Universal image segmentation for optical identification of 2D materials

TL;DR

This paper introduces a universal image segmentation tool using unsupervised clustering algorithms to automatically identify the thickness of 2D materials in optical microscopy images with high accuracy, applicable to various substrates.

Contribution

The method uniquely preserves all color channels and employs Gaussian mixture models, enabling universal and automatic 2D material identification across diverse substrates.

Findings

Achieves approximately 95% pixel accuracy in thickness identification.

Works on both opaque and transparent substrates.

Uses all three color channels for improved generality.

Abstract

Machine learning methods are changing the way data is analyzed. One of the most powerful and widespread applications of these techniques is in image segmentation wherein disparate objects of a digital image are partitioned and classified. Here we present an image segmentation program incorporating a series of unsupervised clustering algorithms for the automatic thickness identification of two-dimensional materials from digital optical microscopy images. The program identifies mono- and few-layer flakes of a variety of materials on both opaque and transparent substrates with a pixel accuracy of roughly 95%. Contrasting with previous attempts, application generality is achieved through preservation and analysis of all three digital color channels and Gaussian mixture model fits to arbitrarily shaped data clusters. Our results provide a facile implementation of data clustering for the universal, automatic identification of two-dimensional materials exfoliated onto any substrate.