Root mean square error (RMS error)

RMSerror

asked 2017-08-24 08:06:51 -0600

Kumar123
6 ●3

I am trying to calculate the RMS error between the two images (chess board). One is real and another is warped virtual image. In order to do it I have pointed 4 fixed corner points on two images separately. So now I have x,y coordinates values for all 8 Points from two different images. In order to calculate the RMS error which value I should take x or y . Or is there any procedure to combined the both values and use the formula.

Please kindly help me to solve this issue.

Thanks in advance.

edit retag flag offensive close merge delete

add a comment

1 answer

Sort by » oldest newest most voted

answered 2017-08-25 00:56:34 -0600

Ziri
292 ●4 ●7

updated 2017-08-25 01:59:04 -0600

Use both x and y coordinates , loop over your points and use this formula :

MEAN_X += pow(x - x0, 2);
MEAN_Y += pow(y - y0, 2);

TOTAL_RMS =  sqrt( 1/n * (MEAN_X + MEAN_Y));

x , y : coordinates from image2

x0 , y0: coordinates from image1

n : number of points

edit flag offensive delete link

Comments

Thank you so much for the reply. Very helpful.

Kumar123 ( 2017-08-25 02:10:40 -0600 )edit

add a comment

Links

Question Tools

1 follower

Stats

Asked: 2017-08-24 08:06:51 -0600

Seen: 3,630 times

Last updated: Aug 25 '17

Copyright OpenCV foundation, 2012-2018. Content on this site is licensed under a Creative Commons Attribution Share Alike 3.0 license.

here is how

Root mean square error (RMS error) edit