Counting molecules: Python based scheme for automated enumeration and categorization of molecules in scanning tunneling microscopy images

Hellerstedt, Jack; Cahlík, Aleš; Švec, Martin; Stetsovych, Oleksandr; Hennen, T.

doi:10.1016/j.simpa.2022.100301

Cited by 6 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The user manually selects target molecules from the STM overview image and then starts the Auto-HR-AFM script. Target molecules can also be selected using a script that automatically finds molecules on the surface like the one used by Hellerstedt, 40 but considering these scripts can confuse similar molecules, and their performance is affected by other features on the surface; it is more robust to manually select the regions of interest. The order these molecules are selected will be the order the script will image them while in the loop.…”

Section: Auto-hr-afm's Decision Makingmentioning

confidence: 99%

Autonomous Molecular Structure Imaging with High-Resolution Atomic Force Microscopy for Molecular Mixture Discovery

et al. 2023

View full text Add to dashboard Cite

Due to its single-molecule sensitivity, high-resolution atomic force microscopy (HR-AFM) has proved to be a valuable and uniquely advantageous tool to study complex molecular mixtures, which hold promise for developing clean energy and achieving environmental sustainability. However, significant challenges remain to achieve the full potential of the sophisticated and time-consuming experiments. Automation combined with machine learning (ML) and artificial intelligence (AI) is key to overcoming these challenges. Here we present Auto-HR-AFM, an AI tool to automatically collect HR-AFM images of petroleum-based mixtures. We trained an instance segmentation model to teach Auto-HR-AFM how to recognize features in HR-AFM images. Auto-HR-AFM then uses that information to optimize the imaging by adjusting the probe-molecule distance for each molecule in the run. Auto-HR-AFM is the initial tool that will lead to fully automated scanning probe microscopy (SPM) experiments, from start to finish. This automation will allow SPM to become a mainstream characterization technique for complex mixtures, an otherwise unattainable target.

show abstract

Section: Auto-hr-afm's Decision Makingmentioning

confidence: 99%

Autonomous Molecular Structure Imaging with High-Resolution Atomic Force Microscopy for Molecular Mixture Discovery

et al. 2023

View full text Add to dashboard Cite

show abstract

“…It is also one of the libraries used in image processing, and in addition to its fast performance and the ability to add effects with simple code, the Mahotas library can dispense with the Nambay library as a helper library for reading images as arrays, as it reads them directly as an array, which simplifies the code and conversions even more [8]. 5) shows that most of the colors within the image are white or close to white, and this is what its seeing in the image that "contains many white areas.…”

Section: Mahotasmentioning

confidence: 99%

“…Figure 4: SimpleITK 4.6 MahotasIt is also one of the libraries used in image processing, and in addition to its fast performance and the ability to add effects with simple code, the Mahotas library can dispense with the Nambay library as a helper library for reading images as arrays, as it reads them directly as an array, which simplifies the code and conversions even more[8].…”

mentioning

confidence: 99%

Image Processing with Python Libraries

Asaad

Ali²,

Ali

et al. 2023

ACAD J NAWROZ UNIV

View full text Add to dashboard Cite

Today, computer vision is considered one of the most important sub-fields of artificial intelligence, due to the variety of its applications and capabilities to transfer the human ability to understand and describe a scene or image to the computer, so that it becomes able to recognize objects, shapes, colors, behavior and other capabilities of understanding the image. Image processing is one of the branches of computer science, and it is a way to perform some operations on an image in order to obtain an improved model for this image or extract some useful information from it. Often the data that is collected is primary data, meaning that it is not suitable for direct use in applications, so its need to analyze or pre-process it and then use it. For example: to build a data set that has been used in a model that classifies images as to whether they contain a house or not, depending on an image as input for this program. Our first step will be to collect hundreds of house images, but the problem is that these images will not be of the same dimensions, for example, so it’s to Change its dimensions, i.e., processing it in advance before submitting it to the model. The above is just one of the many reasons why image processing is important for any computer vision application

show abstract

“…Recently, machine learning techniques, particularly computer vision, have emerged as promising tools in material science research for automating the analysis and processing of image data [18][19][20][21][22][23][24][25]. Machine learning has achieved remarkable advancements even in the field of medical and biological sciences [26][27][28].…”

Section: Introductionmentioning

confidence: 99%

Applying a Deep-Learning-Based Keypoint Detection in Analyzing Surface Nanostructures

Yuan

Zhu

et al. 2023

Molecules

View full text Add to dashboard Cite

Scanning tunneling microscopy (STM) imaging has been routinely applied in studying surface nanostructures owing to its capability of acquiring high-resolution molecule-level images of surface nanostructures. However, the image analysis still heavily relies on manual analysis, which is often laborious and lacks uniform criteria. Recently, machine learning has emerged as a powerful tool in material science research for the automatic analysis and processing of image data. In this paper, we propose a method for analyzing molecular STM images using computer vision techniques. We develop a lightweight deep learning framework based on the YOLO algorithm by labeling molecules with its keypoints. Our framework achieves high efficiency while maintaining accuracy, enabling the recognitions of molecules and further statistical analysis. In addition, the usefulness of this model is exemplified by exploring the length of polyphenylene chains fabricated from on-surface synthesis. We foresee that computer vision methods will be frequently used in analyzing image data in the field of surface chemistry.

show abstract

Counting molecules: Python based scheme for automated enumeration and categorization of molecules in scanning tunneling microscopy images

Cited by 6 publications

References 16 publications

Autonomous Molecular Structure Imaging with High-Resolution Atomic Force Microscopy for Molecular Mixture Discovery

Autonomous Molecular Structure Imaging with High-Resolution Atomic Force Microscopy for Molecular Mixture Discovery

Image Processing with Python Libraries

Applying a Deep-Learning-Based Keypoint Detection in Analyzing Surface Nanostructures

Contact Info

Product

Resources

About