Design of Scale-, Shift- and Rotation-Invariant Diffractive Optical Networks

Deniz Mengu; Yair Rivenson; Aydogan Ozcan

doi:10.1117/12.2594887

1 August 2021 Design of Scale-, Shift- and Rotation-Invariant Diffractive Optical Networks

Deniz Mengu, Yair Rivenson, Aydogan Ozcan

Proceedings Volume 11804, Emerging Topics in Artificial Intelligence (ETAI) 2021; 118040G (2021) https://doi.org/10.1117/12.2594887
Event: SPIE Nanoscience + Engineering, 2021, San Diego, California, United States

Abstract

We quantify the sensitivity of diffractive optical networks’ inference accuracy against input object variations in the form of translation, rotation, and scaling, and present a new training methodology that enables diffractive networks to maintain their classification performance despite such object variations at the input field-of-view. Our analyses on all-optical classification of handwritten digits reveal that this new training scheme provides blind inference accuracy gains of >50%, >30% and >30% for randomly shifted, rotated and scaled input objects, respectively, demonstrating its efficacy. These results are important for using diffractive optical networks in various machine vision applications involving dynamic objects and environments.

Conference Presentation

Citation Download Citation

Deniz Mengu, Yair Rivenson, and Aydogan Ozcan "Design of Scale-, Shift- and Rotation-Invariant Diffractive Optical Networks", Proc. SPIE 11804, Emerging Topics in Artificial Intelligence (ETAI) 2021, 118040G (1 August 2021); https://doi.org/10.1117/12.2594887

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
PRESENTATION

WATCH
PRESENTATION SAVE TO MY LIBRARY

GET CITATION

KEYWORDS

Optical networks

Light-matter interactions

Machine learning

Machine vision

Neural networks

Scene classification

Statistical inference

RELATED CONTENT

Time-lapse image classification using a diffractive optical network
Proceedings of SPIE (January 01 1900)

A remote sensing image scene classification framework based Efficientnet-b7
Proceedings of SPIE (December 09 2021)

Diffractive optical networks with scale, shift, and rotation invariance
Proceedings of SPIE (January 01 1900)

Ensemble learning boosts the inference accuracy of diffractive neural networks
Proceedings of SPIE (January 01 1900)

Diffractive network-based single-pixel machine vision
Proceedings of SPIE (January 01 1900)

Reliable flaw classifiers for machine vision-based quality control
Proceedings of SPIE (October 03 1995)

Aflatoxin contaminated chili pepper detection by hyperspectral imaging and machine...
Proceedings of SPIE (June 02 2011)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years