DeepAI AI Chat
Log In Sign Up

Dependent landmark drift: robust point set registration based on the Gaussian mixture model with a statistical shape model

by   Osamu Hirose, et al.
Kanazawa University

Point set registration is to find point-by-point correspondences between point sets, each of which characterizes the shape of an object. Due to the assumption of the local preservation of object geometry, prevalent algorithms in the area can often elegantly solve the problems without using geometric information specific to the objects. This means that registration performance can be further improved by using the prior knowledge of object geometry. In this paper, we propose a novel point set registration method using the Gaussian mixture model with prior shape information encoded as a statistical shape model. Our transformation model is defined as the combination of the rigid transformation, the motion coherence, and the statistical shape model. Therefore, the proposed method works effectively if the target point set includes outliers and missing regions, or if it is rotated. The computational cost can be reduced to linear and thereby the method is scalable to large point sets. The effectiveness of the method will be verified through comparisons with existing algorithms using datasets concerning human hands and faces.


page 1

page 2

page 3

page 4


The Coherent Point Drift for Clustered Point Sets

The problem of non-rigid point set registration is a key problem for man...

Laplacian Mixture Model Point Based Registration

Point base registration is an important part in many machine VISIOn appl...

Rigid and Articulated Point Registration with Expectation Conditional Maximization

This paper addresses the issue of matching rigid and articulated shapes ...

Robust Feature-Based Point Registration Using Directional Mixture Model

This paper presents a robust probabilistic point registration method for...

Novel Co-variant Feature Point Matching Based on Gaussian Mixture Model

The feature frame is a key idea of feature matching problem between two ...

Reworking geometric morphometrics into a methodology of transformation grids

Today's typical application of geometric morphometrics to a quantitative...

Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration

Given two point sets, the problem of registration is to recover a transf...