how can i calculate rmse ?

2 次查看（过去 30 天）
nadia
nadia 2016-6-19
评论： Muhammad Usman Saleem 2016-6-28
Hi, I want to calculate rmse without using for loops between 2 images. this should produce a number not a matrix. can you help me?

请先登录，再回答此问题。

采纳的回答

Image Analyst
Image Analyst 2016-6-26
Use the immse() function in the Image Processing Toolbox.

更多回答（1 个）

Muhammad Usman Saleem
编辑：Muhammad Usman Saleem 2016-6-19
if you upload your images, batter for me to make a code then. Try this prototype
in order to calculate some RMS error for your images, you require two points
(1) YourOrginalimaege
(2) Extimatedimage
YourOrginalimage=imread('imageA.tif');
Extimatedimage=imread('imageB.tif');
Then you can calculate RMS error as
RMS=sqrt(sum(YourOrginalimage (:)-Extimatedimage (:))^2/N) % thanks to John
where N may be total no of samples in YourOrginalimage
Check it and tell me?
  2 个评论
John D'Errico
John D'Errico 2016-6-19
Um, NO!
You need to square those differences before the sum. In your formula, there is no square operation at all.
As importantly, if the image arrays are stored as uint8, the computation you propose will fail completely. Those image values must first be assured to be doubles before any such computation.

请先登录，再进行评论。

类别

在 Help Center 和 File Exchange 中查找有关 Image Processing Toolbox 的更多信息

标签

产品

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by