EUVIMEDEUVIMED entdecken
Crossref

Deep Learning, Feature Learning, and Clustering Analysis for SEM Image Classification

Rossella Aversa, Piero Coronica, Cristiano De Nobili, Stefano Cozzini

Data Intelligence · 2020-10 · 2 (4) · 513-528

DOI: 10.1162/dint_a_00062 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Data Intelligence, 2020-10. Verfasst von Rossella Aversa und 3 weiteren Autor:innen. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 14 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we report upon our recent work aimed at improving and adapting machine learning algorithms to automatically classify nanoscience images acquired by the Scanning Electron Microscope (SEM). This is done by coupling supervised and unsupervised learning approaches. We first investigate supervised learning on a ten-category data set of images and compare the performance of the different models in terms of training accuracy. Then, we reduce the dimensionality of the features through autoencoders to perform unsupervised learning on a subset of images in a selected range of scales (from 1 μm to 2 μm). Finally, we compare different clustering methods to uncover intrinsic structures in the images.

Zitieren

APA

Aversa, R., Coronica, P., Nobili, C. D., & Cozzini, S. (2020). Deep Learning, Feature Learning, and Clustering Analysis for SEM Image Classification. Data Intelligence, 2(4), 513-528. https://doi.org/10.1162/dint_a_00062

Vancouver

Aversa R, Coronica P, Nobili CD, Cozzini S. Deep Learning, Feature Learning, and Clustering Analysis for SEM Image Classification. Data Intelligence. 2020;2(4):513-528. doi:10.1162/dint_a_00062

BibTeX
@article{Aversa2020,
  author = {Aversa, Rossella and Coronica, Piero and Nobili, Cristiano De and Cozzini, Stefano},
  title = {Deep Learning, Feature Learning, and Clustering Analysis for SEM Image Classification},
  journal = {Data Intelligence},
  year = {2020},
  volume = {2},
  number = {4},
  pages = {513--528},
  doi = {10.1162/dint_a_00062}
}
Kostenlos starten →