Posts /

SIFT Theory and Practice

Twitter Facebook
08 Apr 2017

Matching features across different images in a common problem in computer vision. When all images are similar in nature (same scale, orientation, etc) simple corner detectors can work. But when you have images of different scales and rotations, you need to use the SIFT(Scale Invariant Feature Transform).

SIFT is the below invariant:

After applying SIFT:

The big rectangles mark matched images. The smaller squares are for individual features in those regions. Note how the big rectangles are skewed. They follow the orientation and perspective of the object in the scene.

So, as you can see, that’s some real robust image matching going on.


Twitter Facebook