O'Reilly logo

Computer Vision with Python 3 by Saurabh Kapur

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Keypoint descriptor

Until now, we have achieved scale and rotation invariance. We now need to create a descriptor for various keypoints so as to be able to differentiate them from the other keypoints. To generate a descriptor, we take a 16 x 16 window around the keypoint and break it into 16 windows of size 4 x 4. This can be seen in the following figure:

Figure 7: Image showing how the descriptor is computed

We do this in order to incorporate the fact that objects in two images are rarely never exactly the same. Hence, we try to lose some precision in our calculations. Within each 4 x 4 window, gradient magnitudes and orientations are calculated. ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required