Nanoparticle Recognition on Scanning Probe Microscopy Images Using Computer Vision and Deep Learning | Sciact - CRIS-система Института катализа

Nanoparticle Recognition on Scanning Probe Microscopy Images Using Computer Vision and Deep Learning Научная публикация

Журнал

Nanomaterials
, E-ISSN: 2079-4991

Вых. Данные

Год: 2020, Том: 10, Номер: 7, Номер статьи : 1285, Страниц : 16 DOI: 10.3390/nano10071285

Ключевые слова

particle recognition; deep neural networks; scanning tunneling microscopy; particles

Авторы

Okunev Alexey G. ^1,2 , Mashukov Mikhail Yu. ³ , Nartova Anna V. ^2,3 , Matveev Andrey V. ^2,3

Организации

1	Novosibirsk State University Higher College of Informatics, Russkaja Str. 35, 630058 Novosibirsk, Russia
2	Boreskov Institute of Catalysis SB RAS, pr. Acad. Lavrentieva, 5, 630090 Novosibirsk, Russia
3	Scientific-Educational Center “Machine Learning and Big Data Analysis”, Novosibirsk State University, Pirogova Str. 1, 630090 Novosibirsk, Russia

Информация о финансировании (1)

Федеральное агентство научных организаций России

0303-2016-0001

Identifying, counting and measuring particles is an important component of many research studies. Images with particles are usually processed by hand using a software ruler. Automated processing, based on conventional image processing methods (edge detection, segmentation, etc.) are not universal, can only be used on good-quality images and need to set a number of parameters empirically. In this paper, we present results from the application of deep learning to automated recognition of metal nanoparticles deposited on highly oriented pyrolytic graphite on images obtained by scanning tunneling microscopy (STM). We used the Cascade Mask-RCNN neural network. Training was performed on a data set containing 23 STM images with 5157 nanoparticles. Three images containing 695 nanoparticles were used for verification. As a result, the trained neural network recognized nanoparticles in the verification set with 0.93 precision and 0.78 recall. Predicted contour refining with 2D Gaussian function was a proposed option. The accuracies for mean particle size calculated from predicted contours compared with ground truth were in the range of 0.87–0.99. The results were compared with outcomes from other generally available software, based on conventional image processing methods. The advantages of deep learning methods for automatic particle recognition were clearly demonstrated. We developed a free open-access web service “ParticlesNN” based on the trained neural network, which can be used by any researcher in the world.

Okunev A.G. , Mashukov M.Y. , Nartova A.V. , Matveev A.V.
Nanoparticle Recognition on Scanning Probe Microscopy Images Using Computer Vision and Deep Learning

Nanomaterials. 2020. V.10. N7. 1285 :1-16. DOI: 10.3390/nano10071285 WOS Scopus РИНЦ CAPlus PMID OpenAlex

Полный текст от издателя

Поступила в редакцию:	11 июн. 2020 г.
Принята к публикации:	26 июн. 2020 г.
Опубликована online:	30 июн. 2020 г.
Опубликована в печати:	1 июл. 2020 г.

Web of science:	WOS:000556472600001
Scopus:	2-s2.0-85087371596
РИНЦ:	43303223
Chemical Abstracts:	2020:1587336
PMID (PubMed):	32629955
OpenAlex:	W3039460860

БД	Цитирований
Scopus	61
РИНЦ	55
Web of science	56
OpenAlex	67