normalized euclidean Distance between 2 points in an image

Mahalanobis

asked 2015-07-29 02:04:39 -0600

Nbb
731 ●12 ●23 ●38

Hello forum,

When attempting to find the distance stated above, would it be better to use the bhattacharrya distance or the mahalanobis distance ?

The mahalanobis function requires an input of the covariance matrix. Based on wikipedia it says the matrix should be diagonal for the function to be equal to the normalized euclidean distance. I am not sure how to get that diagonal covariance matrix from 2 points in an image.

edit retag flag offensive close merge delete

add a comment

1 answer

Sort by » oldest newest most voted

answered 2015-07-29 02:52:31 -0600

StevenPuttemans

20029 ●16 ●82 ●207 http://stevenputtemans...

You can simply use the norm interface of OpenCV to do it for you right? Some more info can be found here and here.

edit flag offensive delete link

Comments

Sorry, what I meant was I would like the value to be between 0 to 1

Nbb ( 2015-07-29 04:35:31 -0600 )edit

So once you got the distance measure, you want a value between 0 1? Then you will first have to decide what your maximum distance value will be for your application in order to have a correct remapping.