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.
In recent years deep learning has proved its ability to both extract object features and classifies them. Diffraction patterns from an aperture on screens play a central role on physical optics. Fourier transform of an aperture represents its diffraction pattern in the far-field. In this proposal we consider far-field diffraction patterns of non-symmetric apertures as objects to be recognized. For this purpose, we consider the MNIST dataset as apertures on a screen. Here the diffraction pattern of each aperture varies due to the variations of the digits in the data set. We present a model based on convolutional neural networks to classify far-field diffraction patterns whose accuracy is above 90%.
Pedro Arguijo andLizbeth A. Castañeda Escobar
"Deep learning as a tool to recognize diffraction patterns on the far field", Proc. SPIE 11830, Infrared Remote Sensing and Instrumentation XXIX, 1183005 (1 August 2021); https://doi.org/10.1117/12.2594930
ACCESS THE FULL ARTICLE
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.
The alert did not successfully save. Please try again later.
Pedro Arguijo, Lizbeth A. Castañeda Escobar, "Deep learning as a tool to recognize diffraction patterns on the far field," Proc. SPIE 11830, Infrared Remote Sensing and Instrumentation XXIX, 1183005 (1 August 2021); https://doi.org/10.1117/12.2594930