Fast Steerable Principal Component Analysis

TL;DR

This paper presents a fast, accurate algorithm for steerable PCA that efficiently handles large 2D image datasets with rotations and reflections, significantly reducing computational complexity compared to existing methods.

Contribution

Introduces a novel steerable PCA algorithm utilizing Fourier-Bessel basis and non-uniform FFT, improving efficiency for large cryo-EM image datasets.

Findings

Computational complexity reduced to O(nL^3 + L^4)

Achieves comparable or better accuracy than traditional PCA

Significantly faster for large datasets

Abstract

Cryo-electron microscopy nowadays often requires the analysis of hundreds of thousands of 2D images as large as a few hundred pixels in each direction. Here we introduce an algorithm that efficiently and accurately performs principal component analysis (PCA) for a large set of two-dimensional images, and, for each image, the set of its uniform rotations in the plane and their reflections. For a dataset consisting of $n$ images of size $L \times L$ pixels, the computational complexity of our algorithm is $O(nL^3 + L^4)$, while existing algorithms take $O(nL^4)$. The new algorithm computes the expansion coefficients of the images in a Fourier-Bessel basis efficiently using the non-uniform fast Fourier transform. We compare the accuracy and efficiency of the new algorithm with traditional PCA and existing algorithms for steerable PCA.