Enhancing subwavelength image recognition with resonant metamaterial lenses

In this work, we discuss our recent research advances in the field of subwavelength image recognition using deep learning tools. We show that combining locally-resonant metamaterial lenses with a deep learning technique that uses a multi-layered artificial neural network allows for direct recognition of subwavelength objects from an observer in the far-field, without complex calibration procedures. We will discuss the physics of deeply subwavelength image recognition, and the possibility to tailor the metamaterial lens to increase the conversion of evanescent fields to propagating fields that can reach the far field enhance the image recognition to 80% accuracy for objects as small as λ/10.


Advisor(s):
Fleury, Romain
Presented at:
URSI Commission B International Symposium on Electromagnetic Theory (EMTS 2019), San Diego, United Stated, 27-31 May 2019
Year:
May 19 2019
Keywords:
Dataset(s):
url: http://volta.sdsu.edu/~emts/emts_final_program.pdf
Laboratories:




 Record created 2019-06-05, last modified 2019-06-15


Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)