Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
Recognition of nanoparticles on scanning probe microscopy images using computer vision and deep machine learning. / Okunev, Aleksey G.; Nartova, Anna V.; Matveev, Andrey V.
SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. стр. 940-943 8958363 (SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings).Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
}
TY - GEN
T1 - Recognition of nanoparticles on scanning probe microscopy images using computer vision and deep machine learning
AU - Okunev, Aleksey G.
AU - Nartova, Anna V.
AU - Matveev, Andrey V.
N1 - Publisher Copyright: © 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - Identifying and counting individual particles is an important component of many studies in various explorations. In the paper we present the results of the application of deep learning methods for the automated recognition of platinum nanoparticles deposited on highly oriented pyrolytic graphite (HOPG) on images obtained by scanning tunneling microscopy (STM). We used the neural network CascadeRCNN. The training was performed on a data set containing 10 STM images with 1918 nanoparticles. Five images containing 2052 nanoparticles were used for verification. As a result, the trained neural network recognized nanoparticles in verification set with 50.8% accuracy. Nanoparticles are specified as distinct contours, which are necessary for further determination of the particles dimensions (size, height etc). The obtained results were compared with the possibilities of other software products. The advantage of using deep machine learning methods for automatic particle recognition is clearly shown.
AB - Identifying and counting individual particles is an important component of many studies in various explorations. In the paper we present the results of the application of deep learning methods for the automated recognition of platinum nanoparticles deposited on highly oriented pyrolytic graphite (HOPG) on images obtained by scanning tunneling microscopy (STM). We used the neural network CascadeRCNN. The training was performed on a data set containing 10 STM images with 1918 nanoparticles. Five images containing 2052 nanoparticles were used for verification. As a result, the trained neural network recognized nanoparticles in verification set with 50.8% accuracy. Nanoparticles are specified as distinct contours, which are necessary for further determination of the particles dimensions (size, height etc). The obtained results were compared with the possibilities of other software products. The advantage of using deep machine learning methods for automatic particle recognition is clearly shown.
KW - deep neural networks
KW - nanoparticles
KW - particles recognition
KW - scanning tunneling microscopy
UR - http://www.scopus.com/inward/record.url?scp=85079065198&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/ed160936-7f32-3948-b616-ef1f46e33694/
U2 - 10.1109/SIBIRCON48586.2019.8958363
DO - 10.1109/SIBIRCON48586.2019.8958363
M3 - Conference contribution
T3 - SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings
SP - 940
EP - 943
BT - SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 International Multi-Conference on Engineering, Computer and Information Sciences, SIBIRCON 2019
Y2 - 21 October 2019 through 27 October 2019
ER -
ID: 23427305