# FFT Correlation: Normalized Sum of Square Difference

**URL:** https://discourse.itk.org/t/fft-correlation-normalized-sum-of-square-difference/5827
**Category:** Algorithms
**Tags:** cpp, simpleitk
**Created:** [March 23, 2023, 2:40pm UTC](https://discourse.itk.org/t/fft-correlation-normalized-sum-of-square-difference/5827 "2023-03-23T14:40:54Z")
**Posts on this page:** 2
**Page:** 1

<div class="post-metadata">

### Author: ![elapins](https://discourse.itk.org/letter_avatar_proxy/v4/letter/e/96bed5/32.png) [@elapins](https://discourse.itk.org/u/elapins)
#### Post date: [March 23, 2023, 2:40pm UTC](https://discourse.itk.org/t/fft-correlation-normalized-sum-of-square-difference/5827/1 "2023-03-23T14:40:54Z")

</div>

Hello,

I am wondering if it would be possible to extend the FFTNormalizedCrossCorrelation function to use Normalized Sum of Square Differences instead of Cross Correlation metric?

Thank you!

---

<div class="post-metadata">

### Author: ![matt.mccormick](https://discourse.itk.org/user_avatar/discourse.itk.org/matt.mccormick/32/7_2.png) [@matt.mccormick](https://discourse.itk.org/u/matt.mccormick)
#### Post date: [March 24, 2023, 4:06pm UTC](https://discourse.itk.org/t/fft-correlation-normalized-sum-of-square-difference/5827/2 "2023-03-24T16:06:45Z")

</div>

Hi Elana,

Mathematical FFT properties are utilized in the normalized cross correlation function. These properties do not apply to sum-of-squared differences.

HTH,  
Matt