All-optical image classification through unknown random diffusers using a single-pixel diffractive network

TL;DR

This paper introduces an all-optical, single-pixel classification system that uses a diffractive neural network to classify objects behind unknown diffusers with high accuracy, eliminating the need for digital processing.

Contribution

It presents a novel all-optical diffractive network capable of classifying objects through unknown diffusers using broadband light and a single pixel, reducing computational requirements.

Findings

Achieved 88.53% accuracy in classifying handwritten digits through unknown diffusers.

Demonstrated broadband operation across the electromagnetic spectrum.

Validated the system's effectiveness on unseen diffusers during testing.

Abstract

Classification of an object behind a random and unknown scattering medium sets a challenging task for computational imaging and machine vision fields. Recent deep learning-based approaches demonstrated the classification of objects using diffuser-distorted patterns collected by an image sensor. These methods demand relatively large-scale computing using deep neural networks running on digital computers. Here, we present an all-optical processor to directly classify unknown objects through unknown, random phase diffusers using broadband illumination detected with a single pixel. A set of transmissive diffractive layers, optimized using deep learning, forms a physical network that all-optically maps the spatial information of an input object behind a random diffuser into the power spectrum of the output light detected through a single pixel at the output plane of the diffractive network. We numerically demonstrated the accuracy of this framework using broadband radiation to classify unknown handwritten digits through random new diffusers, never used during the training phase, and achieved a blind testing accuracy of 88.53%. This single-pixel all-optical object classification system through random diffusers is based on passive diffractive layers that process broadband input light and can operate at any part of the electromagnetic spectrum by simply scaling the diffractive features proportional to the wavelength range of interest. These results have various potential applications in, e.g., biomedical imaging, security, robotics, and autonomous driving.