Vectorial fractional-order regularizer-based diffeomorphic image registration model and its numerical algorithm

Jin Zhang; Xu Kong; Jianping Zhang; Fenlin Yang; Ke Chen

doi:10.1007/s10851-025-01254-w

Vectorial fractional-order regularizer-based diffeomorphic image registration model and its numerical algorithm

Jin Zhang, Xu Kong, Jianping Zhang, Fenlin Yang, Ke Chen^*

^*Corresponding author for this work

Mathematics And Statistics

Research output: Contribution to journal › Article › peer-review

Abstract

A diffeomorphic image registration model with a vectorial fractional-order regularizer is introduced to handle displacement fields with varying smoothness and to avoid mesh folding. Furthermore, we combine the damped Newton method with the Armijo line search and apply a multilevel strategy to solve the discretized version of the new model. Furthermore, both the existence of solutions to the model and the convergence of the algorithm have been established. Numerical experiments on synthetic and real images confirm the superiority of the proposed model and the effectiveness of the algorithm.

Original language	English
Article number	38
Number of pages	27
Journal	Journal of Mathematical Imaging and Vision
Volume	67
Issue number	4
DOIs	https://doi.org/10.1007/s10851-025-01254-w
Publication status	Published - 13 Jun 2025

Funding

This research work was supported by the Natural Science Foundation of China (NSFC) (No: 11801249, 11771369), and Natural Science Foundation of Shandong Province (No: ZR2024MF143), and the Education Bureau of Hunan Province, P. R. China (No: 22A0119

Keywords

dieomorphic image registration
mesh folding
fractional-order regularizer

Access to Document

10.1007/s10851-025-01254-wLicence: CC BY 4.0

Zhang-etal-JMIV-2025-Vectorial-fractional-order-regularizer-based-diffeomorphic-image-registrationFinal published version, 10.9 MBLicence: CC BY 4.0

Cite this

@article{fef0b8518cc24d89a9e9d40628c4816c,

title = "Vectorial fractional-order regularizer-based diffeomorphic image registration model and its numerical algorithm",

abstract = "A diffeomorphic image registration model with a vectorial fractional-order regularizer is introduced to handle displacement fields with varying smoothness and to avoid mesh folding. Furthermore, we combine the damped Newton method with the Armijo line search and apply a multilevel strategy to solve the discretized version of the new model. Furthermore, both the existence of solutions to the model and the convergence of the algorithm have been established. Numerical experiments on synthetic and real images confirm the superiority of the proposed model and the effectiveness of the algorithm.",

keywords = "dieomorphic image registration, mesh folding, fractional-order regularizer",

author = "Jin Zhang and Xu Kong and Jianping Zhang and Fenlin Yang and Ke Chen",

year = "2025",

month = jun,

day = "13",

doi = "10.1007/s10851-025-01254-w",

language = "English",

volume = "67",

journal = "Journal of Mathematical Imaging and Vision",

issn = "0924-9907",

publisher = "Springer Netherlands",

number = "4",

}

TY - JOUR

T1 - Vectorial fractional-order regularizer-based diffeomorphic image registration model and its numerical algorithm

AU - Zhang, Jin

AU - Kong, Xu

AU - Zhang, Jianping

AU - Yang, Fenlin

AU - Chen, Ke

PY - 2025/6/13

Y1 - 2025/6/13

N2 - A diffeomorphic image registration model with a vectorial fractional-order regularizer is introduced to handle displacement fields with varying smoothness and to avoid mesh folding. Furthermore, we combine the damped Newton method with the Armijo line search and apply a multilevel strategy to solve the discretized version of the new model. Furthermore, both the existence of solutions to the model and the convergence of the algorithm have been established. Numerical experiments on synthetic and real images confirm the superiority of the proposed model and the effectiveness of the algorithm.

AB - A diffeomorphic image registration model with a vectorial fractional-order regularizer is introduced to handle displacement fields with varying smoothness and to avoid mesh folding. Furthermore, we combine the damped Newton method with the Armijo line search and apply a multilevel strategy to solve the discretized version of the new model. Furthermore, both the existence of solutions to the model and the convergence of the algorithm have been established. Numerical experiments on synthetic and real images confirm the superiority of the proposed model and the effectiveness of the algorithm.

KW - dieomorphic image registration

KW - mesh folding

KW - fractional-order regularizer

U2 - 10.1007/s10851-025-01254-w

DO - 10.1007/s10851-025-01254-w

M3 - Article

SN - 0924-9907

VL - 67

JO - Journal of Mathematical Imaging and Vision

JF - Journal of Mathematical Imaging and Vision

IS - 4

M1 - 38

ER -

Vectorial fractional-order regularizer-based diffeomorphic image registration model and its numerical algorithm

Abstract

Funding

Keywords

Access to Document

Fingerprint

Cite this