IP Library Granted Patent US 12,633,495
Granted Patent B2
US 12,633,495 · App. 16/508,087 · Granted May 19, 2026

SEM image enhancement methods and systems

Inventors: Wei Fang (Milpitas, CA); Lingling Pu (San Jose, CA); Thomas Jarik Huisman (Eindhoven, NL); Erwin Paul Smakman (Eindhoven, NL)
Assignee: ASML Netherlands B.V.
H01J37/222G02B21/008G02B21/365G06N20/00G06T5/50G06T7/0002G06V10/454G06V10/82G06V20/695G06T2207/10061G06T2207/20081
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,633,495
App. No.
16/508,087
Granted
May 19, 2026
Kind
B2
Abstract

Systems and methods for image enhancement are disclosed. A method for enhancing an image may include acquiring a first scanning electron microscopy (SEM) image at a first resolution. The method may also include acquiring a second SEM image at a second resolution. The method may further include providing an enhanced image by using the first SEM image as a reference to enhance the second SEM image. The enhanced image may be provided by using one or more features extracted from the first image to enhance the second SEM image, or using the first SEM image as a reference to numerically enhance the second SEM image.

Claims (37)

1 . A method for enhancing an image, the method comprising:

scanning a wafer simultaneously using an on-axis beam and at least one off-axis beam of a multi-beam system;

acquiring a first scanning electron microscopy (SEM) image by use of the on-axis beam of the multi-beam system;

acquiring a second SEM image by use of the at least one off-axis beam of the multi-beam system, wherein the first SEM image acquired via the on-axis beam has a higher resolution than the second SEM image acquired via the at least one off-axis beam; and

providing an enhanced image, the enhanced image being provided by using the first SEM image as a reference to numerically enhance the second SEM image,

wherein numerically enhancing the second SEM image comprises numerically blurring data representing the first SEM image to match data representing the second SEM image.

2 . The method of claim 1 , wherein the enhanced image is provided by using one or more features extracted from the first SEM image to enhance the second SEM image.

3 . The method of claim 1 , further comprising:

extracting a trained feature from the first SEM image.

4 . The method of claim 1 , further comprising recognizing one or more features in the second SEM image as corresponding one or more features in the first SEM image based on a comparison between the numerically blurred data and the data representing the second SEM image.

5 . An inspection system, comprising:

a memory storing a set of instructions; and

a processor configured to execute the set of instructions to cause the inspection system to:

scan a wafer simultaneously using an on-axis beam and at least one off-axis beam of a multi-beam system;

acquire a first scanning electron microscopy (SEM) image by use of the on-axis beam of the multi-beam system;

acquire a second SEM image by use of the at least one off-axis beam of the multi-beam system, wherein the first SEM image acquired via the on-axis beam has a higher resolution than the second SEM image acquired via the at least one off-axis beam; and

provide an enhanced image, the enhanced image being provided by using the first SEM image as a reference to numerically enhance the second SEM image by numerically blurring data representing the first SEM image to match data representing the second SEM image.

6 . The system of claim 5 , wherein the enhanced image is provided by using one or more features extracted from the first SEM image to enhance the second SEM image.

7 . The system of claim 5 , wherein the processor is further configured to execute the set of instructions to cause the inspection system to:

extract a trained feature from the first SEM image.

8 . The system of claim 7 , wherein the trained feature is extracted from the first SEM image using a machine learning network.

9 . The system of claim 8 , wherein the processor is further configured to execute the set of instructions to cause the inspection system to:

acquire at least one additional SEM image by use of the on-axis beam; and

extract at least one additional trained feature from the at least one additional SEM image using the machine learning network.

10 . The system of claim 7 , wherein the processor is further configured to execute the set of instructions to cause the inspection system to:

extract pattern information of the second SEM image;

determine that the trained feature is identified on the second SEM image using the pattern information; and

in response to the determination that the trained feature is identified on the second SEM image, provide the enhanced image by enhancing the second SEM image using the identified trained feature.

11 . The system of claim 7 , wherein the processor is further configured to execute the set of instructions to cause the inspection system to acquire the first SEM image and extract the trained feature from the first SEM image in an offline mode.

12 . The system of claim 10 , wherein the determination that the trained feature is identified on the second SEM image includes a comparison of the pattern information and the trained feature.

13 . The system of claim 5 , wherein the processor is further configured to execute the set of instructions to cause the inspection system to:

analyze data representing the first SEM image to obtain one or more spatial-spectral characteristics; and

provide the enhanced image by applying one or more numerical compensations to data representing the second SEM image on the one or more spatial-spectral characteristics obtained.

14 . The system of claim 13 , wherein the one or more spatial-spectral characteristics obtained include phase and amplitude characteristics.

15 . The system of claim 13 , wherein the one or more numerical compositions are applied in a Fourier domain.

16 . The system of claim 13 , wherein the one or more numerical compensations deconvolve the second SEM image.

17 . The system of claim 5 , wherein the processor is further configured to execute the set of instructions to cause the inspection system to recognize one or more features in the second SEM image as corresponding one or more features in the first SEM image based on a comparison between the numerically blurred data and the data representing the second SEM image.

Assignments (4)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 25, 2024
From: HERMES MICROVISION INCORPORATED B.V.
To: ASML NETHERLANDS B.V.
Reel/Frame 068694/0077 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 25, 2024
From: HERMES MICROVISION, INC.
To: HERMES MICROVISION INCORPORATED B.V.
Reel/Frame 068693/0754 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 25, 2024
From: FANG, WEI; PU, LINGLING
To: HERMES MICROVISION, INC.
Reel/Frame 068693/0345 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 25, 2024
From: HUISMAN, THOMAS JARIK; SMAKMAN, ERWIN PAUL
To: ASML NETHERLANDS B.V.
Reel/Frame 068694/0358 →
Continuity (3)
Provisional Application 62786942 · Dec 31, 2018
Provisional Application 62697927 · Jul 13, 2018
Related Publication 20200018944A1 · Jan 16, 2020
References Cited (73)
US 5247588A · Komatsu · 1993 [cited by applicant]
US 5715334A · Peters · 1998 [cited by applicant]
US 6201240B1 · Dotan et al. · 2001 [cited by applicant]
US 6768543B1 · Aiyer · 2004 [cited by examiner]
US 6812462B1 · Toth · 2004 [cited by examiner]
US 8045145B1 · Bakker · 2011 [cited by examiner]
US 10169852B1 · Putman et al. · 2019 [cited by applicant]
US 20040000640A1 · Kazumori · 2004 [cited by examiner]
US 20040183014A1 · Kagawa · 2004 [cited by examiner]
US 20050214958A1 · Nakasuji · 2005 [cited by examiner]
US 20050263702A1 · Agemura · 2005 [cited by examiner]
US 20060097166A1 · Ishitani · 2006 [cited by examiner]
US 20080006771A1 · Tseng · 2008 [cited by examiner]
US 20080310704A1 · Tachibana et al. · 2008 [cited by applicant]
US 20090020698A1 · Muto · 2009 [cited by examiner]
US 20090322973A1 · Ito · 2009 [cited by examiner]
US 20100081217A1 · Nagano · 2010 [cited by examiner]
US 20100091362A1 · Isozaki et al. · 2010 [cited by applicant]
US 20100163728A1 · Ohtomo et al. · 2010 [cited by applicant]
US 20100183217A1 · Seung et al. · 2010 [cited by applicant]
US 20110187847A1 · Bai et al. · 2011 [cited by applicant]
US 20120320455A1 · Goruganthu · 2012 [cited by examiner]
US 20130248735A1 · Man · 2013 [cited by examiner]
US 20130335817A1 · Isobe et al. · 2013 [cited by applicant]
US 20140007308A1 · Reuter · 2014 [cited by examiner]
US 20140301630A1 · Kulkarni et al. · 2014 [cited by applicant]
US 20150034824A1 · Mori · 2015 [cited by examiner]
US 20150243474A1 · Lazic · 2015 [cited by examiner]
US 20160268096A1 · Ren et al. · 2016 [cited by applicant]
US 20160290934A1 · Wells · 2016 [cited by examiner]
US 20160300690A1 · Ikegami · 2016 [cited by examiner]
US 20170045722A1 · Fretel · 2017 [cited by examiner]
US 20170193680A1 · Zhang et al. · 2017 [cited by applicant]
US 20170194126A1 · Bhaskar et al. · 2017 [cited by applicant]
US 20170200260A1 · Bhaskar · 2017 [cited by examiner]
US 20170200265A1 · Bhaskar et al. · 2017 [cited by applicant]
US 20170213355A1 · Hujsak et al. · 2017 [cited by applicant]
US 20170345140A1 · Zhang · 2017 [cited by examiner]
US 20180065844A1 · Imhoff · 2018 [cited by examiner]
US 20180113292A1 · Novikau · 2018 [cited by examiner]
US 20180149603A1 · Bhattacharyya · 2018 [cited by examiner]
US 20180217065A1 · Haller · 2018 [cited by examiner]
US 20180308659A1 · Yamazawa · 2018 [cited by examiner]
US 20180342045A1 · Lutz et al. · 2018 [cited by applicant]
US 20180365535A1 · Gesley et al. · 2018 [cited by applicant]
US 20190005629A1 · Sharma · 2019 [cited by examiner]
US 20190087939A1 · Hakimuddin · 2019 [cited by examiner]
US 20190172675A1 · Masnaghetti · 2019 [cited by examiner]
US 20190294055A1 · Huisman et al. · 2019 [cited by applicant]
US 20190333199A1 · Ozcan · 2019 [cited by examiner]
US 20200126755A1 · Suzuki · 2020 [cited by examiner]
US 20200411281A1 · Yamaguchi · 2020 [cited by examiner]
CN 105023240A · 2015 [cited by applicant]
CN 108475417A · 2018 [cited by applicant]
CN 109863573A · 2019 [cited by applicant]
KR 1020050004786A · 2005 [cited by applicant]
KR 1020180001564A · 2018 [cited by applicant]
NL 2021802A1 · 2018 [cited by applicant]
TW 201624050A · 2016 [cited by applicant]
TW 201734895A · 2017 [cited by applicant]
TW 201816670A · 2018 [cited by applicant]
WO WO2009038838A2 · 2009 [cited by applicant]
WO WO2016176354A1 · 2016 [cited by applicant]
WO WO2017014442A1 · 2017 [cited by applicant]
WO WO2017053812A1 · 2017 [cited by applicant]
Faridian et al. Nanoscale imaging using deep ultraviolet digital holographic microscopy Optics Express Jun. 21, 2010 /vol. 18 No. 13 (Year: 2010). [cited by examiner]
Dr. Yougui Liao, “Practical Electron Microscopy and Database”, An Online Book, Second Edition (Year: 2006). [cited by examiner]
O'Quinn et al., “Image Quality Enhancement Using Machine Learning,” Southeastern 2018, IEEE, XP033413124, DOI: 10.1109/SECON.2018.8479289. [cited by applicant]
International Search Report issued by the International Searching Authority in related PCT International Application No. PCT/EP2019/067555, mailed Oct. 16, 2019 (5 pgs.). [cited by applicant]
Office Action issued by the Intellectual Property Office (IPO) in related ROC (Taiwan) Patent Application No. 108124273, mailed Mar. 13, 2020 (11 pgs.). [cited by applicant]
Office Action issued by the Intellectual Property Office of Taiwan in related Taiwanese Patent Application No. 109133909; mailed Aug. 4, 2021 (13 pgs.). [cited by applicant]
Notification of Reason(s) for Refusal issued by the Korean Patent Office in related Korean Patent Application No. 10-2021-7001092; mailed Jun. 21, 2023 (14 pgs.). [cited by applicant]
Notification of Reason(ss) for Refusal issued in related Korean Patent Application No. 10-2021-7001092; mailed Sep. 15, 2022 (8 pgs.). [cited by applicant]