Single pixel image classification using an ultrafast digital light projector

Tools

Kanwal, Aisha and Johnstone, Graeme E. and Dehkhoda, Fahimeh and Herrnsdorf, Johannes H. and Henderson, Robert K. and Dawson, Martin D. and Porte, Xavier and Strain, Michael J. (2026) Single pixel image classification using an ultrafast digital light projector. Other. arXiv. (https://doi.org/10.48550/arXiv.2603.12036)

[thumbnail of Kanwal-etal-arXiv-2026-Single-pixel-image-classification-using-an-ultrafast-digital-light-projector]
Preview
 Text. Filename: Kanwal-etal-arXiv-2026-Single-pixel-image-classification-using-an-ultrafast-digital-light-projector.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (1MB)| Preview

Abstract

Pattern recognition and image classification are essential tasks in machine vision. Autonomous vehicles, for example, require being able to collect the complex information contained in a changing environment and classify it in real time. Here, we experimentally demonstrate image classification at multi-kHz frame rates combining the technique of single pixel imaging (SPI) with a low complexity machine learning model. The use of a microLED-on-CMOS digital light projector for SPI enables ultrafast pattern generation for sub-ms image encoding. We investigate the classification accuracy of our experimental system against the broadly accepted benchmarking task of the MNIST digits classification. We compare the classification performance of two machine learning models: An extreme learning machine (ELM) and a backpropagation trained deep neural network. The complexity of both models is kept low so the overhead added to the inference time is comparable to the image generation time. Crucially, our single pixel image classification approach is based on a spatiotemporal transformation of the information, entirely bypassing the need for image reconstruction. By exploring the performance of our SPI based ELM as binary classifier we demonstrate its potential for efficient anomaly detection in ultrafast imaging scenarios.

ORCID iDs

Kanwal, Aisha ORCID logoORCID: https://orcid.org/0009-0003-4257-8847, Johnstone, Graeme E. ORCID logoORCID: https://orcid.org/0000-0001-5471-4664, Dehkhoda, Fahimeh, Herrnsdorf, Johannes H. ORCID logoORCID: https://orcid.org/0000-0002-3856-5782, Henderson, Robert K., Dawson, Martin D. ORCID logoORCID: https://orcid.org/0000-0002-6639-2989, Porte, Xavier ORCID logoORCID: https://orcid.org/0000-0002-9869-7170 and Strain, Michael J. ORCID logoORCID: https://orcid.org/0000-0002-9752-3144;
CORE (COnnecting REpositories)