Carlos Cabrera Sr.,1 Patricia Juárez,2 David Cervantes,1 Franklin Muñoz,1 Gustavo Hirata,3 Dora Luz Flores3
1Univ. Autónoma de Baja California (Mexico) 2Ctr. de Investigación Científica y de Educación Superior de Ensenada B.C. (Mexico) 3Univ. Nacional Autónoma de México (Mexico)
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
This work uses a deep learning approach using convolutional neural networks to locate and classify nanostructures in a heterogenous composition material from TEM imaging. We developed a methodology that allowed us to create 533 ground truth of TEM images with three different classes: 1) silicon oxide nanoparticles, 2) yttrium silicate particles and 3) silicon oxide coating. We performed the classification, location, and segmentation of chemical compounds reaching scores above 80% of accuracy using Mask R-CNN architecture with Anaconda Python 3.7 and the Tensorflow framework under Windows 10.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Carlos Cabrera Sr., Patricia Juárez, David Cervantes, Franklin Muñoz, Gustavo Hirata, Dora Luz Flores, "Deep learning to classify nanostructured materials with heterogeneous composition from transmission electron microscopy images," Proc. SPIE 11469, Emerging Topics in Artificial Intelligence 2020, 114691P (20 August 2020); https://doi.org/10.1117/12.2568626