Point Pattern Matching based on point pair local nonuniform ODT and Spectral Matching

Abstract

This article proposes a novel and robust point Pattern Matching Algorithm (PPM) which combines the invariant feature and Spectral Matching (SM). A new point-set based invariant feature, point pair local nonuniform ODT (Orientation and Distance Based Topology), is presented firstly. The matching measurement of point pair local nonuniform ODT descriptor's statistic test is used to define new compatibility coefficients. Then on basis of the gained compatibility measurement, we can construct a matching graph and its affinity matrix. Finally, the correct matching results are achieved using the main eigenvector of affinity matrix of assignment graph and the mapping constraint conditions. Convictive experimental results on both synthetic point-sets and real world data indicate that the proposed algorithm is robust to outliers and noise. In addition, it performs better in the presence of similarity or even perspective transformation among point sets in the meantime comparing with the other state-of-art algorithms.