Obtaining high-resolution images using an optical microscope is critical when dealing with micro/nanoscale objects. Current techniques use high magnification objective lenses with high numerical apertures to resolve closely spaced objects at the micron/nanoscale. However, these lenses often require additional optics and have a narrow depth of field, preventing ease of use. To date, scanning electron microscopy (SEM) is used for imaging beyond the diffraction limit and has led to various breakthroughs in semiconductor physics and nanotechnology. An alternative to an SEM is using artificial intelligence (AI) to enable super-resolution techniques with correlated image sets. We utilize a convolutional neural network (CNN) and generative adversarial network (GAN) to train correlated images gathered from higher magnification SEM and lower magnification SEM, resulting in a model that enables resolving nanoscale features. We demonstrated that by training a neural network with SEM images, we are able to aid the optical microscope to image beyond the diffraction limit with a resolution closer to the SEM.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.