Anna V. Nartova , Andrey V. Matveev , Larisa M. Kovtunova , Aleksey G. Okunev
{"title":"Deep machine learning for STEM image analysis","authors":"Anna V. Nartova , Andrey V. Matveev , Larisa M. Kovtunova , Aleksey G. Okunev","doi":"10.1016/j.mencom.2024.10.002","DOIUrl":null,"url":null,"abstract":"<div><div>The universal, user-friendly online iOk Platform for automatic recognition of any type of objects in images based on deep machine learning is presented. Services aggregated in the iOk Platform significantly reduce the time spent on quantitative image analysis, decrease the influence of the subjective factor and increase the accuracy of the analysis by expanding the set of data that can be analyzed automatically. It is shown how the services can be used to analyze scanning transmission electron microscopy images obtained in heterogeneous catalysis studies, allowing for measurements of thousands of objects in an image, as well as simultaneous analysis of objects of different types, namely: nanoparticles and single sites.</div></div>","PeriodicalId":18542,"journal":{"name":"Mendeleev Communications","volume":"34 6","pages":"Pages 774-775"},"PeriodicalIF":1.8000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Mendeleev Communications","FirstCategoryId":"92","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0959943624003006","RegionNum":4,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
The universal, user-friendly online iOk Platform for automatic recognition of any type of objects in images based on deep machine learning is presented. Services aggregated in the iOk Platform significantly reduce the time spent on quantitative image analysis, decrease the influence of the subjective factor and increase the accuracy of the analysis by expanding the set of data that can be analyzed automatically. It is shown how the services can be used to analyze scanning transmission electron microscopy images obtained in heterogeneous catalysis studies, allowing for measurements of thousands of objects in an image, as well as simultaneous analysis of objects of different types, namely: nanoparticles and single sites.
期刊介绍:
Mendeleev Communications is the journal of the Russian Academy of Sciences, launched jointly by the Academy of Sciences of the USSR and the Royal Society of Chemistry (United Kingdom) in 1991. Starting from 1st January 2007, Elsevier is the new publishing partner of Mendeleev Communications.
Mendeleev Communications publishes short communications in chemistry. The journal primarily features papers from the Russian Federation and the other states of the former USSR. However, it also includes papers by authors from other parts of the world. Mendeleev Communications is not a translated journal, but instead is published directly in English. The International Editorial Board is composed of eminent scientists who provide advice on refereeing policy.