Non-rigid point set registration method based on enhanced affine transformation

Abstract

The invention discloses a non-rigid point set registration method based on enhanced affine transformation, belongs to the technical field of image processing, and relates to a point set registration method. According to the present invention, the problem that an existing point set registration method is low in registration precision and poor in robustness due to the local convergence of a registration precision objective function, is solved. According to the method, the rough registration is completed by utilizing a global non-rigid transformation model capable of representing a global deformation rule, and then a rough registration result is finely optimized by utilizing a local non-rigid transformation model, so that the point matching is realized. The method comprises the following steps of firstly, constructing a global non-rigid transformation model by utilizing enhanced affine transformation based on a nonlinear polynomial, and overcoming a local convergence problem in a gradientoptimization process in combination with a registration precision objective function based on a Gaussian field to realize coarse registration; and then taking a coarse registration result as an initial value, and performing fine optimization on the objective function by using a local non-rigid transformation model to realize the final point set registration.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a non-rigid point set registration method based on enhanced affine transformation. Background technique [0002] Point set registration is a key fundamental research problem in many computer vision applications, such as pattern recognition, medical image analysis, image fusion, and binocular stereo vision. Point set registration aims to find correspondences between point sets and derive spatial transformations that can change the shape of one point set to conform to another. [0003] In order to obtain high-precision registration results, researchers have proposed many methods, which can be mainly divided into two categories: rigid registration and non-rigid registration. Rigid registration only includes three transformations: translation, scaling and rotation. Since its implementation is relatively simple, there are many researches and applications on it. On the basis o...

AI Technical Summary

Problems solved by technology

[0004] At present, in most non-rigid point set registration methods, point set registration is often converted into an objective function optimization problem, and the spatial transformation model used is based on the cognition that the non-rigid deformation of each point is independent of each other. , so it is often affected by local convergence, resulting in the inability to obtain the optimal registration effect

Images