Ransac

RANSAC, short for Random Sample Consensus, is an iterative algorithm used for robust fitting of models in the presence of many outliers in a dataset. It works by randomly selecting subsets of the data, fitting a model to each subset, and then evaluating how many data points fit the model within a given tolerance. The algorithm then repeats this process multiple times and selects the model with the highest number of inliers (data points that fit well).

Ransac algorithm can be found here Ranasc