Median K-flats Algorithm(MKF)

Brief Introduction
MKF is a simple online algorithm for hybrid linear modeling, i.e., for approximating data by a mixture of linear subspaces. The algorithm partitions the data into clusters to minimize the average l1 error by a gradient descent method.
Paper
Median K-Flats for Hybrid Linear Modeling with Many Outliers

Matlab codes


Supplemental Data
  1. Artificial data: generated by using 'generate_samples.m' which is contained in the GPCA-voting folder
  2. Real data: Motion Segmentation (http://www.vision.jhu.edu/data/hopkins155/)
Contact Info: