Deep learning as a tool to recognize diffraction patterns on the far field

Pedro Arguijo; Lizbeth A. Castañeda Escobar

doi:10.1117/12.2594930

1 August 2021 Deep learning as a tool to recognize diffraction patterns on the far field

Pedro Arguijo, Lizbeth A. Castañeda Escobar

Proceedings Volume 11830, Infrared Remote Sensing and Instrumentation XXIX; 1183005 (2021) https://doi.org/10.1117/12.2594930
Event: SPIE Optical Engineering + Applications, 2021, San Diego, California, United States

Abstract

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%.

Conference Presentation

Citation Download Citation

Pedro Arguijo and 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

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

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.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available