# US 2021/0263430 A1 · Metrology of semiconductor devices in electron micrographs using fast marching level sets

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0263430 A1
- Document ID: US20210263430A1
- Status: Published application
- Kind: A1
- Application number: 17/176,801
- Filed: 2021-02-16
- Published: 2021-08-26
- Earliest claimed: 2020-02-26
- Assignees: FEI Company
- Applicants: FEI Company
- Inventors: Umesh ADIGA
- Web page: https://patentgrep.com/patent/US20210263430A1

## CPC

- G03F 7/70666: {Aerial image, i.e. measuring the image of the patterned exposure light at the image plane of the projection system}
- G03F 7/70091: {Illumination settings, i.e. intensity distribution in the pupil plane or angular distribution in the field plane; On-axis or off-axis settings, e.g. annular, dipole or quadrupole settings; Partial coherence control, i.e. sigma or numerical aperture [NA]}
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/09: Supervised learning
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06T 7/0004: {Industrial image inspection}
- G06T 7/11: Region-based segmentation
- G06T 7/12: Edge-based segmentation
- G06T 7/149: involving deformable models, e.g. active contour models
- G06N 3/08: Learning methods
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N 20/20: Ensemble learning
- G06T 2207/10056: Microscopic image
- G06T 2207/10061: from scanning electron microscope
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30148: Semiconductor; IC; Wafer
- G03F: PHOTOMECHANICAL PRODUCTION OF TEXTURED OR PATTERNED SURFACES, e.g. FOR PRINTING, FOR PROCESSING OF SEMICONDUCTOR DEVICES; MATERIALS THEREFOR; ORIGINALS THEREFOR; APPARATUS SPECIALLY ADAPTED THEREFOR; (phototypographic composing devices B41B; photosensitive materials or processes for photographic purposes G03C; electrophotography, sensitive layers or processes therefor G03G)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Apparatuses and methods for metrology on devices using fast marching level sets are disclosed herein. An example method at least includes initiating a fast marching level set seed on an image, propagating a fast marching level set curve from the fast marching level set seed to locate boundaries of a plurality of regions of interest within the image, and performing metrology on the regions of interest based in part on the boundaries.

## Claims

### Claim 1

A method comprising:
initiating a fast marching level set seed on an image;
propagating a fast marching level set curve from the fast marching level set seed to locate boundaries of a plurality of regions of interest within the image; and
performing metrology on the regions of interest based in part on the boundaries.

### Claim 2 (depends on 1)

The method of claim 1, wherein initiating a fast marching level set seed on an image includes initiating one or more seed points within the image.

### Claim 3 (depends on 1)

The method of claim 1, wherein initiating a fast marching level set seed on an image includes initiating an enclosed seed curve within the image.

### Claim 4 (depends on 3)

The method of claim 3, wherein the enclosed curve is located around a perimeter of the image.

### Claim 5 (depends on 1)

The method of claim 1, wherein propagating a fast marching level set curve from the fast marching level set seed to locate boundaries of a plurality of regions of interest within the image includes:
constructing a speed function image of the image based on speed function algorithm; and
propagating the fast marching level set seed to determine the boundaries of the plurality of regions of interest within the image.

### Claim 6 (depends on 1)

The method of claim 1, further comprising;
preprocessing the image, wherein preprocessing an image includes:
improving signal to noise ratio of the image;
correcting brightness;
enhancing contrast; and
enhancing object boundaries.

### Claim 7 (depends on 6)

The method of claim 6, wherein the preprocessing is performed using a deep-learning based model, and wherein the deep-learning based model is a trainable nonlinear reaction-diffusion filter.

### Claim 8 (depends on 6)

The method of claim 6, wherein the preprocessed image includes sharp intensity gradient between different material layers and a smooth uniform background.

### Claim 9 (depends on 1)

The method of claim 1, further including:
optimizing the boundaries of the plurality of regions of interest based on active contours or level set algorithms.

### Claim 10 (depends on 1)

The method of claim 1, wherein the metrology is performed using a machine learning based model to determine measurements of one or more regions of interest of the plurality of regions of interest.

### Claim 11

An system comprising:
an electron microscope to acquire an image of a sample, the sample including a plurality of regions of interest;
a core, coupled to or included in the electron microscope, including code or coupled to code that, when executed by the core, causes the core to:
initiate a fast marching level set seed within the image;
propagate a fast marching level set curve from the fast marching level set seed to locate boundaries of each of the plurality of regions of interest within the image; and
perform metrology on the regions of interest based in part on the boundaries.

### Claim 12 (depends on 11)

The system of claim 11, wherein the code that, when executed by the core, causes the core to initiate a fast marching level set seed within the image further includes code that, when executed by the core, causes the core to initiate one or more seed points within the image.

### Claim 13 (depends on 11)

The system of claim 11, wherein the code that, when executed by the core, causes the core to initiate a fast marching level set seed within the image further includes code that, when executed by the core, causes the core to initiate an enclosed seed curve within the image.

### Claim 14 (depends on 13)

The system of claim 13, wherein the enclosed curve is located around a perimeter of the image.

### Claim 15 (depends on 11)

The system of claim 11, wherein the code that, when executed by the core, causes the core to propagate the fast marching level set curve from the fast marching level set seed to locate boundaries of the plurality of regions of interest within the image further includes code that, when executed by the core, causes the core to:
construct a speed function image of the image based on speed function algorithm; and
propagate the fast marching level set seed to determine the boundaries of the plurality of regions of interest within the image.

### Claim 16 (depends on 11)

The system of claim 11, wherein the code further includes code that, when executed by the core, causes the core to preprocess the image, wherein preprocessing the image includes one of:
improve signal to noise ratio of the image;
correct brightness;
enhance contrast; and
enhance object boundaries.

### Claim 17 (depends on 16)

The system of claim 16, wherein the core implements a deep-learning based model to preprocess the image.

### Claim 18 (depends on 17)

The system of claim 17, wherein the deep-learning based model is a nonlinear reaction-diffusion filter.

### Claim 19 (depends on 11)

The system of claim 11, wherein the code further includes code that, when executed by the core, causes the core to:
optimize the boundaries of the plurality of regions of interest based on active contours or level set algorithms.

### Claim 20 (depends on 11)

The system of claim 11, wherein the core implements a machine learning based model to perform the metrology.

### Claim 21 (depends on 20)

The system of claim 20, wherein the machine learning based model is one of a Bayesian-learning based model, classification tree based model, random forest based model, neural network based model and K-nearest neighbors based model.
