Revisiting Fourier-Based Reflection Spectrum Measurement in Coherence Scanning Interferometry

TL;DR

This paper revisits Fourier-based reflection spectrum measurement in coherence scanning interferometry, establishing a generalized framework and analyzing error impacts, with phase change on reflection identified as the dominant factor affecting accuracy.

Contribution

It introduces a matrix-based mathematical model for CSI reflection spectrum measurement and evaluates various error sources affecting spectrum reconstruction accuracy.

Findings

Phase change on reflection significantly impacts spectrum reconstruction.

The generalized model extends Fourier-based methods beyond low NA systems.

Simulation results quantify effects of NA, spectral inaccuracies, and errors on measurement accuracy.

Abstract

Recent advancements have extended the capabilities of coherence scanning interferometry (CSI) beyond surface topography measurement to reflectivity spectrum imaging. It is commonly accepted that the one-dimensional(1-D) Fourier magnitude of a pixel-wise CSI signal is proportional to the product of the sample's absolute reflection coefficient spectrum and the light source spectrum. However, this assumption holds true only for low numerical aperture (NA) CSI systems. In this work, we establish a generalized mathematical framework that represents the CSI signal a matrix multiplication of the spectrum measurement matrix with the element-wise product of the reflection spectrum and the light source spectrum, assuming spectral independence from the incident angles. Considering the light source spectrum and wavenumber channel summation, we utilize a reflection spectrum measurement matrix and its conditioned counterpart to linearly relate the CSI signal to the absolute reflection spectrum. Through simulations, we quantitatively analyze the impacts of various error sources, including NA inaccuracy, pupil apodization, height reconstruction errors, spectral inaccuracies of the light source, and phase change on reflection (PCOR) from the sample, on the reconstruction performance of the absolute reflection coefficient spectrum. It is found that the PCOR is the dominant factor influencing the reconstruction of the reflection coefficient spectrum.