Multimodal image registration using Laplacian commutators

Abstract

The fusion and combination of images from multiple modalities is important in many applications. Typically, this process consists of the alignment of the images and the combination of the complementary information. In this work, we focused on the former part and propose a multimodal image distance measure based on the commutativity of graph Laplacians. The eigenvectors of the image graph Laplacian, and thus the graph Laplacian itself, capture the intrinsic structure of the image's modality. Using Laplacian commutativity as a criterion of image structure preservation, we adapt the problem of finding the closest commuting operators to multimodal image registration. Hence, by using the relation between simultaneous diagonalization and commutativity of matrices, we compare multimodal image structures by means of the commutativity of their graph Laplacians. In this way, we avoid spectrum reordering schemes or additional manifold alignment steps which are necessary to ensure the comparability of eigenspaces across modalities. We show on synthetic and real datasets that this approach is applicable to dense rigid and non-rigid image registration. Results demonstrated that the proposed measure is able to deal with very challenging multimodal datasets and compares favorably to normalized mutual information, a de facto similarity measure for multimodal image registration.

Deformable MRI-Ultrasound registration using correlation-based attribute matching for brain shift correction: Accuracy and generality in multi-site data

“…Dilation margin r in the proposed "rigid+masking+deformable" transformation strategy. We vary r from 1mm to 6mm to compensate for any registration errors that may arise from rigid registration, which, as experiments show, are typically less than 6mm (Zimmer, González Ballester, & Piella, 2019).…”

An Infrared-Visible Image Registration Method Based on the Constrained Point Feature

“…This technique is widely applied in the fields of medical diagnosis [ 2 , 3 ], remote sensing image processing [ 4 , 5 ], and surveillance [ 6 , 7 ]. Image registration is an essential step to ensure fusion operation, which aligns two or more images from different times, sensors, and views by finding a credible spatial transformation [ 8 ]. However, due to the complementary information and different imaging principles of multi-sensor images, the mutual information of infrared and visible images is less [ 9 ].…”

Non-Rigid Registration via Global to Local Transformation

“…Multi-sensor image registration is a prerequisite for image fusion. Therefore, it has always been a research hotspot [5][6][7][8][9][10].…”

“…Thus, multi-sensor image registration, which is very critical for fusion, is still a challenging task. One of the solutions is to transform image registration into point set registration, and then estimate spatial transformation model from point feature [5,11]. This paper focuses on point set registration to achieve IR and VIS image registration.…”