A convolutional neural network (CNN) classifier is trained using simulated energy-dispersive spectroscopy data. The CNN incorporated within a dynamic sampling method is to reduce radiation exposure and data acquisition time for elemental mapping.

© 2017 Optical Society of America

PDF Article


You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
Login to access OSA Member Subscription