta}{\alpha}}}+\text{newMin}</math>
Where <math>\alpha</math> defines the width of the input intensity range, and <math>\beta</math> defines the intensity around which the range is centered <ref>[http://www.itk.org/ItkSoftwareGuide.pdf ITK Software Guide]</ref>. <br />
| |||