An Efficient Approximation Algorithm for Point Pattern Matching Under Noise

TL;DR

This paper presents a new efficient approximation algorithm for point pattern matching under noise, improving speed and accuracy for large matched sets in 3D point sets, with applications in vision and bioinformatics.

Contribution

Introduces a new deterministic 4-distance-approximation algorithm for tolerant-LCP, improves existing algorithms for exact-LCP, and employs expander graphs to enhance performance under large matched set requirements.

Findings

Fastest known deterministic 4-approximation algorithm for tolerant-LCP.

Improved running times for large matched sets in exact-LCP.

Expander graphs used to speed up algorithms with some approximation in matched set size.

Abstract

Point pattern matching problems are of fundamental importance in various areas including computer vision and structural bioinformatics. In this paper, we study one of the more general problems, known as LCP (largest common point set problem): Let $\PP$ and $\QQ$ be two point sets in $\mathbb{R}^3$, and let $\epsilon \geq 0$ be a tolerance parameter, the problem is to find a rigid motion $\mu$ that maximizes the cardinality of subset $\II$ of $Q$, such that the Hausdorff distance $\distance(\PP,\mu(\II)) \leq \epsilon$. We denote the size of the optimal solution to the above problem by $\LCP(P,Q)$. The problem is called exact-LCP for $\epsilon=0$, and \tolerant-LCP when $\epsilon>0$ and the minimum interpoint distance is greater than $2\epsilon$. A $\beta$-distance-approximation algorithm for tolerant-LCP finds a subset $I \subseteq \QQ$ such that $|I|\geq \LCP(P,Q)$ and $\distance(\PP,\mu(\II)) \leq \beta \epsilon$ for some $\beta \ge 1$. This paper has three main contributions. (1) We introduce a new algorithm, called {\DA}, which gives the fastest known deterministic 4-distance-approximation algorithm for \tolerant-LCP. (2) For the exact-LCP, when the matched set is required to be large, we give a simple sampling strategy that improves the running times of all known deterministic algorithms, yielding the fastest known deterministic algorithm for this problem. (3) We use expander graphs to speed-up the \DA algorithm for \tolerant-LCP when the size of the matched set is required to be large, at the expense of approximation in the matched set size. Our algorithms also work when the transformation $\mu$ is allowed to be scaling transformation.