Nanoparticle Detection on SEM Images Using a Neural Network and Semi-Synthetic Training Data

被引:7
作者
Lopez Gutierrez, Jorge David [1 ]
Abundez Barrera, Itzel Maria [1 ]
Torres Gomez, Nayely [1 ]
机构
[1] Tecnol Nacl Mexico, Div Estudios Posgrad & Invest, Inst Tecnol Toluca, Av Tecnol S-N, Mexico City 52149, DF, Mexico
关键词
scanning electron miscroscopy; nanoparticle detection; neural networks; synthetic data; yolov3; yolov4; SIZE;
D O I
10.3390/nano12111818
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Processing images represents a necessary step in the process of analysing the information gathered about nanoparticles after characteristic material samples have been scanned with electron microscopy, which often requires the use of image processing techniques or general purpose image manipulation software to carry out tasks such as nanoparticle detection and measurement. In recent years, the use of networks has been successfully implemented to detect and classify electron microscopy images as well as the objects within them. In this work, we present four detection models using two versions of the YOLO neural network architectures trained to detect cubical and quasi-spherical particles in SEM images; the training datasets are a mixture of real images and synthetic ones generated by a semi-arbitrary method. The resulting models were capable of detecting nanoparticles in images different than the ones used for training and identifying them in some cases as the close proximity between nanoparticles proved a challenge for the neural networks in most situations.
引用
收藏
页数:13
相关论文
共 20 条
[1]   The first annotated set of scanning electron microscopy images for nanoscience [J].
Aversa, Rossella ;
Modarres, Mohammad Hadi ;
Cozzini, Stefano ;
Ciancio, Regina ;
Chiusole, Alberto .
SCIENTIFIC DATA, 2018, 5
[2]  
Bochkovskiy A., 2004, ARXIV
[3]  
Carlueho J, 2018, IEEE INT C INT ROBOT, P2336, DOI 10.1109/IROS.2018.8594067
[4]   A deep learning approach using synthetic images for segmenting and estimating 3D orientation of nanoparticles in EM images [J].
Cid-Mejias, Anton ;
Alonso-Calvo, Raul ;
Gavilan, Helena ;
Crespo, Jose ;
Maojo, Victor .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2021, 202
[5]  
Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848
[6]   Determination of the average pore-size and total porosity in porous silicon layers by image processing of SEM micrographs [J].
Elia, Paz ;
Nativ-Roth, Einat ;
Zeiri, Yehuda ;
Porat, Ze'ev .
MICROPOROUS AND MESOPOROUS MATERIALS, 2016, 225 :465-471
[7]  
Field Kevin G., 2021, Microscopy and Microanalysis, V27, P2136, DOI [10.1017/s1431927621007704, 10.1017/S1431927621007704]
[8]   Machine vision-driven automatic recognition of particle size and morphology in SEM images [J].
Kim, Hyojin ;
Han, Jinkyu ;
Han, T. Yong-Jin .
NANOSCALE, 2020, 12 (37) :19461-19469
[9]  
Kundu S., 2015, 2015 IEEE INTERNATIONAL CONFERENCE ON ELECTRICAL, COMPUTER AND COMMUNICATION TECHNOLOGIES, DOI [10.1109/ICECCT.2015.7226104, DOI 10.1109/ICECCT.2015.7226104]
[10]  
Linmao Li, 2020, IOP Conference Series: Materials Science and Engineering, V782, DOI [10.1088/1757-899x/782/2/022035, 10.1088/1757-899X/782/2/022035]