Share Email Print

Proceedings Paper

Learning EP-net for identification and segmentation of scanning electron microscopic image
Author(s): Shuo Wang; Zhongyu Hou
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The vertical structure (VS) in nanosheet is important to electrical application because the VS in nanosheet determines the efficiency of solar cells, electrochemical biosensors and etc. The scanning electron microscopy (SEM) provides a way to observe the nanosheet structure; however, the identification of the structure is inaccuracy and when just from human justification. Deep learning gives an efficient method to identification and segmentation in an SEM image, which will enhance the precision. And the identification of VS is beneficial to get the relationship between the VS and electrical application from statistical viewpoint. In this paper we design a deep learning framework to detect the VS in the ZnO nanosheet, which overcomes two issues in the SEM: (i) the intensity inhomogeneity issue; (ii) the interference issue which is caused by other nano structures. And the experimental results exhibit height performance.

Paper Details

Date Published: 6 May 2019
PDF: 6 pages
Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 110693D (6 May 2019); doi: 10.1117/12.2524358
Show Author Affiliations
Shuo Wang, Shanghai Jiao Tong Univ. (China)
Zhongyu Hou, Shanghai Jiao Tong Univ. (China)

Published in SPIE Proceedings Vol. 11069:
Tenth International Conference on Graphics and Image Processing (ICGIP 2018)
Chunming Li; Hui Yu; Zhigeng Pan; Yifei Pu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?