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

Revisiting image features

Image gradients and edges give us a lot of information about the shapes of different objects in the image. Using edges, we might also be able to determine the orientation of the objects in the image sometimes. But these are weak features and cannot be relied upon all the time. They are very sensitive to variations in brightness, contrast, and backgrounds. We need features that are more stable than just gradients or edges. To solve this problem, we use more sophisticated feature descriptors such as corners, Local Binary Pattern (LBP), BRISK, and Oriented FAST and Rotated BRIEF. Let's understand what is different in these feature descriptors that makes them better than using just edges and image gradients.

To call ...

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