Optimization over Random and Gradient Probabilistic Pixel Sampling for Fast, Robust Multi-Resolution Image Registration

TL;DR

This paper introduces a probabilistic pixel sampling method that combines gradient-based and random sampling, optimized via particle swarm to improve the speed and robustness of 3D image registration.

Contribution

It proposes a novel learning-based scheme to optimally balance two sampling strategies for fast, accurate, and robust multi-resolution image registration.

Findings

Faster registration compared to state-of-the-art methods

More accurate registration results

Enhanced robustness in 3D rigid registration

Abstract

This paper presents an approach to fast image registration through probabilistic pixel sampling. We propose a practical scheme to leverage the benefits of two state-of-the-art pixel sampling approaches: gradient magnitude based pixel sampling and uniformly random sampling. Our framework involves learning the optimal balance between the two sampling schemes off-line during training, based on a small training dataset, using particle swarm optimization. We then test the proposed sampling approach on 3D rigid registration against two state-of-the-art approaches based on the popular, publicly available, Vanderbilt RIRE dataset. Our results indicate that the proposed sampling approach yields much faster, accurate and robust registration results when compared against the state-of-the-art.