The steerable graph Laplacian and its application to filtering image datasets

Boris Landa*, Yoel Shkolnisky

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

11 Scopus citations

Abstract

In recent years, improvements in various image acquisition techniques gave rise to the need for adaptive processing methods, aimed particularly for large datasets corrupted by noise and deformations. In this work, we consider datasets of images sampled from a low-dimensional manifold (i.e., an image-valued manifold), where the images can assume arbitrary planar rotations. To derive an adaptive and rotation-invariant framework for processing such datasets, we introduce a graph Laplacian (GL)-like operator over the dataset, termed a steerable graph Laplacian. Essentially, the steerable GL extends the standard GL by accounting for all (infinitely many) planar rotations of all images. As it turns out, similarly to the standard GL, a properly normalized steerable GL converges to the Laplace--Beltrami operator on the low-dimensional manifold. However, the steerable GL admits an improved convergence rate compared to the GL, where the improved convergence behaves as if the intrinsic dimension of the underlying manifold is lower by one. Moreover, it is shown that the steerable GL admits eigenfunctions of the form of Fourier modes (along the orbits of the images' rotations) multiplied by eigenvectors of certain matrices, which can be computed efficiently by the FFT. For image datasets corrupted by noise, we employ a subset of these eigenfunctions to ``filter"" the dataset via a Fourier-like filtering scheme, essentially using all images and their rotations simultaneously. We demonstrate our filtering framework by denoising simulated single-particle cryo-electron-microscopy image datasets.

Original languageEnglish
Pages (from-to)2254-2304
Number of pages51
JournalSIAM Journal on Imaging Sciences
Volume11
Issue number4
DOIs
StatePublished - 2018

Funding

FundersFunder number
National Institute of General Medical Sciences
Horizon 2020 Framework Programme723991
European Commission
Israel Science FoundationR01GM090200, 578/14
Horizon 2020

    Keywords

    • Graph Laplacian
    • Manifold denoising
    • Manifold learning
    • Rotation invariance
    • Steerable filters

    Fingerprint

    Dive into the research topics of 'The steerable graph Laplacian and its application to filtering image datasets'. Together they form a unique fingerprint.

    Cite this