In this recipe, you will learn how to robustly filter matches between keypoints in two images using the Random Sample Consensus (RANSAC) algorithm under the assumption that there's a homography transformation between the two images. This technique helps filter out bad matches and only leaves the ones that satisfy the motion model between two images.
Model-based filtering of matches - RANSAC
Getting ready
Before you proceed with this recipe, you need to install the OpenCV version 3.3 (or greater) Python API package.
How to do it...
You need to complete the following...