# registration metric for rgb image
**URL:** https://discourse.itk.org/t/registration-metric-for-rgb-image/2439
**Category:** Uncategorized
**Created:** [November 25, 2019, 4:22pm UTC](https://discourse.itk.org/t/registration-metric-for-rgb-image/2439 "2019-11-25T16:22:59Z")
**Posts on this page:** 5
**Page:** 1
### Author:  [@kayarre](https://discourse.itk.org/u/kayarre)
#### Post date: [November 25, 2019, 4:22pm UTC](https://discourse.itk.org/t/registration-metric-for-rgb-image/2439/1 "2019-11-25T16:22:59Z")
How can you evaluate a registration metric for an rgb image.
the way I have done is by decomposing each channel and evaluating each one, but then I have three different metric values.
how are those three metrics related to each other? should I sum them, root sum squared, can they be combined in a meaningful way to describe how well the fixed and moving image match each other.
---
### Author:  [@dzenanz](https://discourse.itk.org/u/dzenanz)
#### Post date: [November 25, 2019, 5:02pm UTC](https://discourse.itk.org/t/registration-metric-for-rgb-image/2439/2 "2019-11-25T17:02:17Z")
RMSE is a fine choice, [already made](https://www.cbica.upenn.edu/sbia/papers/28.pdf) by somebody in a different contex.
---
### Author:  [@matt.mccormick](https://discourse.itk.org/u/matt.mccormick)
#### Post date: [November 25, 2019, 7:20pm UTC](https://discourse.itk.org/t/registration-metric-for-rgb-image/2439/3 "2019-11-25T19:20:13Z")
Elastix [provides a multi-component metric](http://elastix.isi.uu.nl/download/elastix-5.0.0-manual.pdf) for \alpha-mutual information based on joint histograms.
---
### Author:  [@kayarre](https://discourse.itk.org/u/kayarre)
#### Post date: [November 26, 2019, 4:01pm UTC](https://discourse.itk.org/t/registration-metric-for-rgb-image/2439/4 "2019-11-26T16:01:44Z")
@matt.mccormick
Do you know of an example of doing this with simpleelastix?
---
### Author:  [@matt.mccormick](https://discourse.itk.org/u/matt.mccormick)
#### Post date: [December 2, 2019, 7:40pm UTC](https://discourse.itk.org/t/registration-metric-for-rgb-image/2439/5 "2019-12-02T19:40:27Z")
I have been using the [ITKElastix](https://github.com/InsightSoftwareConsortium/ITKElastix) interfaces. The feature is currently disabled in the binary Python packages due to license and packaging challenges of the ANN library.
But, It could be built locally by enabling the `USE_KNNGraphAlphaMutualInformationMetric` CMake option. Or, it may be available in the [`elastix` command line executable](https://github.com/SuperElastix/elastix/releases).