L+S (FC-RPCA) Foreground-Background OCT Segmentation

McLean, James Patrick; Hendon, Christine P.

We present a variant on the robust-principal component analysis (RPCA) algorithm, called frequency constrained RPCA (FC-RPCA), for selectively segmenting dynamic phenomena that exhibit spectra within a user-defined range of frequencies. The algorithm lacks subjective parameter tuning and demonstrates robust segmentation in datasets containing multiple motion sources and high amplitude noise. This algorithm was designed to be used with time-lapse Optical Coherence Tomography (OCT) datasets that capture sub-resolution motion. Specifically demonstrated for cilia.


Also Published In

More About This Work

Academic Units
Electrical Engineering
Published Here
February 16, 2021


Keywords: sparse representations, L+S, RPCA, cilia, segmentation, background decomposition, OCT, image processing.