Structure assisted compressed sensing reconstruction of undersampled AFM images

Oxvig, Christian Schou; Arildsen, Thomas; Larsen, Torben

doi:10.1016/j.ultramic.2016.09.011

Cited by 33 publications

(27 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accordingly, we present two methods for reconstructing sparse PFM spiral scans: 1) compressive sensing [ 54–60 ] (CS) and 2) Gaussian process [ 61–65 ] (GP) regression. The compressive sensing image inpainting algorithm requires two inputs: 1) The sparse and noisy measurements y , and 2) the scanning mask indicating sampled pixel locations.…”

Section: Introductionmentioning

confidence: 99%

Fast Scanning Probe Microscopy via Machine Learning: Non‐Rectangular Scans with Compressed Sensing and Gaussian Process Optimization

Kelley

Ziatdinov

Collins

et al. 2020

Small

View full text Add to dashboard Cite

Fast scanning probe microscopy enabled via machine learning allows for a broad range of nanoscale, temporally resolved physics to be uncovered. However, such examples for functional imaging are few in number. Here, using piezoresponse force microscopy (PFM) as a model application, a factor of 5.8 reduction in data collection using a combination of sparse spiral scanning with compressive sensing and Gaussian process regression reconstruction is demonstrated. It is found that even extremely sparse spiral scans offer strong reconstructions with less than 6% error for Gaussian process regression reconstructions. Further, the error associated with each reconstructive technique per reconstruction iteration is analyzed, finding the error is similar past ≈15 iterations, while at initial iterations Gaussian process regression outperforms compressive sensing. This study highlights the capabilities of reconstruction techniques when applied to sparse data, particularly sparse spiral PFM scans, with broad applications in scanning probe and electron microscopies.

show abstract

Section: Introductionmentioning

confidence: 99%

Fast Scanning Probe Microscopy via Machine Learning: Non‐Rectangular Scans with Compressed Sensing and Gaussian Process Optimization

Kelley

Ziatdinov

Collins

et al. 2020

Small

View full text Add to dashboard Cite

show abstract

“…The clear advantage of a coarse raster scan is that its implementation only requires adjustments to the data collection and post-processing. • The bulk of this work is based on experiment, not simulation, in contrast to prior work by ourselves [33], [35] and others [38]- [40]. Our main focus here is on delineating the practical issues which must be addressed to effectively realize µ-path scanning, which has only seen limited attention in the past.…”

Section: Introductionmentioning

confidence: 99%

Improving the Image Acquisition Rate of an Atomic Force Microscope Through Spatial Subsampling and Reconstruction

Braker

Luo

Pao

et al. 2020

IEEE/ASME Trans. Mechatron.

View full text Add to dashboard Cite

Undersampling-based approaches in Atomic Force Microscopy (AFM) aim to reduce the time to acquire an image by reducing the number of measurements needed while still maintaining image quality. The approach consists of two components: data acquisition and image reconstruction. Successful practical implementation involves solving a variety of non-trivial problems. In this paper, we describe an implementation based on a collection of short scans known as µ-paths, and we demonstrate it on a commercial AFM using a grating sample. Reconstructions are made from the data using a new variant of basis pursuit designed to reduce artifacts arising from the sampling pattern. The quality of the resulting images is compared to images from standard raster scans of the same regions at comparable imaging rates using both the peak signal-to-noise ratio and the structured similarity index metric and a new metric we call the relative damage index. We also compare to simple subline sampling where only a subset of the rows of the image are acquired (followed by reconstruction). These experiments show that at low sampling densities and slow scan rates, µ-path scanning achieves better image quality in less time than subline sampling. Conversely, for faster scan rates subline sampling is faster and, for higher sampling densities, achieves comparable image quality.

show abstract

“…The identification process of noisy pixels can be seen as compressed sampling. However, it is impossible to ensure that the process meets the demand of theoretical reconstruction guarantees [20–21]. Bayesian compressed sensing (BCS) [22] provides a better reconstruction performance than other methods when the theoretical reconstruction guarantees are partially destroyed [23].…”

Section: Introductionmentioning

confidence: 99%

A novel method to remove impulse noise from atomic force microscopy images based on Bayesian compressed sensing

Zhang¹,

Li²,

Song³

et al. 2019

Beilstein J. Nanotechnol.

View full text Add to dashboard Cite

A novel method based on Bayesian compressed sensing is proposed to remove impulse noise from atomic force microscopy (AFM) images. The image denoising problem is transformed into a compressed sensing imaging problem of the AFM. First, two different ways, including interval approach and self-comparison approach, are applied to identify the noisy pixels. An undersampled AFM image is generated by removing the noisy pixels from the image. Second, a series of measurement matrices, all of which are identity matrices with some rows removed, are constructed by recording the position of the noise-free pixels. Third, the Bayesian compressed sensing reconstruction algorithm is applied to recover the image. Different from traditional compressed sensing reconstruction methods in AFM, each row of the AFM image is reconstructed separately in the proposed method, which will not reduce the quality of the reconstructed image. The denoising experiments are conducted to demonstrate that the proposed method can remove the impulse noise from AFM images while preserving the details of the image. Compared with other methods, the proposed method is robust and its performance is not influenced by the noise density in a certain range.

show abstract

Structure assisted compressed sensing reconstruction of undersampled AFM images

Cited by 33 publications

References 39 publications

Fast Scanning Probe Microscopy via Machine Learning: Non‐Rectangular Scans with Compressed Sensing and Gaussian Process Optimization

Fast Scanning Probe Microscopy via Machine Learning: Non‐Rectangular Scans with Compressed Sensing and Gaussian Process Optimization

Improving the Image Acquisition Rate of an Atomic Force Microscope Through Spatial Subsampling and Reconstruction

A novel method to remove impulse noise from atomic force microscopy images based on Bayesian compressed sensing

Contact Info

Product

Resources

About