scholarly journals Universal image segmentation for optical identification of 2D materials

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Randy M. Sterbentz ◽  
Kristine L. Haley ◽  
Joshua O. Island

AbstractMachine 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.

2011 ◽  
Vol 474-476 ◽  
pp. 442-447
Author(s):  
Zhi Gao Zeng ◽  
Li Xin Ding ◽  
Sheng Qiu Yi ◽  
San You Zeng ◽  
Zi Hua Qiu

In order to improve the accuracy of the image segmentation in video surveillance sequences and to overcome the limits of the traditional clustering algorithms that can not accurately model the image data sets which Contains noise data, the paper presents an automatic and accurate video image segmentation algorithm, according to the spatial properties, which uses the Gaussian mixture models to segment the image. But the expectation-maximization algorithm is very sensitive to initial values, and easy to fall into local optimums, so the paper presents a differential evolution-based parameters estimation for Gaussian mixture models. The experiment result shows that the segmentation accuracy has been improved greatly than by the traditional segmentation algorithms.


2018 ◽  
Author(s):  
Penny Perlepe ◽  
Rodolphe Clérac ◽  
Itziar Oyarzabal ◽  
Corine Mathonière

Nanophotonics ◽  
2020 ◽  
Vol 9 (16) ◽  
pp. 4719-4728
Author(s):  
Tao Deng ◽  
Shasha Li ◽  
Yuning Li ◽  
Yang Zhang ◽  
Jingye Sun ◽  
...  

AbstractThe molybdenum disulfide (MoS2)-based photodetectors are facing two challenges: the insensitivity to polarized light and the low photoresponsivity. Herein, three-dimensional (3D) field-effect transistors (FETs) based on monolayer MoS2 were fabricated by applying a self–rolled-up technique. The unique microtubular structure makes 3D MoS2 FETs become polarization sensitive. Moreover, the microtubular structure not only offers a natural resonant microcavity to enhance the optical field inside but also increases the light-MoS2 interaction area, resulting in a higher photoresponsivity. Photoresponsivities as high as 23.8 and 2.9 A/W at 395 and 660 nm, respectively, and a comparable polarization ratio of 1.64 were obtained. The fabrication technique of the 3D MoS2 FET could be transferred to other two-dimensional materials, which is very promising for high-performance polarization-sensitive optical and optoelectronic applications.


ACS Nano ◽  
2021 ◽  
Vol 15 (4) ◽  
pp. 7155-7167
Author(s):  
Alireza Taghizadeh ◽  
Kristian S. Thygesen ◽  
Thomas G. Pedersen

Sign in / Sign up

Export Citation Format

Share Document