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

Algorithm behind SIFT

The main motivation behind SIFT is to extract local features from an image that is robust. To achieve this, the algorithm is divided into the following four main stages:

  • Scale-space extrema detection
  • Keypoint localization
  • Orientation assignment
  • Keypoint descriptor

If you carefully read Chapter 3, Drilling Deeper into Features-Object Detection, you will realize that this sounds very similar to the ORB algorithm (SIFT was proposed before ORB). The takeaway from this point is that most of the feature-detection algorithms have the same motivation to extract robust features and hence they have a very similar approach. All the algorithms do something unique in each of these stages, which differentiates them from each other ...

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