The Path Assigned Mean Shift Algorithm: A New fast Mean Shift Implementation For Colour Image Segmentation.

Abstract

This paper presents a novel method for colour image segmentationderived from the mean shift theorem. When appliedto colour image segmentation tasks, the path assigned meanshift algorithm performed 1.5 to 5 times faster than existingfast mean shift methods such as the Hierarchical ?NeighbourhoodConsistency? FMS Method proposed by Zhang [1] withcomparable results. The complexity of the new PAMS algorithmcan be represented as O(2) where represents the totalnumber of unassigned points per iteration of the algorithm.