Scale-invariant feature transform
Posts  1 - 1  of  1
PTania
The 2nd step of SIFT talks about keypoint localization.
We have to calcolate the Hessian Matrix and we know that the eigenvalues of H are proportional to the principal curvatures of D.
But what does it means? What are the curvatures and what is their correspondence in a image?
Help me! Thanks all
Save
Cancel
Reply
 
x
OK