Point registration algorithm capable of keeping local topology invariance

Abstract

The invention discloses a point registration algorithm capable of keeping local topology invariance. The point registration algorithm comprises the following steps: converting the point registration problem into an image matching problem, wherein points in a point set serve as nodes in an image; defining a neighbourhood region of each node in the image, wherein the node and the neighbourhood region thereof form a local subgraph, the node and one point in the neighbourhood region thereof are connected to form one edge in the local subgraph; carrying out dynamic planning on the local subgraphs to obtain matching probability between the local subgraphs; carrying out processing on global matching probability through the matching probability between the local subgraphs and a relaxation labeling method to obtain correspondence relation of point pairs; and according to the correspondence relation of the point pairs, carrying out elastic deformation regularization processing on the point set through a thin plate spline function to obtain model parameters. The point registration algorithm capable of keeping local topology invariance accurately quantizes local topology difference, improves accuracy of non-rigid registration when large deformation occurs and improves algorithm robustness when an abnormity point exists.

Description

[0001] technology neighborhood [0002] The invention relates to a point registration algorithm keeping local topological invariance. Background technique [0003] Image registration technology is a very important research topic in the field of computer vision and image processing, and has been successfully applied in many important fields such as pattern recognition, medical image processing and digital media; especially at present, virtual reality and augmented reality Gradually stepping out of the laboratory and coming into the lives of the people will soon become the next economic growth point. The registration algorithm is the core key algorithm for the successful application of this technology. According to the registration object, it can be divided into gray-scale registration algorithm and point registration algorithm; among them, the point registration algorithm can not only effectively reduce the complexity of the algorithm, but also take into account the accuracy o...

AI Technical Summary

Problems solved by technology

[0009] However, when calculating the point neighbor relationship, the matching probabilities between all neighboring points are counted, which contains a lot of redundant information; Lee et al. used the label relaxation method, and quantified the relationship between point pairs through discrete angle and radius differences. Matching correlation; but when comparing the topological differences between points and their neighborhoods, a one-to-many method is also used to statistically calculate the similarity probability; this type of method ignores the prior probability between local matching points, that is, in When calculating the local similarity, the similarity probability between local point pairs is ignored, and the correspondence between a neighborhood point is not established, thus reducing the accuracy of registration

Images