Adaptive Optimizable Gaussian Process Regression Linear Least Squares Regression Filtering Method for SEM Images

Scanning Electron Microscopy (SEM) images often suffer from noise contamination, which degrades image quality and affects further analysis. This research presents a complete approach to estimate their Signal-to-Noise Ratio (SNR) and noise variance (NV), and enhance image quality using NV-guided Wien...

Full description

Saved in:
Bibliographic Details
Main Authors: Dominic Chee Yong Ong, Iksan Bukhori, Kok Swee Sim, Kok Beng Gan
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11015481/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850230646444654592
author Dominic Chee Yong Ong
Iksan Bukhori
Kok Swee Sim
Kok Beng Gan
author_facet Dominic Chee Yong Ong
Iksan Bukhori
Kok Swee Sim
Kok Beng Gan
author_sort Dominic Chee Yong Ong
collection DOAJ
description Scanning Electron Microscopy (SEM) images often suffer from noise contamination, which degrades image quality and affects further analysis. This research presents a complete approach to estimate their Signal-to-Noise Ratio (SNR) and noise variance (NV), and enhance image quality using NV-guided Wiener filter. The main idea of this study is to use a good SNR estimation technique and infuse a machine learning model to estimate NV of the SEM image, which then guides the wiener filter to remove the noise, providing a more robust and accurate SEM image filtering pipeline. First, we investigate five different SNR estimation techniques, namely Nearest Neighbourhood (NN) method, First-Order Linear Interpolation (FOL) method, Nearest Neighbourhood with First-Order Linear Interpolation (NN+FOL) method, Non-Linear Least Squares Regression (NLLSR) method, and Linear Least Squares Regression (LSR) method. It is shown that LSR method to perform better than the rest. Then, Support Vector Machines (SVM) and Gaussian Process Regression (GPR) are tested by pairing it with LSR. In this test, the Optimizable GPR model shows the highest accuracy and it stands as the most effective solution for NV estimation. Combining these results lead to the proposed Adaptive Optimizable Gaussian Process Regression Linear Least Squares Regression (AO-GPRLLSR) Filtering pipeline. The AO-GPRLLSR method generated an estimated noise variance which served as input to NV-guided Wiener filter for improving the quality of SEM images. The proposed method is shown to achieve notable success in estimating SNR and NV of SEM images and leads to lower Mean Squared Error (MSE) after the filtering process.
format Article
id doaj-art-b72f8e294b764ee2bbffb9e671389336
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-b72f8e294b764ee2bbffb9e6713893362025-08-20T02:03:47ZengIEEEIEEE Access2169-35362025-01-0113935749359210.1109/ACCESS.2025.357338911015481Adaptive Optimizable Gaussian Process Regression Linear Least Squares Regression Filtering Method for SEM ImagesDominic Chee Yong Ong0https://orcid.org/0009-0002-9373-5657Iksan Bukhori1https://orcid.org/0000-0001-8216-5607Kok Swee Sim2https://orcid.org/0000-0003-2976-8825Kok Beng Gan3https://orcid.org/0000-0002-8776-5502Faculty of Engineering and Technology, Multimedia University, Melaka, MalaysiaDepartment of Electrical Engineering, Faculty of Engineering, President University, Bekasi, IndonesiaFaculty of Engineering and Technology, Multimedia University, Melaka, MalaysiaDepartment of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, Bangi, MalaysiaScanning Electron Microscopy (SEM) images often suffer from noise contamination, which degrades image quality and affects further analysis. This research presents a complete approach to estimate their Signal-to-Noise Ratio (SNR) and noise variance (NV), and enhance image quality using NV-guided Wiener filter. The main idea of this study is to use a good SNR estimation technique and infuse a machine learning model to estimate NV of the SEM image, which then guides the wiener filter to remove the noise, providing a more robust and accurate SEM image filtering pipeline. First, we investigate five different SNR estimation techniques, namely Nearest Neighbourhood (NN) method, First-Order Linear Interpolation (FOL) method, Nearest Neighbourhood with First-Order Linear Interpolation (NN+FOL) method, Non-Linear Least Squares Regression (NLLSR) method, and Linear Least Squares Regression (LSR) method. It is shown that LSR method to perform better than the rest. Then, Support Vector Machines (SVM) and Gaussian Process Regression (GPR) are tested by pairing it with LSR. In this test, the Optimizable GPR model shows the highest accuracy and it stands as the most effective solution for NV estimation. Combining these results lead to the proposed Adaptive Optimizable Gaussian Process Regression Linear Least Squares Regression (AO-GPRLLSR) Filtering pipeline. The AO-GPRLLSR method generated an estimated noise variance which served as input to NV-guided Wiener filter for improving the quality of SEM images. The proposed method is shown to achieve notable success in estimating SNR and NV of SEM images and leads to lower Mean Squared Error (MSE) after the filtering process.https://ieeexplore.ieee.org/document/11015481/Image processingscanning electron microscope (SEM)noise variance estimationsignal-to-noise ratio (SNR)SNR estimationmachine learning
spellingShingle Dominic Chee Yong Ong
Iksan Bukhori
Kok Swee Sim
Kok Beng Gan
Adaptive Optimizable Gaussian Process Regression Linear Least Squares Regression Filtering Method for SEM Images
IEEE Access
Image processing
scanning electron microscope (SEM)
noise variance estimation
signal-to-noise ratio (SNR)
SNR estimation
machine learning
title Adaptive Optimizable Gaussian Process Regression Linear Least Squares Regression Filtering Method for SEM Images
title_full Adaptive Optimizable Gaussian Process Regression Linear Least Squares Regression Filtering Method for SEM Images
title_fullStr Adaptive Optimizable Gaussian Process Regression Linear Least Squares Regression Filtering Method for SEM Images
title_full_unstemmed Adaptive Optimizable Gaussian Process Regression Linear Least Squares Regression Filtering Method for SEM Images
title_short Adaptive Optimizable Gaussian Process Regression Linear Least Squares Regression Filtering Method for SEM Images
title_sort adaptive optimizable gaussian process regression linear least squares regression filtering method for sem images
topic Image processing
scanning electron microscope (SEM)
noise variance estimation
signal-to-noise ratio (SNR)
SNR estimation
machine learning
url https://ieeexplore.ieee.org/document/11015481/
work_keys_str_mv AT dominiccheeyongong adaptiveoptimizablegaussianprocessregressionlinearleastsquaresregressionfilteringmethodforsemimages
AT iksanbukhori adaptiveoptimizablegaussianprocessregressionlinearleastsquaresregressionfilteringmethodforsemimages
AT koksweesim adaptiveoptimizablegaussianprocessregressionlinearleastsquaresregressionfilteringmethodforsemimages
AT kokbenggan adaptiveoptimizablegaussianprocessregressionlinearleastsquaresregressionfilteringmethodforsemimages