8

I recently stumbled upon a SIFT implementation for C#. I thought it would be great fun to play around with it, so that's what I did.

The implementation generates a set of "interest points" for any given image. How would I actually use this information to compare two images?

What I'm after is a single "value of similarity". Can that be generated out of the two sets of interest points of the two images?

Mar de Romos
  • 719
  • 2
  • 9
  • 22
Boris
  • 8,551
  • 25
  • 67
  • 120

2 Answers2

7

You need to run SIFT on both images so you get interest points (lets call them Keypoints) in both images.

After that you need to find matches between keypoints in both images. There are algorithms implemented for that purpose in OpenCV.

The value of similarity can be computed out of the number of matches. You can consider that if you get more than 4 points the images are the same, and you can also calculate the relative rotation between them.

Jav_Rock
  • 22,059
  • 20
  • 123
  • 164
  • 1
    Keep in mind that the number of features/matches is also dependent on irrelevant qualities from the source images. Instead of simply counting the *number* of matches, it might be better to calculate the *percentage* of features that were matched. – rinogo Jul 09 '20 at 19:09
  • (Obviously, ymmv - it depends a lot on what your data set looks like!) – rinogo Jul 09 '20 at 19:10
0

You can use number of matches as similarity metric.

mrgloom
  • 20,061
  • 36
  • 171
  • 301