Metrology, Inspection, and Process Control for Semiconductor Manufacturing XXXV 2021
DOI: 10.1117/12.2592052
|View full text |Cite
|
Sign up to set email alerts
|

Evaluation of deep learning model for 3D profiling of HAR features using high-voltage CD-SEM

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4

Citation Types

0
6
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(6 citation statements)
references
References 0 publications
0
6
0
Order By: Relevance
“…In the case of in-line scanning electron microscopy (SEM), it is widely used for critical dimension (CD) measurements from top-down view images. The applications of CD-SEM also extend to profile measurements of HAR structure in 3D NAND as reported by Sun et al [1]. However, the total depth of the measurement structures reaches only 3.0μm.…”
Section: Introductionmentioning
confidence: 60%
“…In the case of in-line scanning electron microscopy (SEM), it is widely used for critical dimension (CD) measurements from top-down view images. The applications of CD-SEM also extend to profile measurements of HAR structure in 3D NAND as reported by Sun et al [1]. However, the total depth of the measurement structures reaches only 3.0μm.…”
Section: Introductionmentioning
confidence: 60%
“…In the case of in-line scanning electron microscopy (SEM), it is widely used for critical dimension (CD) measurements from top-down view images. The applications of CD-SEM also extend to profile measurements of HAR structure in 3D NAND as reported by Sun et al [2]. However, the total depth of the measurement structures reaches only 3.0μm.…”
Section: Introductionmentioning
confidence: 60%
“…This way, the excess material on defective features can be etched, or missing material can be deposited with sufficient precision. 5 Deep learning approaches [6][7][8][9] have already demonstrated almost flawless defect detection results. However, the extraction of repair shapes is still a challenge today.…”
Section: Introductionmentioning
confidence: 99%